gemini-2-5-pro-thinking
Developer: Google
Also known as
Gemini 2.5 Pro Thinking by Google is available through 56 API providers on LMSpeed. Compare API pricing from $0.375 to $75.00 per million input tokens across providers. In speed benchmarks, the fastest provider reaches 106 tok/s.
Compare Gemini 2.5 Pro Thinking API pricing across 56 providers. Input prices range from $0.375 to $75.00 per million input. SWT-API offers the lowest rate at $0.375/M.
| Provider | Model Variant | Input ($/M) | Output ($/M) | Speed (t/s) |
|---|---|---|---|---|
| SWT-API | gemini-2.5-pro-thinking | $0.375 | $3.00 | — |
| Nova AI | gemini-2.5-pro-thinking | $0.375 | $3.00 | — |
| Nova AI | gemini-2.5-pro-thinking-* | $0.375 | $3.00 | — |
| 蜜音AI | gemini-2.5-pro-thinking | $0.375 | $3.00 | — |
| 人人 API | gemini-2.5-pro-preview-03-25-thinking | $0.500 | $4.00 | — |
| 人人 API | gemini-2.5-pro-preview-05-06-thinking | $0.500 | $4.00 | — |
| 人人 API | gemini-2.5-pro-thinking | $0.500 | $4.00 | — |
 ModelPool | gemini-2.5-pro-thinking | $1.20 | $9.60 | — |
| AAAI | gemini-2.5-pro-thinking | $1.25 | $10.00 | — |
| AAAI | gemini-2.5-pro-thinking-* | $1.25 | $10.00 | — |
 柏拉图AI | gemini-2.5-pro-thinking-* | $1.25 | $10.00 | — |
| 柏拉图AI | gemini-2.5-pro-thinking-128 | $1.25 | $10.00 | — |
| 柏拉图AI | gemini-2.5-pro-thinking-512 | $1.25 | $10.00 | — |
 UnifyLLM | gemini-2.5-pro-thinking | $1.25 | $10.00 | — |
 V-API | gemini-2.5-pro-thinking | $1.25 | $10.00 | — |
| V-API | gemini-2.5-pro-thinking-* | $1.25 | $10.00 | — |
 毫秒API | gemini-2.5-pro-thinking-* | $1.25 | $10.00 | — |
| 毫秒API | gemini-2.5-pro-thinking-128 | $1.25 | $10.00 | — |
| 毫秒API | gemini-2.5-pro-thinking-512 | $1.25 | $10.00 | — |
| gemini-2.5-pro-thinking-* | $1.25 | $10.00 | — |
Pricing data from provider public APIs
Compare speed and latency performance across all API providers.
Showing 1-1 of 1 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
 YUNWU APIgemini-2.5-pro-thinking | 105.66 tok/s | 9.62s | 10 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 12/26/2025, 19:02 | gemini-2.5-pro-thinking | 108.95 tok/s | 15.38s |
| 12/26/2025, 19:02 | gemini-2.5-pro-thinking | 94.90 tok/s | 15.50s |
| 12/26/2025, 19:02 | gemini-2.5-pro-thinking | 113.87 tok/s | 15.28s |
| 12/26/2025, 19:02 | gemini-2.5-pro-thinking | 126.50 tok/s | 16.18s |
| 12/26/2025, 19:02 | gemini-2.5-pro-thinking | 132.85 tok/s | 13.40s |
| 08/06/2025, 15:41 | gemini-2.5-pro-thinking | 115.80 tok/s | 3.91s |
| 08/06/2025, 15:41 | gemini-2.5-pro-thinking | 90.66 tok/s | 3.88s |
| 08/06/2025, 15:41 | gemini-2.5-pro-thinking | 95.58 tok/s | 3.52s |
| 08/06/2025, 15:41 | gemini-2.5-pro-thinking | 57.29 tok/s | 6.85s |
| 08/06/2025, 15:41 | gemini-2.5-pro-thinking | 120.15 tok/s | 2.32s |
