google

Google: Gemini 2.5 Flash Lite

google/gemini-2.5-flash-lite

A starting point for testing short text transformations in the Gemini 2.5 family. Jevrouter's Balanced routing pool includes this model for everyday tasks; that inclusion is not a guarantee for a new workload.

text

Try in Playground ↗

Input / 1M tokens$0.1

Output / 1M tokens$0.4

Context window1,048,576

Maximum output65,535

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: 2026-11-11T20:54:46.466Z · Price version: cmvv9vd9o1ofcid10xijjwlqj:6

Provider pricing fields · USD per indicated unit

{
  "prompt": "0.0000001",
  "completion": "0.0000004",
  "audio": "0.0000003",
  "image": "0.0000001",
  "web_search": "0.014",
  "input_cache_read": "0.00000001",
  "input_audio_cache": "0.00000003",
  "input_cache_write": "0.0000000833333333333333",
  "internal_reasoning": "0.0000004"
}

JEVROUTER INTEGRATION NOTES · REVIEWED 2026-09-22

What to check in your application

Use a labeled extraction set to check exact output, missing fields and unexpected prose.
Compare the total cost of fixed-model calls with automatic routing; classification overhead can dominate very short requests.

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-flash-lite",
  "messages": [
    {
      "role": "user",
      "content": "Extract the order code from: Please check order AB-204. Return only the code."
    }
  ],
  "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 Nano

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