Claudech gives you a family of fast, capable language models behind a single API that speaks the two formats your tools already understand, with transparent per-token billing and no surprise invoices.
Requests that fail before the model produces output are never billed. If a model is temporarily unavailable, Claudech can transparently route to a fallback model of equal or greater capability; when it does, the response says so ().
Use the host that matches your client’s wire format (same API key for both):
| Format |
|---|
| Base URL |
|---|
| Used by |
|---|
| OpenAI Chat Completions |
| OpenAI SDK, Cursor, LangChain, curl to |
| Anthropic Messages |
| Anthropic SDK, Claude Code (), curl to |
Anthropic clients append themselves — do not set Claude Code to . Requests must use HTTPS; plain HTTP is rejected. Step-by-step tool setup: integrations.
| Model |
|---|
| Best for |
|---|
| Context |
|---|
| Reasoning |
|---|
| Everyday chat, coding and analysis |
| 256K |
| Yes |
| Complex multi-step work where quality matters most |
| 256K |
| Yes |
| Mathematics, research synthesis, hard debugging |
| 256K |
| Extended |
| High-volume classification, extraction and summaries |
| 128K |
| No |
Details, capabilities and current prices are on the Models page and are always available from .
The Playground lets you experiment with prompts and parameters, then copies out the equivalent curl, JavaScript or Python code.
POST /v1/chat/completionsPOST /v1/messagessk-fallback_usedhttps://api.claudech.com/v1/v1/chat/completionshttps://api.claudech.comANTHROPIC_BASE_URL/v1/messages/v1/messages/v1/chat/completionsclaude-sonnet-5claude-fable-5-1claude-opus-5claude-haiku-4-5GET /v1/modelsyour app ──▶ https://api.claudech.com/v1/chat/completions
│ 1. authenticate the API key and check plan limits
│ 2. reserve tokens from your balance
│ 3. route to the model (with automatic fallback if needed)
│ 4. stream the response back to you
└▶ 5. meter the real usage and settle the reservation