{ "generated_at": "2026-10-19T07:14:45.213Z", "provider_count": 11, "providers": [ { "id": "1", "slug": "tinfoil", "name": "Tinfoil", "tagline": "Verifiable private inference with Intel TDX and NVIDIA H100 CC", "description": "Tinfoil provides confidential inference with hardware-attestable privacy guarantees. Every request runs inside an Intel TDX enclave or on an NVIDIA H100 Confidential Computing GPU. Users can cryptographically verify that their prompts are processed in a trusted execution environment and never exposed to the host operator.", "logo_url": null, "website_url": "https://tinfoil.sh", "api_docs_url": "https://docs.tinfoil.sh", "founded_year": null, "headquarters": "San Francisco, CA", "status": "active", "tee_types": [ { "type": "intel_tdx", "attestation_method": "Intel DCAP Remote Attestation", "notes": "CPU-level isolation for model weights and prompts" }, { "type": "nvidia_h100_cc", "attestation_method": "NVIDIA NRAS", "notes": "GPU memory encryption for accelerated inference" } ], "models": [ { "name": "DeepSeek V4.1 Flash", "slug": "deepseek-v4.1-flash", "family": "DeepSeek", "source_id": "deepseek-v4-1-flash", "context_window": null, "max_output_tokens": null }, { "name": "GLM 5.3", "slug": "glm-5.3", "family": "ZhipuAI GLM", "source_id": "glm-5-3", "context_window": null, "max_output_tokens": null }, { "name": "Kimi K3", "slug": "kimi-k3", "family": "Moonshot AI", "source_id": "kimi-k3", "context_window": null, "max_output_tokens": null }, { "name": "Llama 3.3 70B", "slug": "llama-3.3-70b", "family": "Meta Llama", "source_id": "llama3-3-70b", "context_window": 131072, "max_output_tokens": null }, { "name": "Gemma 4 31B", "slug": "gemma-4-31b", "family": "Google Gemma", "source_id": "gemma4-31b", "context_window": null, "max_output_tokens": null }, { "name": "GPT-OSS 120B", "slug": "gpt-oss-120b", "family": "OpenAI GPT", "source_id": "gpt-oss-120b", "context_window": 131072, "max_output_tokens": null }, { "name": "GPT-OSS Safeguard 120B", "slug": "gpt-oss-safeguard-120b", "family": "OpenAI GPT", "source_id": "gpt-oss-safeguard-120b", "context_window": 131072, "max_output_tokens": null }, { "name": "Pii Filter", "slug": "pii-filter", "family": "Unknown", "source_id": "pii-filter", "context_window": null, "max_output_tokens": null }, { "name": "Nomic Embed Text", "slug": "nomic-embed-text", "family": "Nomic", "source_id": "nomic-embed-text", "context_window": 8192, "max_output_tokens": null }, { "name": "Voxtral Small 24B", "slug": "voxtral-small-24b", "family": "Mistral", "source_id": "voxtral-small-24b", "context_window": 32768, "max_output_tokens": null }, { "name": "Whisper Large V3 Turbo", "slug": "whisper-large-v3-turbo", "family": "OpenAI GPT", "source_id": "whisper-large-v3-turbo", "context_window": 30000, "max_output_tokens": null }, { "name": "Qwen3-TTS 1.7B", "slug": "qwen3-tts-1.7b", "family": "Qwen", "source_id": "qwen3-tts", "context_window": null, "max_output_tokens": null }, { "name": "Voxtral Tts", "slug": "voxtral-tts", "family": "Mistral", "source_id": "voxtral-tts", "context_window": null, "max_output_tokens": null }, { "name": "Voxtral Mini 4B Realtime", "slug": "voxtral-mini-4b-realtime", "family": "Mistral", "source_id": "voxtral-mini-4b-realtime", "context_window": null, "max_output_tokens": null } ], "pricing": [ { "model_name": "DeepSeek V4.1 Flash", "price_per_million_input_tokens": 0.65, "price_per_million_output_tokens": 1.45, "price_per_million_cached_input_tokens": 0.13, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "deepseek-v4-1-flash", "offering_id": "deepseek-v4-1-flash#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.3", "price_per_million_input_tokens": 1.8, "price_per_million_output_tokens": 5.75, "price_per_million_cached_input_tokens": 0.45, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "glm-5-3", "offering_id": "glm-5-3#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Kimi K3", "price_per_million_input_tokens": 4, "price_per_million_output_tokens": 20, "price_per_million_cached_input_tokens": 0.8, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "kimi-k3", "offering_id": "kimi-k3#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Llama 3.3 70B", "price_per_million_input_tokens": 1.75, "price_per_million_output_tokens": 2.75, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "llama3-3-70b", "offering_id": "llama3-3-70b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Gemma 4 31B", "price_per_million_input_tokens": 0.4, "price_per_million_output_tokens": 1, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "gemma4-31b", "offering_id": "gemma4-31b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GPT-OSS 120B", "price_per_million_input_tokens": 0.15, "price_per_million_output_tokens": 0.6, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "gpt-oss-120b", "offering_id": "gpt-oss-120b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GPT-OSS Safeguard 120B", "price_per_million_input_tokens": 0.15, "price_per_million_output_tokens": 0.6, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "gpt-oss-safeguard-120b", "offering_id": "gpt-oss-safeguard-120b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Pii Filter", "price_per_million_input_tokens": 0, "price_per_million_output_tokens": 0, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "pii-filter", "offering_id": "pii-filter#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Nomic Embed Text", "price_per_million_input_tokens": 0.05, "price_per_million_output_tokens": 0, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "nomic-embed-text", "offering_id": "nomic-embed-text#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Voxtral Small 24B", "price_per_million_input_tokens": 0.2, "price_per_million_output_tokens": 0.6, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "voxtral-small-24b", "offering_id": "voxtral-small-24b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Whisper Large V3 Turbo", "price_per_million_input_tokens": 0, "price_per_million_output_tokens": 0, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "whisper-large-v3-turbo", "offering_id": "whisper-large-v3-turbo#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3-TTS 1.7B", "price_per_million_input_tokens": 0, "price_per_million_output_tokens": 0, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "qwen3-tts", "offering_id": "qwen3-tts#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Voxtral Tts", "price_per_million_input_tokens": 0, "price_per_million_output_tokens": 0, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "voxtral-tts", "offering_id": "voxtral-tts#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Voxtral Mini 4B Realtime", "price_per_million_input_tokens": 0, "price_per_million_output_tokens": 0, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "voxtral-mini-4b-realtime", "offering_id": "voxtral-mini-4b-realtime#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null } ], "api_features": { "openai_compatible": true, "streaming": true, "function_calling": true, "batch_inference": false, "vision": true, "embeddings": true, "max_concurrent_requests": null, "avg_latency_ms": null }, "payments": { "accepts_crypto": false, "accepts_bitcoin": false, "accepted_assets": [], "notes": null }, "attestation": { "documentation_url": null, "endpoint_url": null, "verifier_url": null, "evidence_format": null, "notes": null }, "sdks": [], "api_compatibility": { "openai_chat_completions": false, "openai_responses": false, "anthropic_messages": false, "notes": null }, "social_links": [], "source_urls": [ { "label": "Tinfoil attestation architecture", "url": "https://docs.tinfoil.sh/verification/attestation-architecture", "checked_at": "2026-07-16" } ], "last_verified_at": null, "data_freshness": { "status": "fresh", "last_success_at": "2026-10-18T12:56:25Z", "last_attempt_at": "2026-10-18T12:56:25Z" }, "source_observations": { "models": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "prices": { "kind": "live", "status": "fresh", "source_url": "https://api.tinfoil.sh/api/config/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "metadata": { "kind": "declared", "status": "declared", "source_url": "https://docs.tinfoil.sh/verification/attestation-architecture", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null } }, "organization_roles": [ "storefront", "router", "workload-operator", "tee-platform" ], "trust_tier": "hw-verified-tls", "pqc": { "status": "pq-gateway", "kex": "X25519MLKEM768", "kex_required": null, "classical_fallback": "observed", "notes": "Measured X25519MLKEM768, SecP256r1MLKEM768, SecP384r1MLKEM1024 TLS on inference.tinfoil.sh (2026-10-19); the termination point is not proven inside the attested TEE. A classical-only handshake completed in the tested matrix.", "source_url": null, "checked_at": "2026-10-19", "measured": { "display": "hybrid-observed", "displayLabel": "Hybrid TLS observed", "claims": [ "hybrid-tls-observed", "classical-fallback-observed" ], "claimLabels": [ "Hybrid TLS observed", "Classical fallback observed" ], "hybridObserved": [ "X25519MLKEM768", "SecP256r1MLKEM768", "SecP384r1MLKEM1024" ], "classicalFallback": "observed", "defaultNegotiated": "X25519MLKEM768", "measuredAt": "2026-10-19T05:41:20.011Z", "stale": false, "boundToAttestedEndpoint": false, "boundCheckId": null, "boundAttemptId": null, "boundCheckedAt": null, "supportingAttemptIds": [ 3102, 3103, 3104, 3105, 3106, 3107 ], "endpoint": "inference.tinfoil.sh", "endpointId": "tinfoil-api", "vantage": "conf-inference", "runId": 33, "latestAttempt": { "at": "2026-10-19T05:41:19.687Z", "outcome": "negotiated", "endpointId": "tinfoil-api" }, "integrity": "verified", "lastObserved": null, "client": { "node": "v24.14.1", "openssl": "3.5.5" }, "evidenceLevel": "authenticated", "reasons": [ "a classical-only handshake completed — hybrid remains optional" ] } }, "current_assurance": { "state": "unreachable", "label": "Availability issue", "summary": "The verifier could not fetch fresh evidence for every check in this run.", "tone": "warn", "checks": 9, "outcome": "checked", "missingTargets": [], "attemptSummary": "Latest attempt complete; discovery complete; 9/9 targets completed; 8 excluded (unsupported utility/modality or non-confidential model class)" } }, { "id": "11", "slug": "nanogpt", "name": "NanoGPT", "tagline": "Pay-per-prompt confidential inference — TEE-backed models with ECDSA per-request attestation", "description": "NanoGPT runs a curated set of open-source models inside Trusted Execution Environments (TEE), providing hardware-enforced confidentiality for prompts and responses. TEE models are identified by a TEE/ prefix and can be cryptographically verified: a dedicated attestation endpoint returns the hardware quote, and a per-request ECDSA signature endpoint lets clients confirm their specific completion was produced inside the enclave. No account or subscription required — anonymous cryptocurrency payments accepted.", "logo_url": null, "website_url": "https://nano-gpt.com", "api_docs_url": "https://docs.nano-gpt.com", "founded_year": null, "headquarters": null, "status": "active", "tee_types": [ { "type": "nvidia_h100_cc", "attestation_method": "Intel/NVIDIA Remote Attestation + ECDSA per-request signatures", "notes": "TEE models prefixed TEE/; per-request ECDSA signatures verifiable independently of NanoGPT" } ], "models": [ { "name": "Qwen3.8 27B", "slug": "qwen3.8-27b", "family": "Qwen", "source_id": "TEE/qwen3.8-27b", "context_window": null, "max_output_tokens": null }, { "name": "Qwen3.6 27B", "slug": "qwen3.6-27b", "family": "Qwen", "source_id": "TEE/qwen3.6-27b", "context_window": 262100, "max_output_tokens": null }, { "name": "GPT-OSS 120B", "slug": "gpt-oss-120b", "family": "OpenAI GPT", "source_id": "TEE/gpt-oss-120b", "context_window": 131072, "max_output_tokens": null }, { "name": "Qwen2.5-VL 72B", "slug": "qwen2.5-vl-72b", "family": "Qwen", "source_id": "TEE/qwen2.5-vl-72b-instruct", "context_window": 65536, "max_output_tokens": null }, { "name": "DeepSeek V4.1 Flash", "slug": "deepseek-v4.1-flash", "family": "DeepSeek", "source_id": "TEE/deepseek-v4.1-flash", "context_window": null, "max_output_tokens": null }, { "name": "DeepSeek V3.2", "slug": "deepseek-v3.2", "family": "DeepSeek", "source_id": "TEE/deepseek-v3.2", "context_window": 164000, "max_output_tokens": null }, { "name": "Qwen3.6 35B A3B", "slug": "qwen3.6-35b-a3b", "family": "Qwen", "source_id": "TEE/qwen3.6-35b-a3b", "context_window": null, "max_output_tokens": null }, { "name": "Qwen3.5 27B", "slug": "qwen3.5-27b", "family": "Qwen", "source_id": "TEE/qwen3.5-27b", "context_window": 262100, "max_output_tokens": null }, { "name": "Qwen3.5 397B A17B", "slug": "qwen3.5-397b-a17b", "family": "Qwen", "source_id": "TEE/qwen3.5-397b-a17b", "context_window": 262100, "max_output_tokens": null }, { "name": "Nemotron 3.5 Lightning", "slug": "nemotron-3.5-lightning", "family": "Unknown", "source_id": "TEE/nemotron-3.5-lightning", "context_window": null, "max_output_tokens": null }, { "name": "Muse Glimmer 30B", "slug": "muse-glimmer-30b", "family": "Unknown", "source_id": "TEE/muse-glimmer-30b", "context_window": null, "max_output_tokens": null }, { "name": "Gemma 4 31B IT", "slug": "gemma-4-31b-it", "family": "Google Gemma", "source_id": "TEE/gemma-4-31b-it", "context_window": 262100, "max_output_tokens": null }, { "name": "Gemma 4 26B A4B Uncensored", "slug": "gemma-4-26b-a4b-uncensored", "family": "Google Gemma", "source_id": "TEE/gemma-4-26b-a4b-uncensored", "context_window": 65500, "max_output_tokens": null }, { "name": "Gemma 4 31B", "slug": "gemma-4-31b", "family": "Google Gemma", "source_id": "TEE/gemma4-31b", "context_window": 262100, "max_output_tokens": null }, { "name": "Gemma 4 31B Thinking", "slug": "gemma-4-31b-thinking", "family": "Google Gemma", "source_id": "TEE/gemma4-31b:thinking", "context_window": 262100, "max_output_tokens": null }, { "name": "Llama 3.3 70B", "slug": "llama-3.3-70b", "family": "Meta Llama", "source_id": "TEE/llama3-3-70b", "context_window": 128000, "max_output_tokens": null }, { "name": "Kimi K3", "slug": "kimi-k3", "family": "Moonshot AI", "source_id": "TEE/kimi-k3", "context_window": null, "max_output_tokens": null }, { "name": "Kimi K2.6", "slug": "kimi-k2.6", "family": "Moonshot AI", "source_id": "TEE/kimi-k2.6", "context_window": null, "max_output_tokens": null }, { "name": "Kimi K2.7 Code", "slug": "kimi-k2.7-code", "family": "Moonshot AI", "source_id": "TEE/kimi-k2.7-code", "context_window": null, "max_output_tokens": null }, { "name": "GLM 5.1", "slug": "glm-5.1", "family": "ZhipuAI GLM", "source_id": "TEE/glm-5.1", "context_window": null, "max_output_tokens": null }, { "name": "GLM 5.1 Thinking", "slug": "glm-5.1-thinking", "family": "ZhipuAI GLM", "source_id": "TEE/glm-5.1-thinking", "context_window": null, "max_output_tokens": null }, { "name": "GLM 5.2", "slug": "glm-5.2", "family": "ZhipuAI GLM", "source_id": "TEE/glm-5.2", "context_window": null, "max_output_tokens": null }, { "name": "GLM 5.2 :Thinking", "slug": "glm-5.2-thinking", "family": "ZhipuAI GLM", "source_id": "TEE/glm-5.2:thinking", "context_window": null, "max_output_tokens": null }, { "name": "GLM 5.3", "slug": "glm-5.3", "family": "ZhipuAI GLM", "source_id": "TEE/glm-5.3", "context_window": null, "max_output_tokens": null }, { "name": "GLM 5.3 Flash", "slug": "glm-5.3-flash", "family": "ZhipuAI GLM", "source_id": "TEE/glm-5.3-flash", "context_window": null, "max_output_tokens": null } ], "pricing": [ { "model_name": "Qwen3.8 27B", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "custom", "free_tier": false, "notes": null, "source_id": "TEE/qwen3.8-27b", "offering_id": "TEE/qwen3.8-27b#custom", "unit": null, "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.6 27B", "price_per_million_input_tokens": 0.32, "price_per_million_output_tokens": 2.7, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "TEE/qwen3.6-27b", "offering_id": "TEE/qwen3.6-27b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GPT-OSS 120B", "price_per_million_input_tokens": 2, "price_per_million_output_tokens": 2, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "TEE/gpt-oss-120b", "offering_id": "TEE/gpt-oss-120b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen2.5-VL 72B", "price_per_million_input_tokens": 0.7, "price_per_million_output_tokens": 0.7, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "TEE/qwen2.5-vl-72b-instruct", "offering_id": "TEE/qwen2.5-vl-72b-instruct#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "DeepSeek V4.1 Flash", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "custom", "free_tier": false, "notes": null, "source_id": "TEE/deepseek-v4.1-flash", "offering_id": "TEE/deepseek-v4.1-flash#custom", "unit": null, "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "DeepSeek V3.2", "price_per_million_input_tokens": 0.5, "price_per_million_output_tokens": 1, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "TEE/deepseek-v3.2", "offering_id": "TEE/deepseek-v3.2#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.6 35B A3B", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "custom", "free_tier": false, "notes": null, "source_id": "TEE/qwen3.6-35b-a3b", "offering_id": "TEE/qwen3.6-35b-a3b#custom", "unit": null, "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.5 27B", "price_per_million_input_tokens": 0.3, "price_per_million_output_tokens": 2.4, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "TEE/qwen3.5-27b", "offering_id": "TEE/qwen3.5-27b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.5 397B A17B", "price_per_million_input_tokens": 0.55, "price_per_million_output_tokens": 3.5, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "TEE/qwen3.5-397b-a17b", "offering_id": "TEE/qwen3.5-397b-a17b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Nemotron 3.5 Lightning", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "custom", "free_tier": false, "notes": null, "source_id": "TEE/nemotron-3.5-lightning", "offering_id": "TEE/nemotron-3.5-lightning#custom", "unit": null, "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Muse Glimmer 30B", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "custom", "free_tier": false, "notes": null, "source_id": "TEE/muse-glimmer-30b", "offering_id": "TEE/muse-glimmer-30b#custom", "unit": null, "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Gemma 4 31B IT", "price_per_million_input_tokens": 0.15, "price_per_million_output_tokens": 0.46, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "TEE/gemma-4-31b-it", "offering_id": "TEE/gemma-4-31b-it#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Gemma 4 26B A4B Uncensored", "price_per_million_input_tokens": 0.15, "price_per_million_output_tokens": 0.7, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "TEE/gemma-4-26b-a4b-uncensored", "offering_id": "TEE/gemma-4-26b-a4b-uncensored#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Gemma 4 31B", "price_per_million_input_tokens": 0.45, "price_per_million_output_tokens": 1, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "TEE/gemma4-31b", "offering_id": "TEE/gemma4-31b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Gemma 4 31B Thinking", "price_per_million_input_tokens": 0.45, "price_per_million_output_tokens": 1, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "TEE/gemma4-31b:thinking", "offering_id": "TEE/gemma4-31b:thinking#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Llama 3.3 70B", "price_per_million_input_tokens": 2, "price_per_million_output_tokens": 2, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "TEE/llama3-3-70b", "offering_id": "TEE/llama3-3-70b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Kimi K3", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "custom", "free_tier": false, "notes": null, "source_id": "TEE/kimi-k3", "offering_id": "TEE/kimi-k3#custom", "unit": null, "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Kimi K2.6", "price_per_million_input_tokens": 1.5, "price_per_million_output_tokens": 5.25, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "Cache read $0.38/1M tokens", "source_id": "TEE/kimi-k2.6", "offering_id": "TEE/kimi-k2.6#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Kimi K2.7 Code", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "custom", "free_tier": false, "notes": null, "source_id": "TEE/kimi-k2.7-code", "offering_id": "TEE/kimi-k2.7-code#custom", "unit": null, "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.1", "price_per_million_input_tokens": 1.5, "price_per_million_output_tokens": 5.25, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "Cache read $0.30/1M tokens", "source_id": "TEE/glm-5.1", "offering_id": "TEE/glm-5.1#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.1 Thinking", "price_per_million_input_tokens": 1.5, "price_per_million_output_tokens": 5.25, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "Cache read $0.30/1M tokens", "source_id": "TEE/glm-5.1-thinking", "offering_id": "TEE/glm-5.1-thinking#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.2", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "custom", "free_tier": false, "notes": null, "source_id": "TEE/glm-5.2", "offering_id": "TEE/glm-5.2#custom", "unit": null, "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.2 :Thinking", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "custom", "free_tier": false, "notes": null, "source_id": "TEE/glm-5.2:thinking", "offering_id": "TEE/glm-5.2:thinking#custom", "unit": null, "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.3", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "custom", "free_tier": false, "notes": null, "source_id": "TEE/glm-5.3", "offering_id": "TEE/glm-5.3#custom", "unit": null, "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.3 Flash", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "custom", "free_tier": false, "notes": null, "source_id": "TEE/glm-5.3-flash", "offering_id": "TEE/glm-5.3-flash#custom", "unit": null, "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null } ], "api_features": { "openai_compatible": true, "streaming": true, "function_calling": false, "batch_inference": false, "vision": false, "embeddings": false, "max_concurrent_requests": null, "avg_latency_ms": null }, "payments": { "accepts_crypto": false, "accepts_bitcoin": false, "accepted_assets": [], "notes": null }, "attestation": { "documentation_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "endpoint_url": "https://api.nano-gpt.com/v1/tee/attestation?model=TEE/llama3-3-70b", "verifier_url": null, "evidence_format": "Tinfoil gzip+base64 quote or dstack all_attestations quote", "notes": "Verifier checks reachable NanoGPT TEE model hardware quotes through the authenticated attestation endpoint. NanoGPT is classified as tee-only because gateway TLS and requester nonce binding are not verified." }, "sdks": [], "api_compatibility": { "openai_chat_completions": false, "openai_responses": false, "anthropic_messages": false, "notes": null }, "social_links": [ { "label": "X", "url": "https://x.com/NanoGPTcom" } ], "source_urls": [ { "label": "NanoGPT TEE verification", "url": "https://docs.nano-gpt.com/api-reference/tee-verification", "checked_at": "2026-07-16" } ], "last_verified_at": null, "data_freshness": { "status": "fresh", "last_success_at": "2026-10-18T12:56:25Z", "last_attempt_at": "2026-10-18T12:56:25Z" }, "source_observations": { "models": { "kind": "live", "status": "fresh", "source_url": "https://nano-gpt.com/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "prices": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "metadata": { "kind": "declared", "status": "declared", "source_url": "https://docs.nano-gpt.com/api-reference/tee-verification", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null } }, "organization_roles": [ "storefront", "aggregator" ], "trust_tier": "tee-only", "pqc": { "status": "pq-gateway", "kex": "X25519MLKEM768", "kex_required": null, "classical_fallback": "observed", "notes": "Measured X25519MLKEM768 TLS on nano-gpt.com (2026-10-19); the termination point is not proven inside the attested TEE. A classical-only handshake completed in the tested matrix.", "source_url": null, "checked_at": "2026-10-19", "measured": { "display": "hybrid-observed", "displayLabel": "Hybrid TLS observed", "claims": [ "hybrid-tls-observed", "classical-fallback-observed" ], "claimLabels": [ "Hybrid TLS observed", "Classical fallback observed" ], "hybridObserved": [ "X25519MLKEM768" ], "classicalFallback": "observed", "defaultNegotiated": "X25519MLKEM768", "measuredAt": "2026-10-19T05:41:20.011Z", "stale": false, "boundToAttestedEndpoint": false, "boundCheckId": null, "boundAttemptId": null, "boundCheckedAt": null, "supportingAttemptIds": [ 3014, 3017, 3018, 3019 ], "endpoint": "nano-gpt.com", "endpointId": "nanogpt-api", "vantage": "conf-inference", "runId": 33, "latestAttempt": { "at": "2026-10-19T05:41:12.621Z", "outcome": "negotiated", "endpointId": "nanogpt-api" }, "integrity": "verified", "lastObserved": null, "client": { "node": "v24.14.1", "openssl": "3.5.5" }, "evidenceLevel": "authenticated", "reasons": [ "a classical-only handshake completed — hybrid remains optional" ] } }, "current_assurance": { "state": "failed", "label": "Explicit trust failures", "summary": "At least one check has an explicit mismatch or policy rejection; other evidence layers may still have passed.", "tone": "bad", "checks": 25, "outcome": "checked", "missingTargets": [], "attemptSummary": "Latest attempt complete; discovery complete; 25/25 targets completed; 638 excluded (catalog model is not in the provider's confidential/TEE class)" } }, { "id": "12", "slug": "confidentialai", "name": "Confidential AI", "tagline": "Confidential inference on Intel TDX with per-workload attestation receipts", "description": "Confidential AI (Inexorable, Inc.) serves open-weight models inside Intel TDX confidential VMs on its open-source c8s platform, with