google/gemini-2.5-pro

Million-token thinking model in wide production use.

TextImageAudioLong contextReasoningProgramminglong-contextreasoningtools

Specifications

Context window: 1.049M
Max output tokens: 65,536
Released: 2025-03
Infra providers: 5
Throughput: 112 tok/s
Latency (TTFB, sample): 590 ms
Capabilities: Supports tools

Pricing

per million tokens

Input

$1.25

Output

$10.00

Blended (3:1)

$3.44

Use this model

Works with any OpenAI SDK — same request shape, different model id.

curl https://api.lokarouter.id/v1/chat/completions \  -H "Authorization: Bearer sk-lkr-your-key" \  -H "Content-Type: application/json" \  -d '{    "model": "google/gemini-2.5-pro",    "messages": [{ "role": "user", "content": "Hello" }]  }'

Sample data for demonstration — connect your workspace for live stats.