{
  "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": "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": "Venice Uncensored 24B",
      "slug": "venice-uncensored-24b",
      "family": "Custom",
      "context_window": 32000,
      "max_output_tokens": 8192
    },
    {
      "name": "Gemma 3 27B",
      "slug": "gemma-3-27b",
      "family": "Google Gemma",
      "context_window": 40000,
      "max_output_tokens": 4096
    },
    {
      "name": "Gemma 4 26B A4B Uncensored",
      "slug": "gemma-4-26b-a4b-uncensored",
      "family": "Google Gemma",
      "context_window": 64000,
      "max_output_tokens": 4096
    },
    {
      "name": "GLM 5.2",
      "slug": "glm-5.2",
      "family": "ZhipuAI GLM",
      "context_window": 524288,
      "max_output_tokens": 32768
    },
    {
      "name": "GLM 4.7",
      "slug": "glm-4.7",
      "family": "ZhipuAI GLM",
      "context_window": 128000,
      "max_output_tokens": 32768
    },
    {
      "name": "GPT-OSS 20B",
      "slug": "gpt-oss-20b",
      "family": "OpenAI GPT",
      "context_window": 128000,
      "max_output_tokens": 32768
    },
    {
      "name": "GPT-OSS 120B",
      "slug": "gpt-oss-120b",
      "family": "OpenAI GPT",
      "context_window": 128000,
      "max_output_tokens": 32768
    },
    {
      "name": "Qwen2.5 7B",
      "slug": "qwen2.5-7b",
      "family": "Qwen",
      "context_window": 32000,
      "max_output_tokens": 4096
    },
    {
      "name": "Qwen3.6 35B A3B Uncensored",
      "slug": "qwen3.6-35b-a3b-uncensored",
      "family": "Qwen",
      "context_window": 128000,
      "max_output_tokens": 4096
    },
    {
      "name": "Qwen3 30B A3B",
      "slug": "qwen3-30b-a3b",
      "family": "Qwen",
      "context_window": 256000,
      "max_output_tokens": 32768
    },
    {
      "name": "Qwen3-VL 30B A3B",
      "slug": "qwen3-vl-30b-a3b",
      "family": "Qwen",
      "context_window": 128000,
      "max_output_tokens": 4096
    },
    {
      "name": "GLM 5.1",
      "slug": "glm-5.1",
      "family": "ZhipuAI GLM",
      "context_window": 200000,
      "max_output_tokens": 32768
    },
    {
      "name": "Qwen3.6 35B A3B",
      "slug": "qwen3.6-35b-a3b",
      "family": "Qwen",
      "context_window": 32000,
      "max_output_tokens": 4096
    },
    {
      "name": "Gemma 4 31B",
      "slug": "gemma-4-31b",
      "family": "Google Gemma",
      "context_window": 32000,
      "max_output_tokens": 4096
    }
  ],
  "pricing": [
    {
      "model_name": "Venice Uncensored 24B",
      "price_per_million_input_tokens": 0.25,
      "price_per_million_output_tokens": 1.15,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": null
    },
    {
      "model_name": "Gemma 3 27B",
      "price_per_million_input_tokens": 0.14,
      "price_per_million_output_tokens": 0.5,
      "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": 0.19,
      "price_per_million_output_tokens": 0.88,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": null
    },
    {
      "model_name": "GLM 5.2",
      "price_per_million_input_tokens": 1.75,
      "price_per_million_output_tokens": 5.75,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": null
    },
    {
      "model_name": "GLM 4.7",
      "price_per_million_input_tokens": 1.1,
      "price_per_million_output_tokens": 4.15,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": null
    },
    {
      "model_name": "GPT-OSS 20B",
      "price_per_million_input_tokens": 0.05,
      "price_per_million_output_tokens": 0.19,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": null
    },
    {
      "model_name": "GPT-OSS 120B",
      "price_per_million_input_tokens": 0.13,
      "price_per_million_output_tokens": 0.65,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": null
    },
    {
      "model_name": "Qwen2.5 7B",
      "price_per_million_input_tokens": 0.05,
      "price_per_million_output_tokens": 0.13,
      "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": 0.38,
      "price_per_million_output_tokens": 1.88,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": null
    },
    {
      "model_name": "Qwen3 30B A3B",
      "price_per_million_input_tokens": 0.19,
      "price_per_million_output_tokens": 0.69,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": null
    },
    {
      "model_name": "Qwen3-VL 30B A3B",
      "price_per_million_input_tokens": 0.25,
      "price_per_million_output_tokens": 0.9,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": null
    },
    {
      "model_name": "GLM 5.1",
      "price_per_million_input_tokens": 1.1,
      "price_per_million_output_tokens": 4.15,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": null
    },
    {
      "model_name": "Qwen3.6 35B A3B",
      "price_per_million_input_tokens": 0.182,
      "price_per_million_output_tokens": 1.18,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": null
    },
    {
      "model_name": "Gemma 4 31B",
      "price_per_million_input_tokens": 0.139,
      "price_per_million_output_tokens": 0.43,
      "price_per_hour": null,
      "pricing_model": "per_token",
      "free_tier": false,
      "notes": 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": [],
  "last_verified_at": null,
  "trust_tier": "app-e2ee",
  "infra_provider": "phala-dstack",
  "e2ee_capability": "ecdh"
}