Choose a model to open its comparison page.
Gemini 2.5 Pro benchmark, API pricing, and provider data cover 555 API providers, with prices starting at $0.0014/request. Gemini 2.5 Pro free API options are available from 19 providers. The page also shows measured API speed and first-token latency.
Google Gemini 2.5 Pro is Google advanced multimodal model with a 1M-token context window, strong STEM reasoning, and native support for images, audio, and video understanding.
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
Input and output token limits for this model, plus how it ranks on long-context understanding.
1 metric
2 metrics
2 metrics
6 metrics · Estimated
8 metrics · Rated
6 metrics · Rated
6 metrics · Provisional
5 metrics · Estimated
1 metric · Provisional
3 metrics · Provisional
2 metrics · Provisional
Third-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Google google-vertex/global/flex | $0.625/M | $5/M | 98.6% | — | — | 1.0M tokens / 65.5K tokens |
Google google-vertex/global | $1.25/M | $10/M | 98.6% | — | — | 1.0M tokens / 65.5K tokens |
Google google-vertex/global/priority | $2.25/M | $18/M | 98.6% | — | — | 1.0M tokens / 65.5K tokens |
Google AI Studio google-ai-studio/flex | $0.625/M | $5/M | 98.0% | — | — | 1.0M tokens / 65.5K tokens |
Google AI Studio google-ai-studio | $1.25/M | $10/M | 98.0% | — | — | 1.0M tokens / 65.5K tokens |
Google AI Studio google-ai-studio/priority | $2.25/M | $18/M | 98.0% | — | — | 1.0M tokens / 65.5K tokens |
Google google-vertex/eu | $1.25/M | $10/M | 94.9% | — | — | 1.0M tokens / 65.5K tokens |
Google google-vertex/us | $1.25/M | $10/M | 22.2% | — | — | 1.0M tokens / 65.5K tokens |
Compare Gemini 2.5 Pro API pricing across 536 providers. Prices range from $0.0014/request to $1095.00/M. 云AI offers the lowest rate at $0.0014/request. 19 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | gemini-2.5-pro | gemini-cli | -86%$0.171/M | -86%$1.37/M | 105.5 t/s | 16.40 s-23% | — | |
L1 79% | gemini-2.5-pro | default | -91%$0.107/M | -91%$0.857/M | 80.6 t/s | 21.18 s-1% | — | |
L1 100% | gemini-2.5-pro | gemini_cli | -50%$0.625/M | -50%$5.00/M | — | — | — | |
L1 100% | gemini-2.5-pro-search | gemini_cli | -50%$0.625/M | -50%$5.00/M | — | — | — | |
L1 100% | gemini-2.5-pro | gemini-slb | -57%$0.536/M | -57%$4.29/M | — | — | — | |
L1 100% | gemini-2.5-pro | gemini-cli | -93%$0.086/M | -93%$0.685/M | — | — | — | |
L1 100% | gemini-2.5-pro | 官转逆向 | -92%$0.103/M Cache read$0.010/M | -92%$0.822/M | — | — | — | |
L1 100% | gemini-2.5-pro-c | gemini-anti | $0.0055/request | - | — | — | — | |
L1 100% | gemini-2.5-pro | gemini-anti | -86%$0.171/M Cache read$0.043/MCache write$0.214/MCache write 1h$0.342/M | -86%$1.37/M | — | — | — | |
L1 100% | gemini-2.5-pro-nothinking | gemini-号池 | -59%$0.514/M | -59%$4.11/M | — | — | — | |
L1 100% | gemini-2.5-pro-c | default | $0.100/request | - | — | — | — | |
L1 100% | gemini-2.5-pro-nothinking | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gemini-2.5-pro | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gemini-2.5-pro | Chat | -93%$0.086/M Cache read$0.0086/M | -93%$0.685/M | — | — | — | |
L1 100% | gemini-2.5-pro | gemini-cli | -87%$0.159/M | -87%$1.27/M | — | — | — | |
L1 100% | gemini-2.5-pro | default | $1.25/M | $10.00/M | — | — | — | |
L1 100% | gemini-2.5-pro-preview-06-05 | default | $1.63/M | $13.00/M | — | — | — | |
L1 100% | gemini-2.5-pro | default | $1.63/M | $13.00/M | — | — | — | |
L1 100% | gemini-2.5-pro-preview-03-25 | default | $1.63/M | $13.00/M | — | — | — | |
L1 100% | gemini-2.5-pro-preview-05-06 | default | $1.63/M | $13.00/M | — | — | — |
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.Standard benchmark data may include BenchLM and other public sources.
