{ "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": "Qwen3.6 27B", "slug": "qwen3.6-27b", "family": "Qwen", "context_window": 262100, "max_output_tokens": null }, { "name": "Qwen3 235B A22B", "slug": "qwen3-235b-a22b", "family": "Qwen", "context_window": 256000, "max_output_tokens": null }, { "name": "GPT-OSS 120B", "slug": "gpt-oss-120b", "family": "OpenAI GPT", "context_window": 131072, "max_output_tokens": null }, { "name": "GPT-OSS 20B", "slug": "gpt-oss-20b", "family": "OpenAI GPT", "context_window": 131072, "max_output_tokens": null }, { "name": "Qwen2.5-VL 72B", "slug": "qwen2.5-vl-72b", "family": "Qwen", "context_window": 65536, "max_output_tokens": null }, { "name": "DeepSeek V3.1", "slug": "deepseek-v3.1", "family": "DeepSeek", "context_window": 164000, "max_output_tokens": null }, { "name": "DeepSeek V3.2", "slug": "deepseek-v3.2", "family": "DeepSeek", "context_window": 164000, "max_output_tokens": null }, { "name": "Qwen3 30B A3B", "slug": "qwen3-30b-a3b", "family": "Qwen", "context_window": 262000, "max_output_tokens": null }, { "name": "Qwen3.6 35B A3B Uncensored", "slug": "qwen3.6-35b-a3b-uncensored", "family": "Qwen", "context_window": 131100, "max_output_tokens": null }, { "name": "Qwen3.5 27B", "slug": "qwen3.5-27b", "family": "Qwen", "context_window": 262100, "max_output_tokens": null }, { "name": "Qwen3.5 397B A17B", "slug": "qwen3.5-397b-a17b", "family": "Qwen", "context_window": 262100, "max_output_tokens": null }, { "name": "Qwen3.5 122B A10B", "slug": "qwen3.5-122b-a10b", "family": "Qwen", "context_window": 262100, "max_output_tokens": null }, { "name": "Gemma 4 31B IT", "slug": "gemma-4-31b-it", "family": "Google Gemma", "context_window": 262100, "max_output_tokens": null }, { "name": "Gemma 4 26B A4B Uncensored", "slug": "gemma-4-26b-a4b-uncensored", "family": "Google Gemma", "context_window": 65500, "max_output_tokens": null }, { "name": "GLM 4.7 Flash", "slug": "glm-4.7-flash", "family": "ZhipuAI GLM", "context_window": 203000, "max_output_tokens": null }, { "name": "Gemma 3 27B", "slug": "gemma-3-27b", "family": "Google Gemma", "context_window": 131072, "max_output_tokens": null }, { "name": "Gemma 4 31B", "slug": "gemma-4-31b", "family": "Google Gemma", "context_window": 262100, "max_output_tokens": null }, { "name": "Gemma 4 31B Thinking", "slug": "gemma-4-31b-thinking", "family": "Google Gemma", "context_window": 262100, "max_output_tokens": null }, { "name": "Llama 3.3 70B", "slug": "llama-3.3-70b", "family": "Meta Llama", "context_window": 128000, "max_output_tokens": null }, { "name": "DeepSeek V4 Pro", "slug": "deepseek-v4-pro", "family": "DeepSeek", "context_window": 800000, "max_output_tokens": null }, { "name": "DeepSeek V4 Pro Thinking", "slug": "deepseek-v4-pro-thinking", "family": "DeepSeek", "context_window": 800000, "max_output_tokens": null }, { "name": "MiniMax M2.5", "slug": "minimax-m2.5", "family": "MiniMax", "context_window": 196600, "max_output_tokens": null }, { "name": "Kimi K2.5", "slug": "kimi-k2.5", "family": "Moonshot AI", "context_window": 128000, "max_output_tokens": null }, { "name": "Kimi K2.5 Thinking", "slug": "kimi-k2.5-thinking", "family": "Moonshot AI", "context_window": 128000, "max_output_tokens": null }, { "name": "Kimi K2.6", "slug": "kimi-k2.6", "family": "Moonshot AI", "context_window": 4096, "max_output_tokens": null }, { "name": "GLM 4.7", "slug": "glm-4.7", "family": "ZhipuAI GLM", "context_window": 131000, "max_output_tokens": null }, { "name": "GLM 5", "slug": "glm-5", "family": "ZhipuAI GLM", "context_window": 203000, "max_output_tokens": null }, { "name": "GLM 5.1", "slug": "glm-5.1", "family": "ZhipuAI GLM", "context_window": 4096, "max_output_tokens": null }, { "name": "GLM 5.1 Thinking", "slug": "glm-5.1-thinking", "family": "ZhipuAI GLM", "context_window": 4096, "max_output_tokens": null } ], "pricing": [ { "model_name": "Qwen3.6 27B", "price_per_million_input_tokens": 0.32, "price_per_million_output_tokens": 2.7, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Qwen3 235B A22B", "price_per_million_input_tokens": 0.13, "price_per_million_output_tokens": 0.5, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "GPT-OSS 120B", "price_per_million_input_tokens": 2, "price_per_million_output_tokens": 2, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "GPT-OSS 