Gemini 2.5 Pro Preview 06-05
Provider: Google AI US Official API price
Input price
$0.63
/ 1M tokens
Output price
$5.00
/ 1M tokens
Cache price
$0.063
/ 1M tokens (read)
Context
1.05M tokens
Max output 66K tokens
Overview
Google's reasoning flagship built for advanced coding, math, and scientific workloads, featuring a 1M-token context window.
Strengths
- 1,048,576 token context window
- Native support for vision, audio, and thinking
- 65,536 max output tokens
- Cached input drops to $0.0625 per million
Best use cases
- Long-document analysis and scientific research
- Complex multi-step coding and math
- Multimodal processing with audio and images
Pricing position
Priced identically to GPT-5.1 at $0.625 input and $5.00 output per million tokens, though output costs more than double GLM 4.7.
Caveats
Higher output cost than GLM 4.7 and Kimi K2 Thinking for standard text generation tasks.
Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.
Key facts
- Price basis
- Official API price
- Max output
- 66K tokens
- Knowledge cutoff
- 2025-01-31
- Listed on OpenRouter
- 2025-06-05
- Tracked since
- 2026-05-08
- Last updated
- 2026-11-10
Features
Image inputAudioFunction callingJSON outputReasoning
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.31 |
| 1M (small app) | 1 | 0.5 | $3.13 |
| 10M (mid scale) | 10 | 5 | $31.25 |
| 100M (large) | 100 | 50 | $312.50 |
※ Cache and batch discounts not factored in. Detailed calculator
Official resources
Other models from Google AI
Similar-priced models
Source: OpenRouter API (google/gemini-2.5-pro-preview)