NVIDIA GPUs in confidential-compute mode. The public /attestation endpoint returns fresh nonce-bound c8s receipts for every workload in the serving cluster — gateway, router, inference workers, and supporting services — including Intel TDX quotes, pinned image measurements, mesh identity proofs, and NVIDIA GPU evidence. A post-quantum over-encryption tunnel (ML-KEM-768 + X25519) terminates inside the attested TEE.", "logo_url": null, "website_url": "https://confidential.ai", "api_docs_url": "https://confidential.ai/docs/inference-api/get-started", "founded_year": null, "headquarters": null, "status": "active", "tee_types": [ { "type": "intel_tdx", "attestation_method": "c8s attestation bundle: per-workload Intel TDX quotes whose report_data binds a SHA-384 transcript over the caller nonce, session keys, and mesh identity", "notes": "GET https://api.confidential.ai/attestation?nonce=<32-byte b64url> returns c8s/attest-pq/v1 receipts for every cluster workload plus a c8s/attest-lb/v1 front-door receipt that binds the live TLS serving certificate." }, { "type": "nvidia_h100_cc", "attestation_method": "NVIDIA GPU evidence relayed inside the cluster attestation bundle (nvidia_gpu per inference worker, gpuEvidence aggregate)", "notes": "GPU evidence is collected and relayed (Blackwell-class devices); independent GPU verdict is not yet produced by this directory's verifier." } ], "models": [ { "name": "DeepSeek V4 Flash", "slug": "deepseek-v4-flash", "family": "DeepSeek", "source_id": "deepseek-ai/DeepSeek-V4-Flash-0731", "context_window": 1048576, "max_output_tokens": null } ], "pricing": [ { "model_name": "DeepSeek V4 Flash", "price_per_million_input_tokens": 0.2, "price_per_million_output_tokens": 0.4, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "Cached input $0.018 per 1M tokens. Capacity-available tier per public pricing page.", "source_id": "deepseek-ai/DeepSeek-V4-Flash-0731", "offering_id": "deepseek-ai/DeepSeek-V4-Flash-0731#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://confidential.ai/pricing", "observed_at": "2026-09-21", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null } ], "api_features": { "openai_compatible": true, "streaming": true, "function_calling": false, "batch_inference": false, "vision": false, "embeddings": false, "max_concurrent_requests": null, "avg_latency_ms": null }, "payments": { "accepts_crypto": false, "accepts_bitcoin": false, "accepted_assets": [], "notes": "Monthly invoicing by card or bank transfer." }, "attestation": { "documentation_url": "https://confidential.ai/docs/inference-api/attestation", "endpoint_url": "https://api.confidential.ai/attestation", "verifier_url": "https://github.com/confidential-dot-ai/c8s-verify-js", "evidence_format": "c8s/attest-pq/v1 per-workload receipts and c8s/attest-lb/v1 front-door receipt (Intel TDX report_data binding a SHA-384 identity transcript; ECDSA P-384 mesh proof; cluster allowlist and OCI digests)", "notes": "Live cluster demo: https://confidential-inference-cluster-demo.confidential.ai/. The transcript construction is specified in c8s PROTOCOL.md and the deployed session-pubkey shape was confirmed against live report_data." }, "sdks": [ { "language": "TypeScript", "package_url": "https://github.com/confidential-dot-ai/c8s-verify-js", "docs_url": "https://confidential.ai/docs/inference-api/attestation" }, { "language": "Go", "package_url": "https://github.com/confidential-dot-ai/c8s", "docs_url": "https://confidential.ai/docs/c8s" } ], "api_compatibility": { "openai_chat_completions": true, "openai_responses": false, "anthropic_messages": false, "notes": "OpenAI-compatible /v1/chat/completions and /v1/completions. API keys are provisioned by request (email or request-access form); /health, /attestation, and the c8s well-known endpoints are public." }, "social_links": [], "source_urls": [ { "label": "Public pricing", "url": "https://confidential.ai/pricing", "checked_at": "2026-09-21" }, { "label": "Inference API attestation docs", "url": "https://confidential.ai/docs/inference-api/attestation", "checked_at": "2026-09-21" }, { "label": "Live cluster attestation demo", "url": "https://confidential-inference-cluster-demo.confidential.ai/", "checked_at": "2026-09-21" }, { "label": "OpenAI-compatible model catalog", "url": "https://api.confidential.ai/v1/models", "checked_at": "2026-09-21" } ], "last_verified_at": "2026-09-21", "data_freshness": { "status": "fresh", "last_success_at": "2026-10-18T12:56:25Z", "last_attempt_at": "2026-10-18T12:56:25Z" }, "source_observations": { "models": { "kind": "live", "status": "fresh", "source_url": "https://api.confidential.ai/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "prices": { "kind": "declared", "status": "declared", "source_url": "https://confidential.ai/pricing", "observed_at": "2026-09-21", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "metadata": { "kind": "declared", "status": "declared", "source_url": "https://confidential.ai/pricing", "observed_at": "2026-09-21", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null } }, "organization_roles": [ "storefront", "workload-operator", "tee-platform" ], "trust_tier": "hw-verified-tls", "pqc": { "status": "pq-gateway", "kex": "X25519MLKEM768", "kex_required": null, "classical_fallback": "observed", "notes": "Measured X25519MLKEM768 TLS on api.confidential.ai (2026-10-19); the termination point is not proven inside the attested TEE. A classical-only handshake completed in the tested matrix.", "source_url": "https://confidential.ai/docs/inference-api/attestation", "checked_at": "2026-10-19", "measured": { "display": "hybrid-observed", "displayLabel": "Hybrid TLS observed", "claims": [ "hybrid-tls-observed", "classical-fallback-observed" ], "claimLabels": [ "Hybrid TLS observed", "Classical fallback observed" ], "hybridObserved": [ "X25519MLKEM768" ], "classicalFallback": "observed", "defaultNegotiated": "X25519MLKEM768", "measuredAt": "2026-10-19T05:41:20.011Z", "stale": false, "boundToAttestedEndpoint": false, "boundCheckId": null, "boundAttemptId": null, "boundCheckedAt": null, "supportingAttemptIds": [ 3022, 3025, 3026, 3027 ], "endpoint": "api.confidential.ai", "endpointId": "confidentialai-api", "vantage": "conf-inference", "runId": 33, "latestAttempt": { "at": "2026-10-19T05:41:13.282Z", "outcome": "negotiated", "endpointId": "confidentialai-api" }, "integrity": "verified", "lastObserved": null, "client": { "node": "v24.14.1", "openssl": "3.5.5" }, "evidenceLevel": "authenticated", "reasons": [ "a classical-only handshake completed — hybrid remains optional" ] } }, "current_assurance": { "state": "failed", "label": "Explicit trust failures", "summary": "At least one check has an explicit mismatch or policy rejection; other evidence layers may still have passed.", "tone": "bad", "checks": 1, "outcome": "checked", "missingTargets": [], "attemptSummary": "Latest attempt complete; discovery complete; 1/1 targets completed" } }, { "id": "13", "slug": "prem", "name": "Prem", "tagline": "OpenAI-compatible end-to-end encrypted confidential inference on dedicated GPUs", "description": "Prem (prem.io) offers OpenAI-compatible confidential inference where the Confidential Proxy encrypts requests end-to-end to the enclave (XWing key encapsulation + XChaCha20-Poly1305). Attestation combines AMD SEV-SNP or Intel TDX CPU evidence with NVIDIA GPU signed EAT tokens, verified client-side by the open-source Reticle verifier. The service is in beta; the confidential catalog is served per API key from the gateway at gateway.prem.io and is distinct from the non-TEE Zero Data Retention (ZDR) catalog.", "logo_url": null, "website_url": "https://www.premai.io", "api_docs_url": "https://docs.prem.io", "founded_year": null, "headquarters": null, "status": "beta", "tee_types": [ { "type": "intel_tdx", "attestation_method": "Shared Intel DCAP/QVL verifier with full 64-byte nonce freshness, followed by the published Prem production-invariant appraisal; measurements are compared to an explicitly unpinned baseline.", "notes": "Only Intel TDX CPU evidence has been observed. AMD SEV-SNP is not listed until independently observed." }, { "type": "nvidia_cc", "attestation_method": "Shared NVIDIA detached-EAT appraisal: pinned ES384/JWKS/issuer, time windows, every GPU nonce, signed submodule set/digests, measurements, RIM/certificate/OCSP claims, secure boot and debug state. NRAS performs device-chain appraisal; CPU-to-GPU/inference binding remains unproven.", "notes": "Prem does not publish GPU SKUs, fleet size, or which models run on which GPUs; the gateway advertises a single NVIDIA vendor module while the EAT response can carry several detached GPU claims" } ], "models": [ { "name": "DeepSeek V4.1 Flash", "slug": "deepseek-v4.1-flash", "family": "DeepSeek", "source_id": "deepseek-v4.1-flash", "context_window": null, "max_output_tokens": null }, { "name": "Qwen 3.8 27B", "slug": "qwen-3.8-27b", "family": "Qwen", "source_id": "qwen38-27b", "context_window": null, "max_output_tokens": null }, { "name": "Nemotron 3 Ultra", "slug": "nemotron-3-ultra", "family": "NVIDIA Nemotron", "source_id": "nvidia/nemotron-3-ultra-550b-a55b", "context_window": null, "max_output_tokens": null }, { "name": "Qwen 3.6 27B", "slug": "qwen-3.6-27b", "family": "Qwen", "source_id": "qwen36-27b", "context_window": null, "max_output_tokens": null }, { "name": "DeepGram General Nova 3", "slug": "deepgram-general-nova-3", "family": "DeepGram", "source_id": "deepgram/general-nova-3", "context_window": null, "max_output_tokens": null } ], "pricing": [ { "model_name": "DeepSeek V4.1 Flash", "price_per_million_input_tokens": 0.35, "price_per_million_output_tokens": 1.4, "price_per_million_cached_input_tokens": 0, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "USD per 1M tokens; live confidential per-1K fields multiplied by 1000. Reasoning rates are listed separately when nonzero.; Cached input promotional rate from Prem docs until 2026-10-20T00:00:00Z; not an API-observed rate", "source_id": "deepseek-v4.1-flash", "offering_id": "deepseek-v4.1-flash#ch", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "declared", "status": "declared", "source_url": "https://docs.prem.io/models-and-pricing", "observed_at": "2026-10-17", "attempted_at": null, "expires_at": "2026-10-20T00:00:00Z", "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen 3.8 27B", "price_per_million_input_tokens": 0.3, "price_per_million_output_tokens": 2.4, "price_per_million_cached_input_tokens": 0, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "USD per 1M tokens; live confidential per-1K fields multiplied by 1000. Reasoning rates are listed separately when nonzero.; reasoning tokens $1.2/1M", "source_id": "qwen38-27b", "offering_id": "qwen38-27b#ch", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://gateway.prem.io/rvenc/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Nemotron 3 Ultra", "price_per_million_input_tokens": 0.625, "price_per_million_output_tokens": 3.125, "price_per_million_cached_input_tokens": 0, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "USD per 1M tokens; live confidential per-1K fields multiplied by 1000. Reasoning rates are listed separately when nonzero.", "source_id": "nvidia/nemotron-3-ultra-550b-a55b", "offering_id": "nvidia/nemotron-3-ultra-550b-a55b#ch", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://gateway.prem.io/rvenc/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen 3.6 27B", "price_per_million_input_tokens": 0.3, "price_per_million_output_tokens": 2.4, "price_per_million_cached_input_tokens": 0, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "USD per 1M tokens; live confidential per-1K fields multiplied by 1000. Reasoning rates are listed separately when nonzero.; reasoning tokens $1.2/1M", "source_id": "qwen36-27b", "offering_id": "qwen36-27b#ch", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://gateway.prem.io/rvenc/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "DeepGram General Nova 3", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": 0.05, "pricing_model": "per_audio_minute", "free_tier": false, "notes": "USD per audio minute from the confidential catalog.", "source_id": "deepgram/general-nova-3", "offering_id": "deepgram/general-nova-3#ch", "unit": "audio-minute", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://gateway.prem.io/rvenc/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null } ], "api_features": { "openai_compatible": true, "streaming": true, "function_calling": true, "batch_inference": false, "vision": true, "embeddings": false, "max_concurrent_requests": null, "avg_latency_ms": null }, "payments": { "accepts_crypto": false, "accepts_bitcoin": false, "accepted_assets": [], "notes": null }, "attestation": { "documentation_url": "https://docs.prem.io/attestation", "endpoint_url": "https://gateway.prem.io/attestation/modules", "verifier_url": "https://github.com/prem-research/reticle", "evidence_format": "Per-model