Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.venice.ai/llms.txt

Use this file to discover all available pages before exploring further.

The API for private, unrestricted access to intelligence.

OpenAI-compatible chat, image, audio, and video behind one API key.

Get an API key →Get started
curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org-glm-5-1",
    "messages": [{"role": "user", "content": "Build without permission."}]
  }'

Endpoints

​
One API for every modality

Chat, image, audio, video, and embeddings behind one API key.

Chat Completions

OpenAI-compatible chat with reasoning, tool use, and streaming across 100+ text models.

StreamingToolsVision
See reference →Image Generation

Text-to-image, image-to-image, upscaling, and background removal across photorealistic, stylized, and uncensored models.

Text-to-imageImage-to-imageUpscale
See reference →Audio

Text-to-speech with 50+ multilingual voices, plus speech-to-text transcription for any audio file.

TTSTranscription50+ voices
See reference →Video

Text-to-video, image-to-video, and reference-to-video through a sync or async job queue.

Text-to-videoImage-to-videoReference-to-video
See reference →

Plus embeddings, file inputs, MCP tools, and wallet payments. View all endpoints →

Agents

​
Built for AI agents

Private inference, MCP tools, and wallet-funded workflows for messaging, coding, and onchain agents.

Agent apps

Connect Venice to WhatsApp, Telegram, Discord, and more through OpenClaw, Hermes, and NanoClaw.

See integrations →Coding agents

Use Claude Code, Cursor, and Codex CLI with Venice models for private coding workflows.

See integrations →MCP + Skills

Expose chat, image, video, audio, and embeddings as MCP tools or runtime skills.

See integrations →

Explore the AI Agents hub →

Models

A few of the most-used models on Venice. Use the ID as your model parameter.

Kimi K2.6Moonshot AI

Open-weights frontier reasoning. Strong long-context and tool use at a fraction of frontier prices.

256K context$0.85 / $4.66 per 1MPrivate
kimi-k2-6
Claude Opus 4.7Anthropic

Best-in-class for coding, planning, and long-horizon agents that need to stay coherent.

1M context$6.00 / $30.00 per 1MAnonymized
claude-opus-4-7
GPT-5.5OpenAI

Frontier general intelligence with 1M context. Strong default for chat, RAG, and multi-step reasoning.

1M context$6.25 / $37.50 per 1MAnonymized
openai-gpt-55
250+ modelsText, image, audio, and videoBrowse the catalog →

Tools

​
Built‑in tools for chat models

Turn on web search, attach files, or query a blockchain with venice_parameters or a Venice-native endpoint.

Web Search

Web Scraping

File Inputs

Crypto RPC

Add real-time web search with citations to any text model via enable_web_search.
curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org-glm-5-1",
    "messages": [{"role": "user", "content": "What are the latest developments in AI?"}],
    "venice_parameters": {
      "enable_web_search": "auto"
    }
  }'
Set enable_web_scraping: true and the model will fetch and read any URLs in the user message before answering.
curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai-gpt-55",
    "messages": [
      {"role": "user", "content": "Summarize this post in five bullets: https://venice.ai/blog/how-to-use-venice-api"}
    ],
    "venice_parameters": {
      "enable_web_scraping": true
    }
  }'
Attach PDFs, Office docs, code, and text files (up to 25MB) directly to a chat request. See the File Inputs guide for the full format list.
# Encode a local file as a base64 data URL, then send it inline
FILE_B64=$(base64 q3-report.pdf | tr -d '\n')

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"model\": \"openai-gpt-55\",
    \"messages\": [
      {
        \"role\": \"user\",
        \"content\": [
          {\"type\": \"text\", \"text\": \"Summarize this report in five bullets and list the main risks.\"},
          {\"type\": \"file\", \"file\": {\"filename\": \"q3-report.pdf\", \"file_data\": \"data:application/pdf;base64,${FILE_B64}\"}}
        ]
      }
    ]
  }"
Proxy JSON-RPC 2.0 calls across 11 supported chains with your Venice key or an x402 wallet. See the Crypto RPC reference for chains, methods, and credit tiers.
curl https://api.venice.ai/api/v1/crypto/rpc/ethereum-mainnet \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "eth_blockNumber",
    "params": [],
    "id": 1
  }'

Pricing

​
Top up, stake, or pay per request

Fund an account with credits, stake DIEM for a daily allowance, or skip the account entirely with USDC on Base.

CreditsUSD or Crypto

Pay as you go in USD or crypto. Credits never expire and work across every endpoint.

Buy Credits
DIEMDaily allowance

Stake DIEM or VVV once and earn a fixed inference allowance every day, with no per-call charges.

Learn about DIEM
x402USDC on Base

Pay per request from any Base wallet in USDC. No account or API key, built for agents.

Read x402 Guide
Questions or feedback? Join us on Discord.