Gemini 2.5 Pro

Featured Latest
Google Gemini 2.5 Generally Available May 2025

Google's most capable model — 1M token context, state-of-the-art reasoning with hybrid thinking, and top scores on AIME, GPQA, and long-context retrieval benchmarks.

Context
1M
tokens
Input
$1.25
per MTok
Output
$10.00
per MTok

About

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Modalities

Input
Text Vision Audio Video Documents / PDFs Code
Output
Text Code

Code Examples

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-pro",
    "messages": [
      { "role": "user", "content": "Explain quantum entanglement in one sentence." }
    ]
  }'

API Parameters

Name Type Description
include_reasoning boolean Include the model's internal reasoning trace in the response.
max_tokens deprecated integer Deprecated. Use max_completion_tokens.
reasoning object Configuration for extended-thinking / reasoning mode.
response_format one of Constrain output to a JSON schema or an enum (structured outputs).
seed integer Deterministic seed for sampling. Same seed + same prompt produces identical output.
stop array Up to 4 sequences where the API will stop generating tokens.
structured_outputs boolean Enable JSON-schema-constrained output.
temperature number Sampling temperature; higher values produce more random output. 0 is deterministic.
tool_choice one of Controls which (if any) tool is called: "none", "auto", "required", or a specific tool.
tools array List of tools (functions) the model may call.
top_p number Nucleus sampling: consider only tokens whose cumulative probability ≥ top_p.

Standard OpenAI-compatible parameters. Consult the provider docs for model-specific behaviour.

Benchmark Scores

Benchmark Score
MMLU 88.6%
GPQA Diamond 84%
MATH 92%

Performance

70
tok / sec
output speed

Source: Google AI docs + Artificial Analysis, April 2026

Strengths & Limitations

Best For
1M token context window
Hybrid thinking mode
Multimodal (text/vision/audio/video)
Top reasoning benchmarks
Free API tier available
Limitations
Higher output price vs competitors
No prompt caching on Gemini API
Thinking mode increases latency

Tags

ReasoningLong ContextThinkingVisionMultimodal