attestation via the Confidential Proxy: AMD SEV-SNP report or Intel TDX quote bound to a verifier nonce, plus NVIDIA GPU signed EAT tokens (detached per-GPU claims), appraised against published OPA golden policies (prem-research/confidential-policies)", "notes": "The site uses shared CPU and NVIDIA verifiers, enforces published TDX production invariants and all signed NRAS GPU security claims, and retains raw response/policy artifacts. A nonce-only TDX report exposes no attested key or TLS-certificate commitment. x-session-id is observed routing metadata, never cryptographic proof. Published illustrative measurements are compared but explicitly unpinned, so workload identity remains unproven. CPU-to-GPU, exact serving GPU set, application encryption and model/inference-route binding remain unproven. A GPU 502 or null discovery cannot waive appraisal. Prem's closed-source KVM hypervisor remains untrusted. Implementation is not a current live verification result." }, "sdks": [ { "language": "Rust", "package_url": "https://github.com/prem-research/reticle", "docs_url": "https://docs.prem.io/attestation" }, { "language": "TypeScript", "package_url": "https://www.npmjs.com/package/@premai/reticle", "docs_url": "https://docs.prem.io/attestation" } ], "api_compatibility": { "openai_chat_completions": true, "openai_responses": false, "anthropic_messages": false, "notes": "Confidential requests go through the Confidential Proxy and its SDK; the SDK includes an Anthropic adapter that is not independently exercised here. The OpenAPI schema declares OpenAI-style tools/tool_choice/function_call parameters on the encrypted chat completions request — function calling is declared, not independently exercised." }, "social_links": [ { "label": "GitHub", "url": "https://github.com/prem-research" } ], "source_urls": [ { "label": "Prem models and pricing", "url": "https://docs.prem.io/models-and-pricing", "checked_at": "2026-10-17" }, { "label": "Prem attestation documentation", "url": "https://docs.prem.io/attestation", "checked_at": "2026-10-17" }, { "label": "Prem security model", "url": "https://docs.prem.io/security-model", "checked_at": "2026-10-17" }, { "label": "Prem confidential model catalog", "url": "https://gateway.prem.io/rvenc/models", "checked_at": "2026-10-17" }, { "label": "Reticle verifier source", "url": "https://github.com/prem-research/reticle", "checked_at": "2026-10-17" }, { "label": "Prem confidential policies", "url": "https://github.com/prem-research/confidential-policies", "checked_at": "2026-10-17" } ], "last_verified_at": "2026-10-17", "data_freshness": { "status": "fresh", "last_success_at": "2026-10-18T12:56:25Z", "last_attempt_at": "2026-10-18T12:56:25Z" }, "source_observations": { "models": { "kind": "live", "status": "fresh", "source_url": "https://gateway.prem.io/rvenc/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "prices": { "kind": "live", "status": "declared", "source_url": "https://docs.prem.io/models-and-pricing", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "metadata": { "kind": "declared", "status": "declared", "source_url": "https://docs.prem.io/models-and-pricing", "observed_at": "2026-10-17", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null } }, "organization_roles": [ "storefront", "workload-operator", "tee-platform" ], "trust_tier": "app-e2ee", "e2ee_capability": "xwing-xchacha20-poly1305", "pqc": { "status": "pq-gateway", "kex": "X25519MLKEM768", "kex_required": null, "classical_fallback": "observed", "notes": "Measured X25519MLKEM768 TLS on gateway.prem.io (2026-10-19); the termination point is not proven inside the attested TEE. A classical-only handshake completed in the tested matrix.", "source_url": "https://confidentialinference.net/api/v1/pqc/runs/31.json", "checked_at": "2026-10-19", "measured": { "display": "hybrid-observed", "displayLabel": "Hybrid TLS observed", "claims": [ "hybrid-tls-observed", "classical-fallback-observed" ], "claimLabels": [ "Hybrid TLS observed", "Classical fallback observed" ], "hybridObserved": [ "X25519MLKEM768" ], "classicalFallback": "observed", "defaultNegotiated": "X25519MLKEM768", "measuredAt": "2026-10-19T05:41:20.011Z", "stale": false, "boundToAttestedEndpoint": false, "boundCheckId": null, "boundAttemptId": null, "boundCheckedAt": null, "supportingAttemptIds": [ 3038, 3041, 3042, 3043, 3046, 3049, 3050, 3051 ], "endpoint": "gateway.prem.io", "endpointId": "prem-api", "vantage": "conf-inference", "runId": 33, "latestAttempt": { "at": "2026-10-19T05:41:15.862Z", "outcome": "negotiated", "endpointId": "prem-api" }, "integrity": "verified", "lastObserved": null, "client": { "node": "v24.14.1", "openssl": "3.5.5" }, "evidenceLevel": "authenticated", "reasons": [ "a classical-only handshake completed — hybrid remains optional" ] } }, "current_assurance": { "state": "unreachable", "label": "Availability issue", "summary": "The verifier could not fetch fresh evidence for every check in this run.", "tone": "warn", "checks": 5, "outcome": "checked", "missingTargets": [], "attemptSummary": "Latest attempt complete; discovery complete; 5/5 targets completed" } }, { "id": "2", "slug": "redpill", "name": "Redpill", "tagline": "OpenAI-compatible confidential inference across attested GPU TEE routes", "description": "Redpill is an OpenAI-compatible confidential inference storefront and router. Its catalog can route models to different confidential workload operators, including Chutes and dstack deployments. Per-model route evidence is shown separately because a storefront identity does not prove which backend served a request.", "logo_url": null, "website_url": "https://www.redpill.ai", "api_docs_url": "https://docs.redpill.ai", "founded_year": null, "headquarters": "Singapore", "status": "active", "tee_types": [ { "type": "intel_tdx", "attestation_method": "Intel DCAP + Phala on-chain attestation", "notes": "Attestation anchored to Phala's blockchain for public verifiability" }, { "type": "nvidia_h100_cc", "attestation_method": "NVIDIA NRAS via Phala TEE Worker", "notes": "GPU memory encryption on Phala's TEE GPU workers" } ], "models": [ { "name": "Qwen3.8 27B Uncensored", "slug": "qwen3.8-27b-uncensored", "family": "Qwen", "source_id": "phala/qwen3.8-27b-uncensored", "context_window": 262144, "max_output_tokens": null }, { "name": "Gemma 4 26B A4B Uncensored", "slug": "gemma-4-26b-a4b-uncensored", "family": "Google Gemma", "source_id": "phala/gemma-4-26b-a4b-uncensored", "context_window": 262144, "max_output_tokens": null } ], "pricing": [ { "model_name": "Qwen3.8 27B Uncensored", "price_per_million_input_tokens": 0.3, "price_per_million_output_tokens": 1.5, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "phala/qwen3.8-27b-uncensored", "offering_id": "phala/qwen3.8-27b-uncensored#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.redpill.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Gemma 4 26B A4B Uncensored", "price_per_million_input_tokens": 0.15, "price_per_million_output_tokens": 0.7, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "phala/gemma-4-26b-a4b-uncensored", "offering_id": "phala/gemma-4-26b-a4b-uncensored#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.redpill.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null } ], "api_features": { "openai_compatible": true, "streaming": true, "function_calling": true, "batch_inference": false, "vision": true, "embeddings": true, "max_concurrent_requests": null, "avg_latency_ms": null }, "payments": { "accepts_crypto": false, "accepts_bitcoin": false, "accepted_assets": [], "notes": null }, "attestation": { "documentation_url": null, "endpoint_url": null, "verifier_url": null, "evidence_format": null, "notes": null }, "sdks": [], "api_compatibility": { "openai_chat_completions": false, "openai_responses": false, "anthropic_messages": false, "notes": null }, "social_links": [ { "label": "X", "url": "https://x.com/redpill_gpt" } ], "source_urls": [ { "label": "Redpill API documentation", "url": "https://docs.redpill.ai", "checked_at": "2026-07-16" } ], "last_verified_at": null, "data_freshness": { "status": "fresh", "last_success_at": "2026-10-18T12:56:25Z", "last_attempt_at": "2026-10-18T12:56:25Z" }, "source_observations": { "models": { "kind": "live", "status": "fresh", "source_url": "https://api.redpill.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "prices": { "kind": "live", "status": "fresh", "source_url": "https://api.redpill.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "metadata": { "kind": "declared", "status": "declared", "source_url": "https://docs.redpill.ai", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null } }, "organization_roles": [ "storefront", "aggregator", "router" ], "trust_tier": "app-e2ee", "e2ee_capability": "ecdh", "pqc": { "status": "pq-gateway", "kex": "X25519MLKEM768", "kex_required": null, "classical_fallback": "observed", "notes": "Measured X25519MLKEM768 TLS on api.redpill.ai (2026-10-19); the termination point is not proven inside the attested TEE. A classical-only handshake completed in the tested matrix.", "source_url": null, "checked_at": "2026-10-19", "measured": { "display": "hybrid-observed", "displayLabel": "Hybrid TLS observed", "claims": [ "hybrid-tls-observed", "classical-fallback-observed" ], "claimLabels": [ "Hybrid TLS observed", "Classical fallback observed" ], "hybridObserved": [ "X25519MLKEM768" ], "classicalFallback": "observed", "defaultNegotiated": "X25519MLKEM768", "measuredAt": "2026-10-19T05:41:20.011Z", "stale": false, "boundToAttestedEndpoint": false, "boundCheckId": null, "boundAttemptId": null, "boundCheckedAt": null, "supportingAttemptIds": [ 3078, 3081, 3082, 3083 ], "endpoint": "api.redpill.ai", "endpointId": "redpill-api", "vantage": "conf-inference", "runId": 33, "latestAttempt": { "at": "2026-10-19T05:41:19.512Z", "outcome": "negotiated", "endpointId": "redpill-api" }, "integrity": "verified", "lastObserved": null, "client": { "node": "v24.14.1", "openssl": "3.5.5" }, "evidenceLevel": "authenticated", "reasons": [ "a classical-only handshake completed — hybrid remains optional" ] } }, "current_assurance": { "state": "failed", "label": "Explicit trust failures", "summary": "At least one check has an explicit mismatch or policy rejection; other evidence layers may still have passed.", "tone": "bad", "checks": 2, "outcome": "checked", "missingTargets": [], "attemptSummary": "Latest attempt complete; discovery complete; 2/2 targets completed; 66 excluded (catalog model is not in the provider's confidential/TEE class)" } }, { "id": "3", "slug": "chutes", "name": "Chutes", "tagline": "Decentralized confidential inference on Bittensor with TEE", "description": "Chutes is a decentralized AI compute marketplace built on the Bittensor network. TEE-tagged models run inside AMD SEV-SNP and Intel TDX enclaves, providing verifiable privacy on community-run hardware. Offers the widest selection of open-source models with hardware-attested confidentiality.", "logo_url": null, "website_url": "https://chutes.ai", "api_docs_url": "https://chutes.ai/docs", "founded_year": null, "headquarters": null, "status": "active", "tee_types": [ { "type": "amd_sev_snp", "attestation_method": "AMD SEV-SNP Attestation Report", "notes": "Available on AMD-based Bittensor miner nodes" }, { "type": "intel_tdx", "attestation_method": "Intel DCAP Remote Attestation", "notes": "Available on Intel-based Bittensor miner nodes" } ], "models": [ { "name": "Gemma 4 31B Turbo", "slug": "gemma-4-31b-turbo", "family": "Google Gemma", "source_id": "google/gemma-4-31B-turbo-TEE", "context_window": 131072, "max_output_tokens": 65536 }, { "name": "Qwen3.8 27B", "slug": "qwen3.8-27b", "family": "Qwen", "source_id": "Qwen/Qwen3.8-27B-TEE", "context_window": 262144, "max_output_tokens": 65536 }, { "name": "DeepSeek V3.2", "slug": "deepseek-v3.2", "family": "DeepSeek", "source_id": "deepseek-ai/DeepSeek-V3.2-TEE", "context_window": 131072, "max_output_tokens": 65536 }, { "name": "GLM 5.1", "slug": "glm-5.1", "family": "ZhipuAI GLM", "source_id": "zai-org/GLM-5.1-TEE", "context_window": 202752, "max_output_tokens": 65535 }, { "name": "DeepSeek V4 Flash 0731", "slug": "deepseek-v4-flash-0731", "family": "DeepSeek", "source_id": "deepseek-ai/DeepSeek-V4-Flash-0731-TEE", "context_window": 1048576, "max_output_tokens": 131072 }, { "name": "Qwen3.6 27B", "slug": "qwen3.6-27b", "family": "Qwen", "source_id": "Qwen/Qwen3.6-27B-TEE", "context_window": 262144, "max_output_tokens": 65536 }, { "name": "Qwen3.5 397B A17B", "slug": "qwen3.5-397b-a17b", "family": "Qwen", "source_id": "Qwen/Qwen3.5-397B-A17B-TEE", "context_window": 262144, "max_output_tokens": 65536 }, { "name": "Kimi K2.6", "slug": "kimi-k2.6", "family": "Moonshot AI", "source_id": "moonshotai/Kimi-K2.6-TEE", "context_window": 262144, "max_output_tokens": 65535 }, { "name": "GLM 5.2", "slug": "glm-5.2", "family": "ZhipuAI GLM", "source_id": "zai-org/GLM-5.2-TEE", "context_window": 1048576, "max_output_tokens": 