anthropic

Anthropic: Claude Sonnet 4

anthropic/claude-sonnet-4

A Claude candidate for testing code changes, review and text reasoning through an OpenAI-compatible request shape. Model selection is fixed when you send this ID.

text

Try in Playground ↗

Input / 1M tokens$3

Output / 1M tokens$15

Context window200,000

Maximum output64,000

Provider-supported parameters

These are upstream capabilities. Jevrouter supports the subset described in the API contract; chat input is currently text only.

include_reasoningmax_tokensreasoningstoptemperaturetool_choicetoolstop_ktop_pstreamdeveloper_role

Capabilities are imported from OpenRouter’s catalog. This does not mean every model has been independently tested by Jevrouter.

Catalog updated: 2026-09-22T08:51:50.371Z · Price version: cmubxr2o807wpjn0z3w3uv2l9:4

Provider pricing fields · USD per indicated unit

{
  "prompt": "0.000003",
  "completion": "0.000015",
  "overrides": [
    {
      "prompt": "0.000006",
      "completion": "0.0000225",
      "input_cache_read": "0.0000006",
      "input_cache_write": "0.0000075",
      "min_prompt_tokens": 200000,
      "input_cache_write_1h": "0.000012"
    }
  ],
  "web_search": "0.01",
  "input_cache_read": "0.0000003",
  "input_cache_write": "0.00000375",
  "input_cache_write_1h": "0.000006"
}

JEVROUTER INTEGRATION NOTES · REVIEWED 2026-09-22

What to check in your application

Use the tool schema supported by Jevrouter, not provider-specific request fields copied from another SDK.
Do not assume that long conversation state can move between model families without changing behavior.

Start with the example below, then test representative inputs against your own acceptance criteria.

Make a request

curl --no-buffer https://api.jevrouter.io/v1/chat/completions \
  -H "Authorization: Bearer $JEVROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d @- <<'JSON'
{
  "model": "anthropic/claude-sonnet-4",
  "messages": [
    {
      "role": "user",
      "content": "A cache key includes user ID but omits project ID. Explain the isolation bug and propose a regression test."
    }
  ],
  "max_tokens": 1024
}
JSON

Plan your integration

Connect with the OpenAI Python SDK →Estimate this model’s cost →Budgets, request status and safe retries →

Related models to evaluate

Use identical inputs and scoring rules. No ranking is implied by this selection.

Anthropic: Claude Haiku 4.5 OpenAI: GPT-4.1

Source: OpenRouter model catalog. Imported descriptions and capabilities are provider declarations, not independent benchmark results. Jevrouter currently uses OpenRouter as its managed upstream.