Скорость вывода
34140.3 tok/s
35133.4 tok/s
36Gemini 2.5 Pro132.3 tok/s
37129.4 tok/s
Gemini 2.5 Pro by Google is available through 301 API providers on LMSpeed. Compare API pricing from $0.0006 to $1000.00 per million input tokens across providers. Free API access is offered by 1 provider. Context window: 1,048,576. In speed benchmarks, the fastest provider reaches 159 tok/s.
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.
Также известна как
Compare Gemini 2.5 Pro API pricing across 300 providers. Input prices range from $0.0006 to $1000.00 per million input. SWT-API offers the lowest rate at $0.0006/M. 1 provider offers free API credits or a free tier.
| Провайдер | Вариант модели | Аудит | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен |
|---|---|---|---|---|---|---|
DeepRouter100% | gemini-2.5-pro | — | $1.25 | $10.00 | 91.9 t/s | 16.35 s-29% |
| gemini-2.5-pro-nothinking | — | $1.25 | $10.00 | — | — | |
ModelPool97.7% | gemini-2.5-pro | — | $0.107-91% | $0.857-91% | 80.6 t/s | 21.18 s-8% |
CatClaw API100% | gemini-2.5-pro | — | $0.050-96% | $0.050-99% | 47.4 t/s | 25.24 s |
柏拉图AI100% | gemini-2.5-pro | — | $0.171-86% | $1.37-86% | — | — |
| gemini-2.5-pro-nothinking | — | $0.171-86% | $1.37-86% | — | — | |
| gemini-2.5-pro-preview-03-25 | — | $0.171-86% | $1.37-86% | — | — | |
| gemini-2.5-pro-preview-05-06 | — | $0.171-86% | $1.37-86% | — | — | |
| gemini-2.5-pro-preview-06-05 | — | $0.171-86% | $1.37-86% | — | — | |
| gemini-2.5-pro-preview-06-05-nothinking | — | $0.171-86% | $1.37-86% | — | — | |
| gemini-2.5-pro-as | — | $10.27 | $82.19 | — | — | |
V-API100% | gemini-2.5-pro | — | $1.25 | $10.00 | — | — |
| gemini-2.5-pro-search | — | $1.25 | $10.00 | — | — | |
老张API100% | gemini-2.5-pro | — | $1.20-4% | $9.59-4% | — | — |
PackyAPI100% | gemini-2.5-pro | — | $0.179-86% | $1.43-86% | — | — |
小水管 API100% | gemini-2.5-pro | — | Бесплатно | Бесплатно | — | — |
MapleLeaf API100% | gemini-2.5-pro | — | $1.13-10% | $9.00-10% | — | — |
天絮 API100% | gemini-2.5-pro-exp-03-25 | — | $17.86 | $71.43 | — | — |
| gemini-2.5-pro-preview-03-25 | — | $17.86 | $71.43 | — | — | |
钠 API100% | gemini-2.5-pro | — | $0.014-99% | $0.904-91% | — | — |
Данные о ценах из публичных API провайдеров
Сравните производительность по скорости и задержке у всех API-провайдеров.
| Провайдер | Скорость | Задержка | Тесты |
|---|---|---|---|
BT6 API gemini-2.5-pro-preview-05-06 | 158.75 tok/s | 9.72s | 5 |
Xmdbd gemini-2.5-pro-preview-06-05-search | 114.70 tok/s | 11.37s | 15 |
gemini-2.5-pro | 111.40 tok/s | 17.90s | 5 |
gemini-2.5-pro | 105.53 tok/s | 16.40s | 5 |
gemini-2.5-pro-nothinking | 105.11 tok/s | 4.64s | 10 |
gemini-2.5-pro-exp-03-25 | 103.21 tok/s | 16.91s | 10 |
google/gemini-2.5-pro-exp | 101.91 tok/s | 17.27s | 8 |
gemini-2.5-pro | 91.91 tok/s | 16.35s | 5 |
测试/gemini-2.5-pro | 82.44 tok/s | 17.04s | 5 |
gemini-2.5-pro | 80.56 tok/s | 21.18s | 5 |
Gemini-2.5-Pro | 79.38 tok/s | 19.14s | 5 |
gemini-2.5-pro-search | 77.46 tok/s | 17.52s | 14 |
流式抗截断/gemini-2.5-pro | 52.63 tok/s | 15.62s | 5 |
gemini-2.5-pro | 47.39 tok/s | 25.24s | 25 |
Показано 1–14 из 14 провайдеров
gemini-3-flash
Google Gemini 3 Flash is a fast and efficient language model in the Gemini series, optimized for quick responses and high throughput.
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
gemini-3-1-pro
Google Gemini 3.1 Pro is a Gemini 3 series model with advanced multimodal reasoning, long-context support, and strong performance on coding and analytical tasks.
gemini-2-5-flash
Google Gemini 2.5 Flash is a fast and efficient language model in the Gemini series, optimized for quick responses and high throughput.
gpt-5-2
OpenAI GPT-5.2 is a GPT-5 series model emphasizing advanced reasoning, multimodal understanding, and high-quality outputs for complex enterprise workloads.
gpt-5-3-codex
OpenAI GPT-5.3 Codex is a code-specialized variant in the GPT-5 series, optimized for code generation, debugging, and software development tasks.
Рейтинги основаны на тестах, предоставленных сообществом, и периодических зондах работоспособности. Носит рекомендательный характер, не является официальными данными.Artificial Analysis
