Google: Gemini 2.5 Pro, Google — route, pricing & source

Google's state-of-the-art Gemini thinking model for complex code, math, STEM, large datasets, and long context.

Gemini APIhighLast checked: May 13, 2026
Input
$1.25 / 1M
/ 1M tokens
Output
$10.00 / 1M
/ 1M tokens
Cached input
$0.1250 / 1M
/ 1M tokens
Cache write
Not available
Not available

Context and limits

Context window
1.0M
Max output
65,536
Input modalities
text, image, video, audio, pdf
Output modalities
text
Weight access
Closed
Availability
Official API
Capability flags
VisionToolsJSONReasoningAudioLong context

From source metadata + verification fields — confirm provider docs before production.

Benchmarks

Access and license

Official API
Yes
Open weights
No
Self-hostable
No
License
Closed · API onlyNo public weights: use through a vendor’s cloud API or product. “Proprietary” means the creator does not distribute the trained model weights for self-hosting.
Open license

Example costs

Scenario: 1K input + 300 output tokens / request

10,000 requests
$42.50
100,000 requests
$425.00
1,000,000 requests
$4,250.00

Cheaper alternatives

Lower-cost models for the same scenario

inclusionAI: Ling-2.6-flash
OpenRouter
$1.90
Mistral: Mistral Nemo
OpenRouter
$2.90
Meta: Llama 3.1 8B Instruct
OpenRouter
$3.50
IBM: Granite 4.0 Micro
OpenRouter
$5.06
Meta: Llama 3 8B Instruct
OpenRouter
$5.20

Source

Source
Google Gemini public model and pricing docs
Confidence
high
Route
Gemini API
Last checked
May 13, 2026
Source notes
  • Pricing varies above 200K prompt tokens; show tier note in UI before ranking high-context scenarios.
  • No independent benchmark score has been merged yet for this model.
  • Includes Hugging Face benchmark data only when the dataset is public, ungated, allowlisted, and matched by reviewed aliases.
Open source
Skip to main content