gemini-2-0-flash-thinking
Developer: Google
Also known as
Gemini 2.0 Flash Thinking by Google is available through 17 API providers on LMSpeed. Compare API pricing from $0.150 to $75.00 per million input tokens across providers. In speed benchmarks, the fastest provider reaches 231 tok/s.
Compare Gemini 2.0 Flash Thinking API pricing across 17 providers. Input prices range from $0.150 to $75.00 per million input. 钱多多 API offers the lowest rate at $0.150/M.
| Provider | Model Variant | Input ($/M) | Output ($/M) | Speed (t/s) |
|---|---|---|---|---|
| 钱多多 API | gemini-2.0-flash-thinking-exp | $0.150 | $0.600 | — |
| 钱多多 API | gemini-2.0-flash-thinking-exp-01-21 | $0.150 | $0.600 | — |
| 钱多多 API | gemini-2.0-flash-thinking-exp-1219 | $0.150 | $0.600 | — |
 IXIOCCAPI | Gemini-2.0-Flash-Thinking | $0.200 | $0.800 | — |
| IXIOCCAPI | gemini-2.0-flash-thinking-exp | $0.200 | $0.800 | — |
| IXIOCCAPI | gemini-2.0-flash-thinking-exp-01-21 | $0.200 | $0.800 | — |
| IXIOCCAPI | gemini-2.0-flash-thinking-exp-1219 | $0.200 | $0.800 | — |
 天絮 API | gemini-2.0-flash-thinking-exp | $1.40 | $5.60 | — |
 SanShui API | gemini-2.0-flash-thinking-exp-01-21 | $2.00 | $8.00 | — |
| AIGCBAR | gemini-2.0-flash-thinking-exp-01-21 | $3.60 | $14.40 | — |
| SanShui API | gemini-2.0-flash-thinking-exp | $75.00 | $300.00 | — |
 AIO通用智能服务平台 | gemini-2.0-flash-thinking-exp | $75.00 | $300.00 | — |
| AIO通用智能服务平台 | gemini-2.0-flash-thinking-exp-01-21 | $75.00 | $300.00 | 121.9 t/s |
| AIO通用智能服务平台 | gemini-2.0-flash-thinking-exp-1219 | $75.00 | $300.00 | — |
| 天絮 API | gemini-2.0-flash-thinking-exp-01-21 | $75.00 | $300.00 | — |
| 天絮 API | gemini-2.0-flash-thinking-exp-1219 | $75.00 | $300.00 | — |
| IXIOCCAPI | gemini-2.0-flash-thinking | $75.00 | $300.00 | — |
Pricing data from provider public APIs
Compare speed and latency performance across all API providers.
Showing 1-4 of 4 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
 ai.api.xn--fiqs8sgemini-2.0-flash-thinking-exp-01-21 | 230.82 tok/s | 7.47s | 5 |
 ZetaTechs APIgemini-2.0-flash-thinking-exp | 224.26 tok/s | 7.53s | 5 |
 gemini-2.0-flash-thinking-exp-01-21 | 124.47 tok/s | 2.12s | 5 |
 gemini-2.0-flash-thinking-exp-01-21 | 121.89 tok/s | 1.38s | 5 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 02/25/2025, 10:31 | gemini-2.0-flash-thinking-exp-01-21 | 135.37 tok/s | 3.18s |
| 02/25/2025, 10:31 | gemini-2.0-flash-thinking-exp-01-21 | 125.78 tok/s | 1.70s |
| 02/25/2025, 10:31 | gemini-2.0-flash-thinking-exp-01-21 | 142.35 tok/s | 1.95s |
| 02/25/2025, 10:31 | gemini-2.0-flash-thinking-exp-01-21 | 65.08 tok/s | 2.31s |
| 02/25/2025, 10:31 | gemini-2.0-flash-thinking-exp-01-21 | 153.79 tok/s | 1.45s |
| 02/19/2025, 02:50 | gemini-2.0-flash-thinking-exp | 228.96 tok/s | 6.40s |
| 02/19/2025, 02:50 | gemini-2.0-flash-thinking-exp | 188.25 tok/s | 9.03s |
| 02/19/2025, 02:50 | gemini-2.0-flash-thinking-exp | 217.80 tok/s | 8.35s |
| 02/19/2025, 02:50 | gemini-2.0-flash-thinking-exp | 254.06 tok/s | 7.69s |
| 02/19/2025, 02:50 | gemini-2.0-flash-thinking-exp | 232.25 tok/s | 6.16s |
| 02/19/2025, 02:48 | gemini-2.0-flash-thinking-exp-01-21 | 109.19 tok/s | 1.61s |
| 02/19/2025, 02:48 | gemini-2.0-flash-thinking-exp-01-21 | 109.25 tok/s | 1.34s |
| 02/19/2025, 02:48 | gemini-2.0-flash-thinking-exp-01-21 | 126.37 tok/s | 1.35s |
| 02/19/2025, 02:48 | gemini-2.0-flash-thinking-exp-01-21 | 138.95 tok/s | 1.62s |
| 02/19/2025, 02:48 | gemini-2.0-flash-thinking-exp-01-21 | 125.71 tok/s | 0.96s |
| 02/09/2025, 04:13 | gemini-2.0-flash-thinking-exp-01-21 | 245.62 tok/s | 8.26s |
| 02/09/2025, 04:13 | gemini-2.0-flash-thinking-exp-01-21 | 195.73 tok/s | 8.08s |
| 02/09/2025, 04:13 | gemini-2.0-flash-thinking-exp-01-21 | 199.97 tok/s | 8.11s |
| 02/09/2025, 04:13 | gemini-2.0-flash-thinking-exp-01-21 | 283.17 tok/s | 6.98s |
| 02/09/2025, 04:13 | gemini-2.0-flash-thinking-exp-01-21 | 229.59 tok/s | 5.93s |
