ONE GATEWAY · PAY FOR USAGE

One API.LeadingAI models.

Connect OpenAI, Claude, Gemini, and DeepSeek.
Choose a model, compare prices, and start building.

  • OpenAI-compatible
  • One Base URL
  • Pay as you go

API compatibility and model access depend on your selected group.

OpenAI, Anthropic, Google, and DeepSeek connected through TimRouter

Flagships from each provider

Selected flagship series in our current catalog. Choose by task and supported API.

Model availability follows your selected group. Catalog retrieved: 2026年11月8日 10:33。 Pricing details

FROM MODEL TO APPLICATION

A shorter path to building

One API key

Connect supported providers through one gateway. Check each model’s API format before use.

Read the setup guides

Find the right model

Browse text, image, media, and retrieval models with filters and model details.

Browse the marketplace

Usage-based pricing

Compare input, output, and per-request reference prices. Final billing follows your group.

How billing works

Build with your tools

Follow setup guides for Claude Code, Codex, Cursor, and SDKs.

Tool guides
START WITH A REQUEST

Your first call,
in familiar code.

Set your API key and Base URL, then choose an accessible model. Use the guide to check the response and troubleshoot errors.

  1. Create an API keyRegister in the console and check your group’s model access.
  2. Set the environment variableexport TIMROUTER_API_KEY="sk-…"
  3. Send the sample requestRun the sample request, then check the response.
Read the setup guide
curl https://api.timrouter.com/v1/chat/completions \
  -H "Authorization: Bearer $TIMROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Set TIMROUTER_API_KEY first. Model access and billing depend on your selected group.

Before you start

Find more API details in the documentation.

Explore the guides
First requestHow do I get started?

Register in the console, review available groups and prices, create an API key, and follow the first-request guide.

CompatibilityDo all models use the same API format?

No. OpenAI-compatible, Anthropic, image, and media APIs have different request formats. Each model detail page links to its supported endpoints and relevant guides.

BillingHow are prices calculated?

Token models have separate input and output prices. Other models may bill per request or by task parameters. Reference prices use the lowest publicly configured group; your selected group determines the actual charge.

AccountWhere can I manage my account?

Use the external console to manage keys, balances, billing, and request logs. The website provides model information and documentation.

Build with your next model.

Register for an API key, then follow the first-request guide to send your first call.