65535 }, { "name": "Qwen3 32B", "slug": "qwen3-32b", "family": "Qwen", "source_id": "Qwen/Qwen3-32B-TEE", "context_window": 40960, "max_output_tokens": 40960 }, { "name": "Kimi K3", "slug": "kimi-k3", "family": "Moonshot AI", "source_id": "moonshotai/Kimi-K3-TEE", "context_window": 1048576, "max_output_tokens": 65535 }, { "name": "Mistral Nemo 2407", "slug": "mistral-nemo-2407", "family": "Mistral", "source_id": "unsloth/Mistral-Nemo-Instruct-2407-TEE", "context_window": 131072, "max_output_tokens": null }, { "name": "Qwen3 235B A22B Thinking 2507", "slug": "qwen3-235b-a22b-thinking-2507", "family": "Qwen", "source_id": "Qwen/Qwen3-235B-A22B-Thinking-2507-TEE", "context_window": 262144, "max_output_tokens": 262144 }, { "name": "Nemotron 3 Nano Omni 30B", "slug": "nemotron-3-nano-omni-30b", "family": "Unknown", "source_id": "Nemotron-3-Nano-Omni-30B-TEE", "context_window": 131072, "max_output_tokens": null } ], "pricing": [ { "model_name": "Gemma 4 31B Turbo", "price_per_million_input_tokens": 0.12, "price_per_million_output_tokens": 0.37, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "google/gemma-4-31B-turbo-TEE", "offering_id": "google/gemma-4-31B-turbo-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.8 27B", "price_per_million_input_tokens": 0.039, "price_per_million_output_tokens": 1.25, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "Qwen/Qwen3.8-27B-TEE", "offering_id": "Qwen/Qwen3.8-27B-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "DeepSeek V3.2", "price_per_million_input_tokens": 1, "price_per_million_output_tokens": 1, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "deepseek-ai/DeepSeek-V3.2-TEE", "offering_id": "deepseek-ai/DeepSeek-V3.2-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.1", "price_per_million_input_tokens": 0.98, "price_per_million_output_tokens": 3.08, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "zai-org/GLM-5.1-TEE", "offering_id": "zai-org/GLM-5.1-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "DeepSeek V4 Flash 0731", "price_per_million_input_tokens": 0.44, "price_per_million_output_tokens": 1.32, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "deepseek-ai/DeepSeek-V4-Flash-0731-TEE", "offering_id": "deepseek-ai/DeepSeek-V4-Flash-0731-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.6 27B", "price_per_million_input_tokens": 0.25, "price_per_million_output_tokens": 2, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "Qwen/Qwen3.6-27B-TEE", "offering_id": "Qwen/Qwen3.6-27B-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.5 397B A17B", "price_per_million_input_tokens": 0.45, "price_per_million_output_tokens": 3, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "Qwen/Qwen3.5-397B-A17B-TEE", "offering_id": "Qwen/Qwen3.5-397B-A17B-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Kimi K2.6", "price_per_million_input_tokens": 0.45, "price_per_million_output_tokens": 1.95, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "moonshotai/Kimi-K2.6-TEE", "offering_id": "moonshotai/Kimi-K2.6-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.2", "price_per_million_input_tokens": 1.25, "price_per_million_output_tokens": 3.95, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "zai-org/GLM-5.2-TEE", "offering_id": "zai-org/GLM-5.2-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3 32B", "price_per_million_input_tokens": 0.104, "price_per_million_output_tokens": 0.416, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "Qwen/Qwen3-32B-TEE", "offering_id": "Qwen/Qwen3-32B-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Kimi K3", "price_per_million_input_tokens": 1.85, "price_per_million_output_tokens": 9.5, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "moonshotai/Kimi-K3-TEE", "offering_id": "moonshotai/Kimi-K3-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Mistral Nemo 2407", "price_per_million_input_tokens": 0.0245, "price_per_million_output_tokens": 0.0978, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "unsloth/Mistral-Nemo-Instruct-2407-TEE", "offering_id": "unsloth/Mistral-Nemo-Instruct-2407-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3 235B A22B Thinking 2507", "price_per_million_input_tokens": 0.2989, "price_per_million_output_tokens": 1.1957, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "Qwen/Qwen3-235B-A22B-Thinking-2507-TEE", "offering_id": "Qwen/Qwen3-235B-A22B-Thinking-2507-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Nemotron 3 Nano Omni 30B", "price_per_million_input_tokens": 0.0245, "price_per_million_output_tokens": 0.0978, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "Nemotron-3-Nano-Omni-30B-TEE", "offering_id": "Nemotron-3-Nano-Omni-30B-TEE#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null } ], "api_features": { "openai_compatible": true, "streaming": true, "function_calling": false, "batch_inference": false, "vision": false, "embeddings": false, "max_concurrent_requests": null, "avg_latency_ms": null }, "payments": { "accepts_crypto": false, "accepts_bitcoin": false, "accepted_assets": [], "notes": null }, "attestation": { "documentation_url": null, "endpoint_url": null, "verifier_url": null, "evidence_format": null, "notes": null }, "sdks": [], "api_compatibility": { "openai_chat_completions": false, "openai_responses": false, "anthropic_messages": false, "notes": null }, "social_links": [], "source_urls": [ { "label": "Chutes security architecture", "url": "https://chutes.ai/docs/core-concepts/security-architecture", "checked_at": "2026-07-16" } ], "last_verified_at": null, "data_freshness": { "status": "fresh", "last_success_at": "2026-10-18T12:56:25Z", "last_attempt_at": "2026-10-18T12:56:25Z" }, "source_observations": { "models": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "prices": { "kind": "live", "status": "fresh", "source_url": "https://llm.chutes.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "metadata": { "kind": "declared", "status": "declared", "source_url": "https://chutes.ai/docs/core-concepts/security-architecture", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null } }, "organization_roles": [ "storefront", "aggregator", "workload-operator", "tee-platform" ], "trust_tier": "tee-only", "pqc": { "status": "classical", "kex": null, "kex_required": null, "classical_fallback": "observed", "notes": "Complete tested matrix on llm.chutes.ai (2026-10-19) negotiated no standardized hybrid group under a working authenticated baseline. A classical-only handshake completed in the tested matrix.", "source_url": null, "checked_at": "2026-10-19", "measured": { "display": "no-hybrid", "displayLabel": "No tested hybrid observed", "claims": [ "classical-fallback-observed", "no-tested-hybrid-observed" ], "claimLabels": [ "Classical fallback observed", "No tested hybrid observed" ], "hybridObserved": [], "classicalFallback": "observed", "defaultNegotiated": "X25519", "measuredAt": "2026-10-19T05:41:20.011Z", "stale": false, "boundToAttestedEndpoint": false, "boundCheckId": null, "boundAttemptId": null, "boundCheckedAt": null, "supportingAttemptIds": [ 2990, 2991, 2992, 2993, 2994, 2995, 2996, 2997 ], "endpoint": "llm.chutes.ai", "endpointId": "chutes-api", "vantage": "conf-inference", "runId": 33, "latestAttempt": { "at": "2026-10-19T05:41:11.294Z", "outcome": "negotiated", "endpointId": "chutes-api" }, "integrity": "verified", "lastObserved": null, "client": { "node": "v24.14.1", "openssl": "3.5.5" }, "evidenceLevel": "authenticated", "reasons": [ "a classical-only handshake completed — hybrid remains optional" ] } }, "current_assurance": { "state": "unreachable", "label": "Availability issue", "summary": "The verifier could not fetch fresh evidence for every check in this run.", "tone": "warn", "checks": 14, "outcome": "checked", "missingTargets": [], "attemptSummary": "Latest attempt complete; discovery complete; 14/14 targets completed" } }, { "id": "4", "slug": "near", "name": "NEAR AI", "tagline": "Private, verifiable AI — Intel TDX + NVIDIA H200 TEE with on-chain attestation", "description": "NEAR AI Cloud runs inference inside Intel TDX confidential VMs backed by NVIDIA H200 Confidential Computing GPUs. TLS terminates inside the TEE (not at an external load balancer), so prompts are never exposed in plaintext outside the enclave. An optional E2EE layer lets clients encrypt messages with the model's attested public key before they leave the machine. Attestation reports are verifiable on-chain via the NEAR blockchain.", "logo_url": null, "website_url": "https://cloud.near.ai", "api_docs_url": "https://docs.near.ai", "founded_year": null, "headquarters": "San Francisco, CA", "status": "beta", "tee_types": [ { "type": "intel_tdx", "attestation_method": "Intel DCAP Remote Attestation", "notes": "TLS terminates inside the TDX VM — prompts never leave the enclave in plaintext" }, { "type": "nvidia_h100_cc", "attestation_method": "NVIDIA NRAS", "notes": "8× NVIDIA H200 GPUs per node with GPU memory encryption and confidential computing" } ], "models": [ { "name": "DeepSeek V3.2", "slug": "deepseek-v3.2", "family": "DeepSeek", "source_id": "deepseek/deepseek-v3.2", "context_window": 128000, "max_output_tokens": null }, { "name": "Kimi K2.6", "slug": "kimi-k2.6", "family": "Moonshot AI", "source_id": "moonshotai/kimi-k2.6", "context_window": 262144, "max_output_tokens": null }, { "name": "Kimi K3", "slug": "kimi-k3", "family": "Moonshot AI", "source_id": "moonshotai/kimi-k3", "context_window": 1048576, "max_output_tokens": null }, { "name": "Privacy Filter", "slug": "privacy-filter", "family": "Unknown", "source_id": "openai/privacy-filter", "context_window": 512, "max_output_tokens": null }, { "name": "Whisper Large v3", "slug": "whisper-large-v3", "family": "OpenAI GPT", "source_id": "openai/whisper-large-v3", "context_window": 448, "max_output_tokens": null }, { "name": "Qwen3.5 397B A17B", "slug": "qwen3.5-397b-a17b", "family": "Qwen", "source_id": "qwen/qwen3.5-397b-a17b", "context_window": 128000, "max_output_tokens": null }, { "name": "Qwen3.6 35B A3B Fp8", "slug": "qwen3.6-35b-a3b-fp8", "family": "Qwen", "source_id": "Qwen/Qwen3.6-35B-A3B-FP8", "context_window": 262144, "max_output_tokens": null }, { "name": "Qwen3.8 27B", "slug": "qwen3.8-27b", "family": "Qwen", "source_id": "Qwen/Qwen3.8-27B", "context_window": 262144, "max_output_tokens": null }, { "name": "Qwen3-Embedding 0.6B", "slug": "qwen3-embedding-0.6b", "family": "Qwen", "source_id": "Qwen/Qwen3-Embedding-0.6B", "context_window": 32768, "max_output_tokens": null }, { "name": "Qwen3-Reranker 0.6B", "slug": "qwen3-reranker-0.6b", "family": "Qwen", "source_id": "Qwen/Qwen3-Reranker-0.6B", "context_window": 40960, "max_output_tokens": null }, { "name": "Qwen3-VL 30B A3B Instruct", "slug": "qwen3-vl-30b-a3b-instruct", "family": "Qwen", "source_id": "Qwen/Qwen3-VL-30B-A3B-Instruct", "context_window": 16384, "max_output_tokens": null }, { "name": "GLM 5.3 Flash", "slug": "glm-5.3-flash", "family": "ZhipuAI GLM", "source_id": "z-ai/glm-5.3-flash", "context_window": 1048576, "max_output_tokens": null } ], "pricing": [ { "model_name": "DeepSeek V3.2", "price_per_million_input_tokens": 1.1, "price_per_million_output_tokens": 1.1, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "deepseek/deepseek-v3.2", "offering_id": "deepseek/deepseek-v3.2#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Kimi K2.6", "price_per_million_input_tokens": 0.81, "price_per_million_output_tokens": 3.85, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "moonshotai/kimi-k2.6", "offering_id": "moonshotai/kimi-k2.6#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Kimi K3", "price_per_million_input_tokens": 3.3000000000000003, "price_per_million_output_tokens": 16.5, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "moonshotai/kimi-k3", "offering_id": "moonshotai/kimi-k3#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Privacy Filter", "price_per_million_input_tokens": 0.01, "price_per_million_output_tokens": 0, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "openai/privacy-filter", "offering_id": "openai/privacy-filter#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Whisper Large v3", "price_per_million_input_tokens": 0.01, "price_per_million_output_tokens": 0.01, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "openai/whisper-large-v3", "offering_id": "openai/whisper-large-v3#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.5 397B A17B", "price_per_million_input_tokens": 0.5, "price_per_million_output_tokens": 3.3000000000000003, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "qwen/qwen3.5-397b-a17b", "offering_id": "qwen/qwen3.5-397b-a17b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.6 35B A3B Fp8", "price_per_million_input_tokens": 0.17, "price_per_million_output_tokens": 1.1, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "Qwen/Qwen3.6-35B-A3B-FP8", "offering_id": "Qwen/Qwen3.6-35B-A3B-FP8#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.8 27B", "price_per_million_input_tokens": 