Google model on Crazyrouter

Use the Gemini 2.5 Flash API with one key and pay-as-you-go pricing

Gemini 2.5 Flash is available on Crazyrouter through the OpenAI-compatible endpoint and the native Gemini protocol. Switch models without changing your integration, and see every request in one billing view.

Gemini nativeLong contextMultimodalFast
Get API KeyView live pricing
Model ID
gemini-2.5-flash
Provider
Google
Endpoint
/v1/chat/completions
Task
chat
Context window
1M tokens
Input modalities
Text, image, audio, video
Output modalities
Text
Release date
2025-04-17

What is Gemini 2.5 Flash?

Gemini 2.5 Flash is a Gemini 2.5 model from Google for chat, reasoning, coding and agent workflows. It was released on 2025-04-17. On Crazyrouter it runs behind the same API key and billing account as 300+ other models, so you can benchmark it against alternatives and route traffic without new credentials.

Drop-in OpenAI compatibility

Works with the OpenAI SDKs, LangChain, Cursor, Cline and any tool that accepts a custom base URL.

Streaming and tool use

Server-sent events, function calling and JSON output behave the way the upstream model documents them.

Live, discounted pricing

Rates on this page come straight from the billing table and already include the Crazyrouter discount.

One account for every model

Compare against Claude, GPT, Gemini, DeepSeek and more without juggling vendor accounts.

Gemini 2.5 Flash API quickstart

Point your OpenAI SDK at https://crazyrouter.com/v1 and set the model to gemini-2.5-flash. If your client speaks Gemini natively, use the second example instead.

cURL
curl https://crazyrouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $CRAZYROUTER_API_KEY" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [{"role": "user", "content": "Explain the tradeoffs of this architecture decision."}],
    "stream": true
  }'
Show OpenAI-compatible migration example
cURL
curl "https://crazyrouter.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $CRAZYROUTER_API_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "Explain the tradeoffs of this architecture decision."}]}]
  }'

Best use cases

Coding assistants and agent loops with tool calls
Long-document analysis, summarisation and extraction
Customer-facing chat with streaming responses
Evaluation and A/B tests across model vendors
Batch classification, tagging and structured extraction
Technical writing, design docs and code review

Works with developer tools

OpenAI SDKs

Set base_url to https://crazyrouter.com/v1 and model to gemini-2.5-flash.

Cursor, Cline, Continue

Add Crazyrouter as a custom OpenAI-compatible provider and pick the model from the list.

LangChain / LlamaIndex

Use the OpenAI chat model class with the Crazyrouter base URL.

Claude Code / Codex CLI

Follow the Crazyrouter deployment guides to point either CLI at your key.

Gemini 2.5 Flash FAQ

What base URL do I use for Gemini 2.5 Flash?

https://crazyrouter.com/v1. Chat completions go to /v1/chat/completions; native Gemini requests use their usual path.

How is usage billed?

Per token, at the input/output rates shown on this page. Your balance is debited per request; there is no subscription.

Does it support streaming and function calling?

Yes. Set stream: true and pass tools as you would with the upstream API. Behaviour follows the upstream model.

Can I switch to another model later?

Change the model string. The same key works for every model in the Crazyrouter catalogue.

Where do I see the current price?

The pricing page lists live rates for every model, including group discounts if you are logged in.