google

Google: Gemini 2.5 Pro

google/gemini-2.5-pro

A Gemini candidate for text reasoning and longer document analysis. Evaluate whether its answers improve the task outcome enough to justify the observed latency and cost in your application.

text

Try in Playground ↗

Input / 1M tokens$1.25

Output / 1M tokens$10

Context window1,048,576

Maximum output65,536

Provider-supported parameters

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

include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_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: cmub815o8020ajn0zs5jri4qh:2

Provider pricing fields · USD per indicated unit

{
  "prompt": "0.00000125",
  "completion": "0.00001",
  "audio": "0.00000125",
  "image": "0.00000125",
  "overrides": [
    {
      "audio": "0.0000025",
      "prompt": "0.0000025",
      "completion": "0.000015",
      "input_cache_read": "0.00000025",
      "input_audio_cache": "0.00000025",
      "min_prompt_tokens": 200000
    }
  ],
  "web_search": "0.014",
  "input_cache_read": "0.000000125",
  "input_audio_cache": "0.000000125",
  "input_cache_write": "0.000000375",
  "internal_reasoning": "0.00001"
}

JEVROUTER INTEGRATION NOTES · REVIEWED 2026-09-22

What to check in your application

Check long-context price overrides in the provider pricing fields before extrapolating a base-rate estimate.
Keep enough output budget for reasoning and the final answer; a small maximum can produce a truncated or empty answer.

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": "google/gemini-2.5-pro",
  "messages": [
    {
      "role": "user",
      "content": "Review this proposal: cache account balances for one hour and use the cache to authorize spending. Explain two failure scenarios and a safer design."
    }
  ],
  "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.

Google: Gemini 2.5 Flash 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.