0.04, "price_per_million_output_tokens": 1.35, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "Qwen/Qwen3.8-27B", "offering_id": "Qwen/Qwen3.8-27B#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3-Embedding 0.6B", "price_per_million_input_tokens": 0.01, "price_per_million_output_tokens": 0.01, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "Qwen/Qwen3-Embedding-0.6B", "offering_id": "Qwen/Qwen3-Embedding-0.6B#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3-Reranker 0.6B", "price_per_million_input_tokens": 0.01, "price_per_million_output_tokens": 0.01, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "Qwen/Qwen3-Reranker-0.6B", "offering_id": "Qwen/Qwen3-Reranker-0.6B#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3-VL 30B A3B Instruct", "price_per_million_input_tokens": 0.15, "price_per_million_output_tokens": 0.55, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "Qwen/Qwen3-VL-30B-A3B-Instruct", "offering_id": "Qwen/Qwen3-VL-30B-A3B-Instruct#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.3 Flash", "price_per_million_input_tokens": 0.08, "price_per_million_output_tokens": 0.5, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "z-ai/glm-5.3-flash", "offering_id": "z-ai/glm-5.3-flash#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null } ], "api_features": { "openai_compatible": true, "streaming": true, "function_calling": true, "batch_inference": false, "vision": false, "embeddings": false, "max_concurrent_requests": null, "avg_latency_ms": null }, "payments": { "accepts_crypto": false, "accepts_bitcoin": false, "accepted_assets": [], "notes": null }, "attestation": { "documentation_url": null, "endpoint_url": null, "verifier_url": null, "evidence_format": null, "notes": null }, "sdks": [], "api_compatibility": { "openai_chat_completions": false, "openai_responses": false, "anthropic_messages": false, "notes": null }, "social_links": [ { "label": "X", "url": "https://x.com/near_ai" } ], "source_urls": [ { "label": "NEAR AI private inference architecture", "url": "https://docs.near.ai/cloud/private-inference/", "checked_at": "2026-07-16" }, { "label": "NEAR AI TLS attestation verification", "url": "https://docs.near.ai/cloud/verification/tls/", "checked_at": "2026-07-16" } ], "last_verified_at": null, "data_freshness": { "status": "fresh", "last_success_at": "2026-10-18T12:56:25Z", "last_attempt_at": "2026-10-18T12:56:25Z" }, "source_observations": { "models": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "prices": { "kind": "live", "status": "fresh", "source_url": "https://cloud-api.near.ai/v1/models", "observed_at": "2026-10-18T12:56:22Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "metadata": { "kind": "declared", "status": "declared", "source_url": "https://docs.near.ai/cloud/private-inference/", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null } }, "organization_roles": [ "storefront", "aggregator" ], "trust_tier": "app-e2ee", "e2ee_capability": "x25519-xchacha20-poly1305", "pqc": { "status": "classical", "kex": null, "kex_required": null, "classical_fallback": "observed", "notes": "Complete tested matrix on cloud-api.near.ai (2026-10-19) negotiated no standardized hybrid group under a working authenticated baseline. A classical-only handshake completed in the tested matrix.", "source_url": null, "checked_at": "2026-10-19", "measured": { "display": "no-hybrid", "displayLabel": "No tested hybrid observed", "claims": [ "classical-fallback-observed", "no-tested-hybrid-observed" ], "claimLabels": [ "Classical fallback observed", "No tested hybrid observed" ], "hybridObserved": [], "classicalFallback": "observed", "defaultNegotiated": "X25519", "measuredAt": "2026-10-19T05:41:20.011Z", "stale": false, "boundToAttestedEndpoint": false, "boundCheckId": null, "boundAttemptId": null, "boundCheckedAt": null, "supportingAttemptIds": [ 3030, 3031, 3032, 3033, 3034, 3035, 3036, 3037 ], "endpoint": "cloud-api.near.ai", "endpointId": "near-api", "vantage": "conf-inference", "runId": 33, "latestAttempt": { "at": "2026-10-19T05:41:14.490Z", "outcome": "negotiated", "endpointId": "near-api" }, "integrity": "verified", "lastObserved": null, "client": { "node": "v24.14.1", "openssl": "3.5.5" }, "evidenceLevel": "authenticated", "reasons": [ "a classical-only handshake completed — hybrid remains optional" ] } }, "current_assurance": { "state": "failed", "label": "Explicit trust failures", "summary": "At least one check has an explicit mismatch or policy rejection; other evidence layers may still have passed.", "tone": "bad", "checks": 9, "outcome": "checked", "missingTargets": [], "attemptSummary": "Latest attempt complete; discovery complete; 9/9 targets completed; 48 excluded (45 × catalog model is not in the provider's confidential/TEE class; 3 × unsupported utility/modality or non-confidential model class)" } }, { "id": "5", "slug": "maple", "name": "Maple", "tagline": "Privacy-first inference with AWS Nitro Enclave attestation", "description": "trymaple.ai does not provide a public model list or public pricing without subscribing, so this directory does not currently cover Maple models or pricing.", "logo_url": null, "website_url": "https://trymaple.ai", "api_docs_url": "https://docs.maple.build", "founded_year": null, "headquarters": null, "status": "beta", "tee_types": [ { "type": "aws_nitro_enclave", "attestation_method": "AWS Nitro Enclave COSE attestation document", "notes": "The verifier validates the Nitro certificate chain, document signature, nonce, and enclave key binding" } ], "models": [], "pricing": [], "api_features": { "openai_compatible": true, "streaming": true, "function_calling": false, "batch_inference": false, "vision": true, "embeddings": false, "max_concurrent_requests": null, "avg_latency_ms": null }, "payments": { "accepts_crypto": false, "accepts_bitcoin": false, "accepted_assets": [], "notes": null }, "attestation": { "documentation_url": null, "endpoint_url": null, "verifier_url": null, "evidence_format": null, "notes": null }, "sdks": [], "api_compatibility": { "openai_chat_completions": false, "openai_responses": false, "anthropic_messages": false, "notes": null }, "social_links": [], "source_urls": [ { "label": "Maple documentation", "url": "https://docs.maple.build", "checked_at": "2026-07-16" } ], "last_verified_at": null, "data_freshness": { "status": "fresh", "last_success_at": "2026-10-18T12:56:25Z", "last_attempt_at": "2026-10-18T12:56:25Z" }, "source_observations": { "models": { "kind": "declared", "status": "declared", "source_url": "https://docs.maple.build", "observed_at": "2026-07-16", "attempted_at": "2026-10-18T12:56:23Z", "expires_at": null, "error": null, "empty_reason": null }, "prices": { "kind": "declared", "status": "declared", "source_url": "https://docs.maple.build", "observed_at": "2026-07-16", "attempted_at": "2026-10-18T12:56:23Z", "expires_at": null, "error": null, "empty_reason": null }, "metadata": { "kind": "declared", "status": "declared", "source_url": "https://docs.maple.build", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null } }, "organization_roles": [ "storefront", "workload-operator" ], "trust_tier": "app-e2ee", "e2ee_capability": "x25519", "pqc": { "status": "pq-gateway", "kex": "X25519MLKEM768", "kex_required": null, "classical_fallback": "observed", "notes": "Measured X25519MLKEM768 TLS on enclave.trymaple.ai (2026-10-19); the termination point is not proven inside the attested TEE. A classical-only handshake completed in the tested matrix.", "source_url": null, "checked_at": "2026-10-19", "measured": { "display": "hybrid-observed", "displayLabel": "Hybrid TLS observed", "claims": [ "hybrid-tls-observed", "classical-fallback-observed" ], "claimLabels": [ "Hybrid TLS observed", "Classical fallback observed" ], "hybridObserved": [ "X25519MLKEM768" ], "classicalFallback": "observed", "defaultNegotiated": "X25519MLKEM768", "measuredAt": "2026-10-19T05:41:20.011Z", "stale": false, "boundToAttestedEndpoint": false, "boundCheckId": null, "boundAttemptId": null, "boundCheckedAt": null, "supportingAttemptIds": [ 2998, 3001, 3002, 3003, 3006, 3009, 3010, 3011 ], "endpoint": "enclave.trymaple.ai", "endpointId": "maple-enclave", "vantage": "conf-inference", "runId": 33, "latestAttempt": { "at": "2026-10-19T05:41:12.386Z", "outcome": "negotiated", "endpointId": "maple-enclave" }, "integrity": "verified", "lastObserved": null, "client": { "node": "v24.14.1", "openssl": "3.5.5" }, "evidenceLevel": "authenticated", "reasons": [ "a classical-only handshake completed — hybrid remains optional" ] } }, "current_assurance": { "state": "incomplete", "label": "Incomplete evidence", "summary": "Hardware evidence may have passed, but one or more required evidence gates are excluded or not proven.", "tone": "warn", "checks": 1, "outcome": "checked", "missingTargets": [], "attemptSummary": "Latest attempt complete; discovery complete; 1/1 targets completed" } }, { "id": "6", "slug": "privatemode", "name": "Privatemode", "tagline": "EU-hosted confidential inference via Cosmian VM", "description": "Privatemode delivers privacy-first AI inference from EU data centers using Cosmian VM — a hardened confidential VM combining AMD SEV-SNP and Intel TDX. Accessed via Edgeless's JS/Python SDK, the service is designed for GDPR-sensitive workloads where data must remain within a cryptographically isolated enclave throughout processing.", "logo_url": null, "website_url": "https://privatemode.ai", "api_docs_url": "https://docs.privatemode.ai", "founded_year": null, "headquarters": "Paris, France", "status": "active", "tee_types": [ { "type": "amd_sev_snp", "attestation_method": "Contrast remote attestation (AMD SEV-SNP)", "notes": "Contrast enforces the active deployment manifest for confidential containers" }, { "type": "intel_tdx", "attestation_method": "Contrast remote attestation (Intel TDX)", "notes": "Contrast Coordinator and workload policies are remotely attested" } ], "models": [ { "name": "DeepSeek OCR 2", "slug": "deepseek-ocr-2", "family": "DeepSeek", "source_id": "deepseek-ocr-2", "context_window": 8192, "max_output_tokens": null }, { "name": "GLM 5.3", "slug": "glm-5.3", "family": "ZhipuAI GLM", "source_id": "glm-5.3", "context_window": 262144, "max_output_tokens": null }, { "name": "GLM 5.3 Flash", "slug": "glm-5.3-flash", "family": "ZhipuAI GLM", "source_id": "glm-5.3-flash", "context_window": 262144, "max_output_tokens": null }, { "name": "GPT-OSS 120B", "slug": "gpt-oss-120b", "family": "OpenAI GPT", "source_id": "gpt-oss-120b", "context_window": 131072, "max_output_tokens": null }, { "name": "Whisper Large v3", "slug": "whisper-large-v3", "family": "OpenAI GPT", "source_id": "whisper-large-v3", "context_window": 30000, "max_output_tokens": null }, { "name": "Qwen3 Embedding 4B", "slug": "qwen3-embedding-4b", "family": "Qwen", "source_id": "qwen3-embedding-4b", "context_window": 32768, "max_output_tokens": null }, { "name": "Voxtral Mini 3B", "slug": "voxtral-mini-3b", "family": "Mistral", "source_id": "voxtral-mini-3b", "context_window": 32768, "max_output_tokens": null } ], "pricing": [ { "model_name": "DeepSeek OCR 2", "price_per_million_input_tokens": 0.866481, "price_per_million_output_tokens": 1.429131, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "$0.866481 in / $1.42913 out per 1M tokens (preview)", "source_id": "deepseek-ocr-2", "offering_id": "deepseek-ocr-2#tokens", "unit": "tokens", "currency": "USD", "original_currency": "EUR", "original_input_price": 0.77, "original_output_price": 1.27, "fx_rate": 1.1253, "fx_source_url": "https://api.frankfurter.dev/v1/latest?from=EUR&to=USD", "fx_observed_at": "2026-10-18T12:56:23Z", "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://www.privatemode.ai/pricing", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": "2026-10-18T12:56:23Z", "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.3", "price_per_million_input_tokens": 1.744215, "price_per_million_output_tokens": 6.4592220000000005, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "$1.74422 in / $6.45922 out per 1M tokens (preview)", "source_id": "glm-5.3", "offering_id": "glm-5.3#tokens", "unit": "tokens", "currency": "USD", "original_currency": "EUR", "original_input_price": 1.55, "original_output_price": 5.74, "fx_rate": 1.1253, "fx_source_url": "https://api.frankfurter.dev/v1/latest?from=EUR&to=USD", "fx_observed_at": "2026-10-18T12:56:23Z", "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://www.privatemode.ai/pricing", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": "2026-10-18T12:56:23Z", "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.3 Flash", "price_per_million_input_tokens": 0.22506, "price_per_million_output_tokens": 0.731445, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "$0.22506 in / $0.731445 out per 1M tokens (preview)", "source_id": "glm-5.3-flash", "offering_id": "glm-5.3-flash#tokens", "unit": "tokens", "currency": "USD", "original_currency": "EUR", "original_input_price": 