20B", "price_per_million_input_tokens": 0.2, "price_per_million_output_tokens": 0.8, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Qwen2.5-VL 72B", "price_per_million_input_tokens": 0.7, "price_per_million_output_tokens": 0.7, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "DeepSeek V3.1", "price_per_million_input_tokens": 1, "price_per_million_output_tokens": 2.5, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "DeepSeek V3.2", "price_per_million_input_tokens": 0.5, "price_per_million_output_tokens": 1, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Qwen3 30B A3B", "price_per_million_input_tokens": 0.15, "price_per_million_output_tokens": 0.45, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Qwen3.6 35B A3B Uncensored", "price_per_million_input_tokens": 0.3, "price_per_million_output_tokens": 1.5, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Qwen3.5 27B", "price_per_million_input_tokens": 0.3, "price_per_million_output_tokens": 2.4, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Qwen3.5 397B A17B", "price_per_million_input_tokens": 0.55, "price_per_million_output_tokens": 3.5, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Qwen3.5 122B A10B", "price_per_million_input_tokens": 0.46, "price_per_million_output_tokens": 3.68, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Gemma 4 31B IT", "price_per_million_input_tokens": 0.15, "price_per_million_output_tokens": 0.46, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Gemma 4 26B A4B Uncensored", "price_per_million_input_tokens": 0.15, "price_per_million_output_tokens": 0.7, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "GLM 4.7 Flash", "price_per_million_input_tokens": 0.15, "price_per_million_output_tokens": 0.5, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Gemma 3 27B", "price_per_million_input_tokens": 0.2, "price_per_million_output_tokens": 0.8, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Gemma 4 31B", "price_per_million_input_tokens": 0.45, "price_per_million_output_tokens": 1, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Gemma 4 31B Thinking", "price_per_million_input_tokens": 0.45, "price_per_million_output_tokens": 1, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Llama 3.3 70B", "price_per_million_input_tokens": 2, "price_per_million_output_tokens": 2, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "DeepSeek V4 Pro", "price_per_million_input_tokens": 1.5, "price_per_million_output_tokens": 5.25, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": "Cache read $0.15/1M tokens" }, { "model_name": "DeepSeek V4 Pro Thinking", "price_per_million_input_tokens": 1.5, "price_per_million_output_tokens": 5.25, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": "Cache read $0.15/1M tokens" }, { "model_name": "MiniMax M2.5", "price_per_million_input_tokens": 0.2, "price_per_million_output_tokens": 1.38, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Kimi K2.5", "price_per_million_input_tokens": 0.6, "price_per_million_output_tokens": 3, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Kimi K2.5 Thinking", "price_per_million_input_tokens": 0.6, "price_per_million_output_tokens": 3, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "Kimi K2.6", "price_per_million_input_tokens": 1.5, "price_per_million_output_tokens": 5.25, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": "Cache read $0.38/1M tokens" }, { "model_name": "GLM 4.7", "price_per_million_input_tokens": 0.85, "price_per_million_output_tokens": 3.3, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": null }, { "model_name": "GLM 5", "price_per_million_input_tokens": 1.2, "price_per_million_output_tokens": 3.5, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": "Cache read $0.24/1M tokens" }, { "model_name": "GLM 5.1", "price_per_million_input_tokens": 1.5, "price_per_million_output_tokens": 5.25, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": "Cache read $0.30/1M tokens" }, { "model_name": "GLM 5.1 Thinking", "price_per_million_input_tokens": 1.5, "price_per_million_output_tokens": 5.25, "price_per_hour": null, "pricing_model": "per_token", "free_tier": false, "notes": "Cache read $0.30/1M tokens" } ], "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", "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": [], "last_verified_at": null, "trust_tier": "tee-only" }