Gemini 2.5 Pro Preview 06-05
- Context
- 1.0M
- Released
- 1y ago
- Input / 1M tokens
- $1.25
- Output / 1M tokens
- $10.00
- Cached input / 1M tokens
- $0.13
- Cache write / 1M tokens
- $0.38
Sources:OpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
Other published benchmarks
| Evaluation | Reported score and source |
|---|---|
| ARC-AGI-2 | 0.0% Third-party evaluator · gemini-2.5-pro-preview-06-05_1K Thinking budget: 1K External evaluation via Epoch AIOriginal-source terms apply |
| FrontierMath-2025-02-28-Private | |
| FrontierMath-Tier-4-2025-07-01-Private | |
| GPQA diamond |
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.
Specifications
- Developer
- Google DeepMind
- Model family
- Gemini
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- June 5, 2025
- Model ID
google/gemini-2.5-pro-preview- Openness
- Closed
- License
- —
- Input modalities
- file, image, text, audio
- Output modalities
- text
- Modality
- text+image+file+audio->text
- Tokenizer
- Gemini
- Max output tokens
- 66K
- Knowledge cutoff
- 2025-01-31
- Hugging Face
- —
- Source freshness
- Endpoints synced Oct 15, 2026, 2:13 PM UTC
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| google-ai-studio/flex | 1.0M | $0.63 | $5.00 | $0.06 | $0.19 | 97.22% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/global | 1.0M | $1.25 | $10.00 | $0.13 | $0.38 | 97.92% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/eu | 1.0M | $1.25 | $10.00 | $0.13 | $0.38 | 46.32% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/us | 1.0M | $1.25 | $10.00 | $0.13 | $0.38 | 94.20% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-ai-studio | 1.0M | $1.25 | $10.00 | $0.13 | $0.38 | 99.23% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/global/priority | 1.0M | $2.25 | $18.00 | $0.22 | $0.68 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-ai-studio/priority | 1.0M | $2.25 | $18.00 | $0.22 | $0.68 | — | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Text provenance
Gemini app/webGoogle SynthID text watermarking
Google DeepMind says text generated in the Gemini app and web experience is watermarked with SynthID by adjusting token probabilities.
Official explanation