0.2, "original_output_price": 0.65, "fx_rate": 1.1253, "fx_source_url": "https://api.frankfurter.dev/v1/latest?from=EUR&to=USD", "fx_observed_at": "2026-10-18T12:56:23Z", "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://www.privatemode.ai/pricing", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": "2026-10-18T12:56:23Z", "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GPT-OSS 120B", "price_per_million_input_tokens": 0.22506, "price_per_million_output_tokens": 0.731445, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "$0.22506 in / $0.731445 out per 1M tokens", "source_id": "gpt-oss-120b", "offering_id": "gpt-oss-120b#tokens", "unit": "tokens", "currency": "USD", "original_currency": "EUR", "original_input_price": 0.2, "original_output_price": 0.65, "fx_rate": 1.1253, "fx_source_url": "https://api.frankfurter.dev/v1/latest?from=EUR&to=USD", "fx_observed_at": "2026-10-18T12:56:23Z", "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://www.privatemode.ai/pricing", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": "2026-10-18T12:56:23Z", "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Whisper Large v3", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": 0.0157542, "pricing_model": "per_audio_minute", "free_tier": false, "notes": "$0.0157542/min audio", "source_id": "whisper-large-v3", "offering_id": "whisper-large-v3#audio-minute", "unit": "audio-minute", "currency": "USD", "original_currency": "EUR", "original_input_price": 0.014, "original_output_price": null, "fx_rate": 1.1253, "fx_source_url": "https://api.frankfurter.dev/v1/latest?from=EUR&to=USD", "fx_observed_at": "2026-10-18T12:56:23Z", "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://www.privatemode.ai/pricing", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": "2026-10-18T12:56:23Z", "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3 Embedding 4B", "price_per_million_input_tokens": 0.146289, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": "$0.146289/1M tokens", "source_id": "qwen3-embedding-4b", "offering_id": "qwen3-embedding-4b#tokens", "unit": "tokens", "currency": "USD", "original_currency": "EUR", "original_input_price": 0.13, "original_output_price": null, "fx_rate": 1.1253, "fx_source_url": "https://api.frankfurter.dev/v1/latest?from=EUR&to=USD", "fx_observed_at": "2026-10-18T12:56:23Z", "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://www.privatemode.ai/pricing", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": "2026-10-18T12:56:23Z", "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Voxtral Mini 3B", "price_per_million_input_tokens": null, "price_per_million_output_tokens": null, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": 0.0045012, "pricing_model": "per_audio_minute", "free_tier": false, "notes": "$0.0045012/min audio", "source_id": "voxtral-mini-3b", "offering_id": "voxtral-mini-3b#audio-minute", "unit": "audio-minute", "currency": "USD", "original_currency": "EUR", "original_input_price": 0.004, "original_output_price": null, "fx_rate": 1.1253, "fx_source_url": "https://api.frankfurter.dev/v1/latest?from=EUR&to=USD", "fx_observed_at": "2026-10-18T12:56:23Z", "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://www.privatemode.ai/pricing", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": "2026-10-18T12:56:23Z", "expires_at": null, "error": null, "empty_reason": null }, "conditions": null } ], "api_features": { "openai_compatible": true, "streaming": true, "function_calling": false, "batch_inference": false, "vision": true, "embeddings": true, "max_concurrent_requests": null, "avg_latency_ms": null }, "payments": { "accepts_crypto": false, "accepts_bitcoin": false, "accepted_assets": [], "notes": null }, "attestation": { "documentation_url": "https://docs.privatemode.ai/guides/verify-source/", "endpoint_url": "https://cdn.confidential.cloud/privatemode/v2/manifest.json", "verifier_url": "https://docs.privatemode.ai/reference/sdk/", "evidence_format": "SDK-era attestation document (SNP quote + embedded AMD chain + manifest history) verified against the CDN manifest over api.privatemode.ai", "notes": "The public manifest contains reference values only; it is not verification by itself. The standalone Contrast coordinator endpoint was retired in September 2026; the monitor now verifies the SDK-era attestation flow over api.privatemode.ai (SNP quote, AMD chain, report-data nonce binding, active manifest match, policy bindings). Privatemode advertises an attested sealed channel from SDK to enclave; the monitor observes the mesh-CA handshake signature but does not yet independently prove the sealed channel end-to-end — it is not monitor-verified E2EE." }, "sdks": [], "api_compatibility": { "openai_chat_completions": false, "openai_responses": false, "anthropic_messages": false, "notes": null }, "social_links": [ { "label": "X", "url": "https://x.com/edgelesssystems" } ], "source_urls": [ { "label": "Privatemode architecture", "url": "https://docs.privatemode.ai/architecture/overview", "checked_at": "2026-07-16" }, { "label": "Privatemode source verification", "url": "https://docs.privatemode.ai/guides/verify-source/", "checked_at": "2026-07-16" } ], "last_verified_at": null, "data_freshness": { "status": "fresh", "last_success_at": "2026-10-18T12:56:25Z", "last_attempt_at": "2026-10-18T12:56:25Z" }, "source_observations": { "models": { "kind": "live", "status": "fresh", "source_url": "https://api.privatemode.ai/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "prices": { "kind": "live", "status": "fresh", "source_url": "https://www.privatemode.ai/pricing", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": "2026-10-18T12:56:23Z", "expires_at": null, "error": null, "empty_reason": null }, "metadata": { "kind": "declared", "status": "declared", "source_url": "https://docs.privatemode.ai/architecture/overview", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "fx": { "kind": "live", "status": "fresh", "source_url": "https://api.frankfurter.dev/v1/latest?from=EUR&to=USD", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null } }, "organization_roles": [ "storefront", "workload-operator", "tee-platform" ], "trust_tier": "tee-only", "pqc": { "status": "pq-gateway", "kex": "X25519MLKEM768", "kex_required": null, "classical_fallback": "observed", "notes": "Measured X25519MLKEM768, SecP256r1MLKEM768, SecP384r1MLKEM1024 TLS on api.privatemode.ai (2026-10-19); the termination point is not proven inside the attested TEE. A classical-only handshake completed in the tested matrix.", "source_url": null, "checked_at": "2026-10-19", "measured": { "display": "hybrid-observed", "displayLabel": "Hybrid TLS observed", "claims": [ "hybrid-tls-observed", "classical-fallback-observed" ], "claimLabels": [ "Hybrid TLS observed", "Classical fallback observed" ], "hybridObserved": [ "X25519MLKEM768", "SecP256r1MLKEM768", "SecP384r1MLKEM1024" ], "classicalFallback": "observed", "defaultNegotiated": "X25519MLKEM768", "measuredAt": "2026-10-19T05:41:20.011Z", "stale": false, "boundToAttestedEndpoint": false, "boundCheckId": null, "boundAttemptId": null, "boundCheckedAt": null, "supportingAttemptIds": [ 3054, 3055, 3056, 3057, 3058, 3059 ], "endpoint": "api.privatemode.ai", "endpointId": "privatemode-api", "vantage": "conf-inference", "runId": 33, "latestAttempt": { "at": "2026-10-19T05:41:16.667Z", "outcome": "negotiated", "endpointId": "privatemode-api" }, "integrity": "verified", "lastObserved": null, "client": { "node": "v24.14.1", "openssl": "3.5.5" }, "evidenceLevel": "authenticated", "reasons": [ "a classical-only handshake completed — hybrid remains optional" ] } }, "current_assurance": { "state": "incomplete", "label": "Incomplete evidence", "summary": "Hardware evidence may have passed, but one or more required evidence gates are excluded or not proven.", "tone": "warn", "checks": 13, "outcome": "checked", "missingTargets": [], "attemptSummary": "Latest attempt complete; discovery complete; 13/13 targets completed" } }, { "id": "7", "slug": "ppq", "name": "PPQ.AI", "tagline": "Private TEE inference via hardware-attested confidential compute", "description": "PPQ.AI is a multi-model AI API platform that offers a dedicated private inference tier running inside hardware Trusted Execution Environments. Models prefixed with 'private/' execute in isolated enclaves with hardware attestation, ensuring that prompts and outputs remain confidential throughout the inference process.", "logo_url": null, "website_url": "https://ppq.ai", "api_docs_url": "https://ppq.ai/api-docs", "founded_year": null, "headquarters": null, "status": "active", "tee_types": [ { "type": "amd_sev_snp", "attestation_method": "Model-specific PPQ Tinfoil router attestation plus mapped Tinfoil model backend attestation", "notes": "Private inference is accessed through PPQ's private-mode proxy. The verifier checks the PPQ router bundle and attested HPKE key for each private model, then verifies the corresponding Tinfoil model backend enclave." } ], "models": [ { "name": "GPT-OSS 120B", "slug": "gpt-oss-120b", "family": "OpenAI GPT", "source_id": "private/gpt-oss-120b", "context_window": 131072, "max_output_tokens": null }, { "name": "Llama 3.3 70B", "slug": "llama-3.3-70b", "family": "Meta Llama", "source_id": "private/llama3-3-70b", "context_window": 131072, "max_output_tokens": null }, { "name": "GLM 5.3", "slug": "glm-5.3", "family": "ZhipuAI GLM", "source_id": "private/glm-5-3", "context_window": 1048576, "max_output_tokens": null }, { "name": "Gemma 4 31B", "slug": "gemma-4-31b", "family": "Google Gemma", "source_id": "private/gemma4-31b", "context_window": 262144, "max_output_tokens": null }, { "name": "Kimi K3", "slug": "kimi-k3", "family": "Moonshot AI", "source_id": "private/kimi-k3", "context_window": 256000, "max_output_tokens": null }, { "name": "DeepSeek V4.1 Flash", "slug": "deepseek-v4.1-flash", "family": "DeepSeek", "source_id": "private/deepseek-v4-1-flash", "context_window": 1048576, "max_output_tokens": null } ], "pricing": [ { "model_name": "GPT-OSS 120B", "price_per_million_input_tokens": 0.15824999999999997, "price_per_million_output_tokens": 0.6329999999999999, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "private/gpt-oss-120b", "offering_id": "private/gpt-oss-120b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.ppq.ai/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Llama 3.3 70B", "price_per_million_input_tokens": 1.84625, "price_per_million_output_tokens": 2.9012499999999997, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "private/llama3-3-70b", "offering_id": "private/llama3-3-70b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.ppq.ai/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.3", "price_per_million_input_tokens": 1.899, "price_per_million_output_tokens": 6.066249999999999, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "private/glm-5-3", "offering_id": "private/glm-5-3#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.ppq.ai/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Gemma 4 31B", "price_per_million_input_tokens": 0.422, "price_per_million_output_tokens": 1.055, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "private/gemma4-31b", "offering_id": "private/gemma4-31b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.ppq.ai/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Kimi K3", "price_per_million_input_tokens": 4.22, "price_per_million_output_tokens": 21.099999999999998, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "private/kimi-k3", "offering_id": "private/kimi-k3#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.ppq.ai/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "DeepSeek V4.1 Flash", "price_per_million_input_tokens": 0.68575, "price_per_million_output_tokens": 1.52975, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "private/deepseek-v4-1-flash", "offering_id": "private/deepseek-v4-1-flash#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.ppq.ai/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null } ], "api_features": { "openai_compatible": true, "streaming": true, "function_calling": true, "batch_inference": false, "vision": true, "embeddings": false, "max_concurrent_requests": null, "avg_latency_ms": null }, "payments": { "accepts_crypto": false, "accepts_bitcoin": false, "accepted_assets": [], "notes": null }, "attestation": { "documentation_url": "https://ppq.ai/api-docs", "endpoint_url": "https://api.ppq.ai/private/attestation", "verifier_url": "https://github.com/PayPerQ/ppq-private-mode-proxy", "evidence_format": "PPQ model-specific Tinfoil router ATC bundle plus Tinfoil model backend attestation", "notes": "The verifier checks the PPQ router and HPKE key for each current private model. Tinfoil backend checks are reported separately, and the PPQ-to-backend route remains unverified unless a request-bound route receipt is