openai

OpenAI: GPT-5 Mini

openai/gpt-5-mini

A GPT-5 family reasoning candidate that can be accessed through the text chat contract. Test it with the default provider behavior before assuming all familiar sampling parameters are supported.

text

Try in Playground ↗

Input / 1M tokens$0.25

Output / 1M tokens$2

Context window400,000

Maximum output128,000

Provider-supported parameters

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

include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsstreamdeveloper_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: cmubxr2ft07uqjn0zzgvyydv9:3

Provider pricing fields · USD per indicated unit

{
  "prompt": "0.00000025",
  "completion": "0.000002",
  "web_search": "0.01",
  "input_cache_read": "0.000000025"
}

JEVROUTER INTEGRATION NOTES · REVIEWED 2026-09-22

What to check in your application

Check the current supported-parameter list before sending temperature or top_p.
Allow room for reasoning in max_tokens and inspect finish_reason when final content is missing.

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": "openai/gpt-5-mini",
  "messages": [
    {
      "role": "user",
      "content": "A job retries after a network timeout, but the first payment may have succeeded. Describe an idempotent recovery procedure in four steps."
    }
  ],
  "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.

OpenAI: GPT-4.1 Mini OpenAI: GPT-5

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