Gemini 2.5 Flash

by Googleewest/gemini-flash

Fast, low-cost model with optional reasoning.

LanguageChatStreamingReasoning
PlaygroundAPIPricingDetails
Illustration made with FLUX.1 schnell: streams of light flowing through a vast library

Try Gemini 2.5 Flash in your browser

Sign in to run this model in the playground. Usage is billed to your organisation.

Sign in to try it

API

OpenAI-compatible chat completions; works with the official OpenAI SDKs. Every response carries an x-request-id trace ID.

curl https://api.ewest.ai/v1/chat/completions \
  -H "Authorization: Bearer $EWEST_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "ewest/gemini-flash", "stream": true,
       "messages": [{"role": "user", "content": "Hello!"}]}'

Pricing

Input
$0.30 per million tokens
Output
$2.50 per million tokens

1,000 requests of 1,000 tokens in and 300 out cost about $1.05. Billed on the tokens the model actually reads and writes.

Details

Context window
1,048,576 tokens
API
OpenAI-compatible chat completions, streaming