exposed." }, "sdks": [], "api_compatibility": { "openai_chat_completions": false, "openai_responses": false, "anthropic_messages": false, "notes": null }, "social_links": [ { "label": "X", "url": "https://x.com/PPQdotAI" } ], "source_urls": [ { "label": "PPQ private TEE model documentation", "url": "https://ppq.ai/api-docs#private-tee-models", "checked_at": "2026-07-16" }, { "label": "PPQ private mode proxy source", "url": "https://github.com/PayPerQ/ppq-private-mode-proxy", "checked_at": "2026-07-16" } ], "last_verified_at": null, "data_freshness": { "status": "fresh", "last_success_at": "2026-10-18T12:56:25Z", "last_attempt_at": "2026-10-18T12:56:25Z" }, "source_observations": { "models": { "kind": "live", "status": "fresh", "source_url": "https://api.ppq.ai/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "prices": { "kind": "live", "status": "fresh", "source_url": "https://api.ppq.ai/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "metadata": { "kind": "declared", "status": "declared", "source_url": "https://ppq.ai/api-docs#private-tee-models", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null } }, "organization_roles": [ "storefront", "aggregator" ], "trust_tier": "app-e2ee", "e2ee_capability": "hpke", "pqc": { "status": "pq-gateway", "kex": "X25519MLKEM768", "kex_required": null, "classical_fallback": "observed", "notes": "Measured X25519MLKEM768 TLS on api.ppq.ai (2026-10-19); the termination point is not proven inside the attested TEE. A classical-only handshake completed in the tested matrix.", "source_url": null, "checked_at": "2026-10-19", "measured": { "display": "hybrid-observed", "displayLabel": "Hybrid TLS observed", "claims": [ "hybrid-tls-observed", "classical-fallback-observed" ], "claimLabels": [ "Hybrid TLS observed", "Classical fallback observed" ], "hybridObserved": [ "X25519MLKEM768" ], "classicalFallback": "observed", "defaultNegotiated": "X25519MLKEM768", "measuredAt": "2026-10-19T05:41:20.011Z", "stale": false, "boundToAttestedEndpoint": false, "boundCheckId": null, "boundAttemptId": null, "boundCheckedAt": null, "supportingAttemptIds": [ 3062, 3065, 3066, 3067, 3070, 3073, 3074, 3075 ], "endpoint": "api.ppq.ai", "endpointId": "ppq-api", "vantage": "conf-inference", "runId": 33, "latestAttempt": { "at": "2026-10-19T05:41:16.948Z", "outcome": "negotiated", "endpointId": "ppq-api" }, "integrity": "verified", "lastObserved": null, "client": { "node": "v24.14.1", "openssl": "3.5.5" }, "evidenceLevel": "authenticated", "reasons": [ "a classical-only handshake completed — hybrid remains optional" ] } }, "current_assurance": { "state": "unreachable", "label": "Availability issue", "summary": "The verifier could not fetch fresh evidence for every check in this run.", "tone": "warn", "checks": 6, "outcome": "checked", "missingTargets": [], "attemptSummary": "Latest attempt complete; discovery complete; 6/6 targets completed; 385 excluded (catalog model is not in the provider's confidential/TEE class)" } }, { "id": "8", "slug": "venice", "name": "Venice.ai", "tagline": "End-to-end encrypted private AI with TEE attestation", "description": "Venice.ai is a privacy-first AI platform that combines end-to-end encryption with Trusted Execution Environment attestation. Conversations and model weights are protected through hardware-level confidential computing — Venice cannot access your prompts, and TEE attestation lets you verify this cryptographically. The E2EE private tier covers a curated set of open-source models with per-model pricing.", "logo_url": null, "website_url": "https://venice.ai", "api_docs_url": "https://docs.venice.ai", "founded_year": 2024, "headquarters": "United States", "status": "active", "tee_types": [ { "type": "intel_tdx", "attestation_method": "Intel DCAP remote attestation", "notes": "The model attestation response exposes a raw Intel TDX quote and verifier nonce" }, { "type": "nvidia_h100_cc", "attestation_method": "NVIDIA Confidential Computing attestation", "notes": "Models run in NVIDIA H100 Confidential Computing enclaves; TEE attestation verifiable per request" } ], "models": [ { "name": "Gemma 4 26B A4B Uncensored P", "slug": "gemma-4-26b-a4b-uncensored-p", "family": "Google Gemma", "source_id": "e2ee-gemma-4-26b-a4b-uncensored-p", "context_window": 64000, "max_output_tokens": 4096 }, { "name": "GLM 5.2 P", "slug": "glm-5.2-p", "family": "ZhipuAI GLM", "source_id": "e2ee-glm-5-2-p", "context_window": 524288, "max_output_tokens": 32768 }, { "name": "GLM 5.3 P", "slug": "glm-5.3-p", "family": "ZhipuAI GLM", "source_id": "e2ee-glm-5-3-p", "context_window": 1000000, "max_output_tokens": 32768 }, { "name": "GPT-OSS 120B", "slug": "gpt-oss-120b", "family": "OpenAI GPT", "source_id": "e2ee-gpt-oss-120b-p", "context_window": 128000, "max_output_tokens": 32768 }, { "name": "Kimi K3 P", "slug": "kimi-k3-p", "family": "Moonshot AI", "source_id": "e2ee-kimi-k3-p", "context_window": 1000000, "max_output_tokens": 131072 }, { "name": "Qwen2.5 7B", "slug": "qwen2.5-7b", "family": "Qwen", "source_id": "e2ee-qwen-2-5-7b-p", "context_window": 32000, "max_output_tokens": 4096 }, { "name": "Qwen3-VL 30B A3B", "slug": "qwen3-vl-30b-a3b", "family": "Qwen", "source_id": "e2ee-qwen3-vl-30b-a3b-p", "context_window": 128000, "max_output_tokens": 4096 }, { "name": "Qwen3.6 35B A3B", "slug": "qwen3.6-35b-a3b", "family": "Qwen", "source_id": "e2ee-qwen3-6-35b-a3b", "context_window": 32000, "max_output_tokens": 4096 }, { "name": "DeepSeek V4 Flash", "slug": "deepseek-v4-flash", "family": "DeepSeek", "source_id": "e2ee-deepseek-v4-flash", "context_window": 1000000, "max_output_tokens": 8192 }, { "name": "GLM 5.3 Flash", "slug": "glm-5.3-flash", "family": "ZhipuAI GLM", "source_id": "e2ee-glm-5-3-flash", "context_window": 1000000, "max_output_tokens": 32768 }, { "name": "Qwen3.8 27B", "slug": "qwen3.8-27b", "family": "Qwen", "source_id": "e2ee-qwen3-8-27b", "context_window": 262144, "max_output_tokens": 8192 }, { "name": "Kimi K2.6", "slug": "kimi-k2.6", "family": "Moonshot AI", "source_id": "e2ee-kimi-k2-6", "context_window": 262144, "max_output_tokens": 8192 } ], "pricing": [ { "model_name": "Gemma 4 26B A4B Uncensored P", "price_per_million_input_tokens": 0.19, "price_per_million_output_tokens": 0.88, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-gemma-4-26b-a4b-uncensored-p", "offering_id": "e2ee-gemma-4-26b-a4b-uncensored-p#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.2 P", "price_per_million_input_tokens": 1.75, "price_per_million_output_tokens": 5.75, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-glm-5-2-p", "offering_id": "e2ee-glm-5-2-p#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.3 P", "price_per_million_input_tokens": 1.75, "price_per_million_output_tokens": 5.5, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-glm-5-3-p", "offering_id": "e2ee-glm-5-3-p#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GPT-OSS 120B", "price_per_million_input_tokens": 0.13, "price_per_million_output_tokens": 0.65, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-gpt-oss-120b-p", "offering_id": "e2ee-gpt-oss-120b-p#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Kimi K3 P", "price_per_million_input_tokens": 3.75, "price_per_million_output_tokens": 18.75, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-kimi-k3-p", "offering_id": "e2ee-kimi-k3-p#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen2.5 7B", "price_per_million_input_tokens": 0.05, "price_per_million_output_tokens": 0.13, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-qwen-2-5-7b-p", "offering_id": "e2ee-qwen-2-5-7b-p#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3-VL 30B A3B", "price_per_million_input_tokens": 0.25, "price_per_million_output_tokens": 0.9, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-qwen3-vl-30b-a3b-p", "offering_id": "e2ee-qwen3-vl-30b-a3b-p#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.6 35B A3B", "price_per_million_input_tokens": 0.182, "price_per_million_output_tokens": 1.18, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-qwen3-6-35b-a3b", "offering_id": "e2ee-qwen3-6-35b-a3b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "DeepSeek V4 Flash", "price_per_million_input_tokens": 0.182, "price_per_million_output_tokens": 0.373, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-deepseek-v4-flash", "offering_id": "e2ee-deepseek-v4-flash#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "GLM 5.3 Flash", "price_per_million_input_tokens": 0.16, "price_per_million_output_tokens": 0.54, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-glm-5-3-flash", "offering_id": "e2ee-glm-5-3-flash#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Qwen3.8 27B", "price_per_million_input_tokens": 0.47, "price_per_million_output_tokens": 3.53, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-qwen3-8-27b", "offering_id": "e2ee-qwen3-8-27b#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null }, { "model_name": "Kimi K2.6", "price_per_million_input_tokens": 0.87, "price_per_million_output_tokens": 4.12, "price_per_million_cached_input_tokens": null, "price_per_million_cache_write_tokens": null, "price_per_hour": null, "price_per_request": null, "price_per_audio_minute": null, "pricing_model": "per_token", "free_tier": false, "notes": null, "source_id": "e2ee-kimi-k2-6", "offering_id": "e2ee-kimi-k2-6#tokens", "unit": "tokens", "currency": "USD", "original_currency": null, "original_input_price": null, "original_output_price": null, "fx_rate": null, "fx_source_url": null, "fx_observed_at": null, "source_observation": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "conditions": null } ], "api_features": { "openai_compatible": true, "streaming": true, "function_calling": true, "batch_inference": false, "vision": true, "embeddings": false, "max_concurrent_requests": null, "avg_latency_ms": null }, "payments": { "accepts_crypto": false, "accepts_bitcoin": false, "accepted_assets": [], "notes": null }, "attestation": { "documentation_url": null, "endpoint_url": null, "verifier_url": null, "evidence_format": null, "notes": null }, "sdks": [], "api_compatibility": { "openai_chat_completions": false, "openai_responses": false, "anthropic_messages": false, "notes": null }, "social_links": [ { "label": "X", "url": "https://x.com/askvenice" } ], "source_urls": [ { "label": "Venice TEE and E2EE model verification", "url": "https://docs.venice.ai/guides/features/tee-e2ee-models", "checked_at": "2026-07-16" } ], "last_verified_at": null, "data_freshness": { "status": "fresh", "last_success_at": "2026-10-18T12:56:25Z", "last_attempt_at": "2026-10-18T12:56:25Z" }, "source_observations": { "models": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "prices": { "kind": "live", "status": "fresh", "source_url": "https://api.venice.ai/api/v1/models", "observed_at": "2026-10-18T12:56:23Z", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null }, "metadata": { "kind": "declared", "status": "declared", "source_url": "https://docs.venice.ai/guides/features/tee-e2ee-models", "observed_at": "2026-07-16", "attempted_at": null, "expires_at": null, "error": null, "empty_reason": null } }, "organization_roles": [ "storefront", "aggregator" ], "trust_tier": "app-e2ee", "e2ee_capability": "ecdh", "pqc": { "status": "pq-gateway", "kex": "X25519MLKEM768", "kex_required": null, "classical_fallback": "observed", "notes": "Measured X25519MLKEM768 TLS on api.venice.ai (2026-10-19); the termination point is not proven inside the attested TEE. A classical-only handshake completed in the tested matrix.", "source_url": null, "checked_at": "2026-10-19", "measured": { "display": "hybrid-observed", "displayLabel": "Hybrid TLS observed", "claims": [ "hybrid-tls-observed", "classical-fallback-observed" ], "claimLabels": [ "Hybrid TLS observed", "Classical fallback observed" ], "hybridObserved": [ "X25519MLKEM768" ], "classicalFallback": "observed", "defaultNegotiated": "X25519MLKEM768", "measuredAt": "2026-10-19T05:41:20.011Z", "stale": false, "boundToAttestedEndpoint": false, "boundCheckId": null, "boundAttemptId": null, "boundCheckedAt": null, "supportingAttemptIds": [ 3086, 3089, 3090, 3091, 3094, 3097, 3098, 3099 ], "endpoint": "api.venice.ai", "endpointId": "venice-api", "vantage": "conf-inference", "runId": 33, "latestAttempt": { "at": "2026-10-19T05:41:19.974Z", "outcome": "negotiated", "endpointId": "venice-api" }, "integrity": "verified", "lastObserved": null, "client": { "node": "v24.14.1", "openssl": "3.5.5" }, "evidenceLevel": "authenticated", "reasons": [ "a classical-only handshake completed — hybrid remains optional" ] } }, "current_assurance": { "state": "failed", "label": "Explicit trust failures", "summary": "At least one check has an explicit mismatch or policy rejection; other evidence layers may still have passed.", "tone": "bad", "checks": 12, "outcome": "checked", "missingTargets": [], "attemptSummary": "Latest attempt complete; discovery complete; 12/12 targets completed; 124 excluded (catalog model is not in the provider's confidential/TEE class)" } } ] }