Скорость вывода
30149.7 tok/s
34140.3 tok/s
35Gemini 3.1 Pro133.4 tok/s
36132.3 tok/s
Gemini 3.1 Pro by Google is available through 271 API providers on LMSpeed. Compare API pricing from $0.0001 to $1600.00 per million input tokens across providers. Free API access is offered by 3 providers. Context window: 1,048,576. In speed benchmarks, the fastest provider reaches 121 tok/s.
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.
Также известна как
Compare Gemini 3.1 Pro API pricing across 268 providers. Input prices range from $0.0001 to $1600.00 per million input. Joverna offers the lowest rate at $0.0001/M. 3 providers offer free API credits or a free tier.
| Провайдер | Вариант модели | Аудит | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен |
|---|---|---|---|---|---|---|
CatClaw API100% | gemini-3.1-pro-preview | — | $0.050-97% | $0.050-100% | 121.0 t/s | 11.40 s-60% |
速创API99.9% | gemini-3.1-pro-preview | — | $2.00 | $12.00 | 105.4 t/s | 12.72 s-56% |
TradingBase API100% | gemini-3.1-pro-preview | — | $2.14 | $12.83 | 101.8 t/s | 12.93 s-55% |
Tokeness99.9% | gemini-3.1-pro | — | $1.30-35% | $7.80-35% | 97.9 t/s | 12.32 s-57% |
钠 API100% | gemini-3.1-pro-preview | — | $0.0041-100% | $0.0041-100% | 95.5 t/s | 13.02 s-55% |
| gemini-3.1-pro-high | — | $0.0041-100% | $0.0041-100% | — | — | |
| gemini-3.1-pro-low | — | $0.0041-100% | $0.0041-100% | — | — | |
贵州大模型云算力 Token98.6% | gemini-3.1-pro | — | $20.00 | $100.00 | 88.8 t/s | 11.90 s-59% |
| gemini-3.1-pro-preview | — | $20.00 | $100.00 | — | — | |
Sliam74.2% | gemini-3.1-pro-preview | — | $75.00 | $300.00 | 83.3 t/s | 20.27 s-29% |
Hi API99.9% | gemini-3.1-pro-preview | — | $2.80 | $16.80 | 70.1 t/s | 23.27 s-19% |
| gemini-3.1-pro | — | $2.80 | $16.80 | — | — | |
| gemini-3.1-pro-preview-customtools | — | $2.80 | $16.80 | — | — | |
艾可API99.4% | gemini-3.1-pro-preview | — | $2.00 | $12.00 | 69.9 t/s | 18.61 s-35% |
柠檬API99.9% | gemini-3.1-pro-preview | — | $0.060-97% | $0.060-99% | 68.9 t/s | 19.70 s-31% |
| [L]gemini-3.1-pro-preview | — | $10.50 | $10.50-12% | — | — | |
柏拉图AI100% | gemini-3.1-pro-preview | — | $0.274-86% | $1.64-86% | — | — |
| gemini-3.1-pro-preview-customtools | — | $0.274-86% | $1.64-86% | — | — | |
V-API100% | gemini-3.1-pro-preview | — | $2.00 | $12.00 | — | — |
| gemini-3.1-pro-preview-high | — | $2.00 | $12.00 | — | — |
Данные о ценах из публичных API провайдеров
Сравните производительность по скорости и задержке у всех API-провайдеров.
| Провайдер | Скорость | Задержка | Тесты |
|---|---|---|---|
CatClaw API gemini-3.1-pro-preview | 120.98 tok/s | 11.40s | 10 |
gemini-3.1-pro-low | 113.28 tok/s | 15.70s | 5 |
gemini-3.1-pro-preview | 105.41 tok/s | 12.72s | 5 |
gemini-3.1-pro-preview | 101.84 tok/s | 12.93s | 10 |
gemini-3.1-pro | 97.93 tok/s | 12.32s | 5 |
gemini-3.1-pro-preview | 95.53 tok/s | 13.02s | 5 |
gemini-3.1-pro | 88.84 tok/s | 11.90s | 5 |
gemini-3.1-pro-preview | 83.31 tok/s | 20.27s | 5 |
Gemini-3-1-Pro | 80.71 tok/s | 10.09s | 5 |
gemini-3.1-pro-preview | 70.11 tok/s | 23.27s | 5 |
gemini-3.1-pro-preview | 69.88 tok/s | 18.61s | 5 |
gemini-3.1-pro-preview | 69.84 tok/s | 25.06s | 5 |
gemini-3.1-pro-preview | 68.85 tok/s | 19.70s | 5 |
Показано 1–13 из 13 провайдеров
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.
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.
claude-sonnet-4-6
Anthropic Claude Sonnet 4.6 extends the Sonnet line with improved tool use, coding reliability, and long-context performance for everyday production workloads.
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.
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.
claude-opus-4-6
Anthropic Claude Opus 4.6 is the most capable Claude Opus tier, optimized for complex analysis, long-horizon coding, and high-stakes enterprise reasoning workloads.
Рейтинги основаны на тестах, предоставленных сообществом, и периодических зондах работоспособности. Носит рекомендательный характер, не является официальными данными.Artificial Analysis
