gemini-2-5-flash
Developer: Google
Also known as
Gemini 2.5 Flash by Google is available through 160 API providers on LMSpeed. Compare API pricing from $0.0006 to $75.00 per million input tokens across providers. In speed benchmarks, the fastest provider reaches 225 tok/s.
Compare Gemini 2.5 Flash API pricing across 160 providers. Input prices range from $0.0006 to $75.00 per million input. 91VIP offers the lowest rate at $0.0006/M.
| Provider | Model Variant | Input ($/M) | Output ($/M) | Speed (t/s) |
|---|---|---|---|---|
| 91VIP | gemini-2.5-flash | $0.0006 | $0.0015 | — |
| Futureppo | gemini-2.5-flash | $0.0006 | $0.0015 | — |
 X666 API | gemini-2.5-flash | $0.0010 | $0.0010 | — |
| SWT-API | gemini-2.5-flash | $0.0015 | $0.013 | — |
| gemini-2.5-flash | $0.0050 | $0.0050 | — | |
| gemini-2.5-flash-maxthinking | $0.0050 | $0.0050 | — | |
| 素墨API | gemini-2.5-flash | $0.010 | $0.010 | 136.0 t/s |
| 素墨API | gemini-2.5-flash-maxthinking | $0.010 | $0.010 | — |
| 素墨API | gemini-2.5-flash-nothinking | $0.010 | $0.010 | — |
| CookingAI | gemini-2.5-flash-preview-09-2025 | $0.010 | $0.010 | — |
| 紫脑喵 | gemini-2.5-flash-preview-09-2025 | $0.010 | $0.010 | — |
 Meta API | gemini-2.5-flash | $0.015 | $0.015 | — |
| Meta API | gemini-2.5-flash-preview-05-20 | $0.015 | $0.015 | — |
| Meta API | gemini-2.5-flash-preview-09-2025 | $0.015 | $0.015 | — |
 123NHH API | gemini-2.5-flash | $0.030 | $0.250 | — |
 GLM BigModel Relay | gemini-2.5-flash | $0.030 | $0.250 | — |
| uglycat | gemini-2.5-flash | $0.030 | $0.030 | — |
| 碳硅生命体 | gemini-2.5-flash | $0.036 | $0.300 | — |
 SanShui API | gemini-2.5-flash | $0.075 | $0.300 | — |
 天絮 API | gemini-2.5-flash | $0.075 | $0.300 | — |
Pricing data from provider public APIs
Compare speed and latency performance across all API providers.
Showing 1-12 of 12 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
Lido LLM gcli/gemini-2.5-flash | 225.13 tok/s | 8.61s | 5 |
 N1Ngemini-2.5-flash | 200.10 tok/s | 8.21s | 5 |
models/gemini-2.5-flash | 192.40 tok/s | 8.02s | 25 |
gemini-2.5-flash | 185.65 tok/s | 10.41s | 5 |
models/gemini-2.5-flash-preview-09-2025 | 175.68 tok/s | 0.57s | 5 |
 gemini-2.5-flash | 158.01 tok/s | 9.77s | 10 |
gemini-2.5-flash | 157.11 tok/s | 9.19s | 150 |
 google/gemini-2.5-flash-preview | 140.85 tok/s | 2.05s | 10 |
gemini-2.5-flash-nothinking | 138.51 tok/s | 4.00s | 25 |
gemini-2.5-flash | 136.00 tok/s | 11.32s | 5 |
gemini-2.5-flash | 54.24 tok/s | 10.36s | 10 |
gemini-2.5-flash | 34.41 tok/s | 17.36s | 5 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 02/28/2026, 04:30 | gemini-2.5-flash | 241.24 tok/s | 9.10s |
| 02/28/2026, 04:30 | gemini-2.5-flash | 145.00 tok/s | 13.43s |
| 02/28/2026, 04:30 | gemini-2.5-flash | 166.74 tok/s | 12.55s |
| 02/28/2026, 04:30 | gemini-2.5-flash | 159.97 tok/s | 9.33s |
| 02/28/2026, 04:30 | gemini-2.5-flash | 215.30 tok/s | 7.65s |
| 02/25/2026, 03:40 | gemini-2.5-flash | 151.86 tok/s | 9.32s |
| 02/25/2026, 03:40 | gemini-2.5-flash | 123.16 tok/s | 11.80s |
| 02/25/2026, 03:40 | gemini-2.5-flash | 164.90 tok/s | 8.55s |
| 02/25/2026, 03:40 | gemini-2.5-flash | 176.81 tok/s | 10.23s |
| 02/25/2026, 03:40 | gemini-2.5-flash | 233.58 tok/s | 6.80s |
| 02/25/2026, 03:38 | gemini-2.5-flash | 177.70 tok/s | 9.02s |
| 02/25/2026, 03:38 | gemini-2.5-flash | 130.82 tok/s | 12.67s |
| 02/25/2026, 03:38 | gemini-2.5-flash | 164.78 tok/s | 11.05s |
| 02/25/2026, 03:38 | gemini-2.5-flash | 37.83 tok/s | 10.10s |
| 02/25/2026, 03:38 | gemini-2.5-flash | 218.65 tok/s | 8.13s |
| 02/08/2026, 07:01 | gemini-2.5-flash | 142.77 tok/s | 10.95s |
| 02/08/2026, 07:01 | gemini-2.5-flash | 145.64 tok/s | 11.98s |
| 02/08/2026, 07:01 | gemini-2.5-flash | 171.01 tok/s | 11.07s |
| 02/08/2026, 07:01 | gemini-2.5-flash | 32.90 tok/s | 11.58s |
| 02/08/2026, 07:01 | gemini-2.5-flash | 187.67 tok/s | 11.04s |
