Скорость вывода
10206.4 tok/s
11201.0 tok/s
13Gemini 2.5 Flash194.9 tok/s
14190.4 tok/s
Gemini 2.5 Flash by Google is available through 246 API providers on LMSpeed. Compare API pricing from $0.0001 to $75.00 per million input tokens across providers. Context window: 1,048,576. In speed benchmarks, the fastest provider reaches 225 tok/s.
Google Gemini 2.5 Flash is a fast and efficient language model in the Gemini series, optimized for quick responses and high throughput.
Также известна как
Compare Gemini 2.5 Flash API pricing across 246 providers. Input prices range from $0.0001 to $75.00 per million input. SWT-API offers the lowest rate at $0.0001/M.
| Провайдер | Вариант модели | Аудит | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен |
|---|---|---|---|---|---|---|
KZW API100% | gemini-2.5-flash | — | $0.300 | $2.50 | 185.7 t/s | 10.41 s |
UniAiX100% | gemini-2.5-flash | — | $0.300 | $2.50 | 158.0 t/s | 9.77 s |
素墨API100% | gemini-2.5-flash | — | $0.010-97% | $0.010-100% | 136.0 t/s | 11.32 s |
| anti/gemini-2.5-flash | — | $0.010-97% | $0.010-100% | — | — | |
| cli/gemini-2.5-flash | — | $0.010-97% | $0.010-100% | — | — | |
柏拉图AI100% | gemini-2.5-flash | — | $0.041-86% | $0.342-86% | — | — |
| gemini-2.5-flash-nothinking | — | $0.041-86% | $0.342-86% | — | — | |
| gemini-2.5-flash-preview-04-17 | — | $0.041-86% | $0.342-86% | — | — | |
| gemini-2.5-flash-preview-05-20 | — | $0.041-86% | $0.342-86% | — | — | |
| gemini-2.5-flash-preview-09-2025 | — | $0.041-86% | $0.342-86% | — | — | |
| gemini-2.5-flash-preview-09-2025-nothinking | — | $10.27 | $41.10 | — | — | |
V-API100% | gemini-2.5-flash | — | $0.300 | $2.50 | — | — |
| gemini-2.5-flash-nothinking | — | $0.300 | $2.50 | — | — | |
老张API100% | gemini-2.5-flash | — | $0.288-4% | $2.30-8% | — | — |
| gemini-2.5-flash-nothinking | — | $0.288-4% | $2.30-8% | — | — | |
PackyAPI100% | gemini-2.5-flash | — | $0.043-86% | $0.357-86% | — | — |
MapleLeaf API100% | gemini-2.5-flash | — | $0.075-75% | $0.300-88% | — | — |
钠 API100% | gemini-2.5-flash | — | $0.025-92% | $0.205-92% | — | — |
速创API99.9% | gemini-2.5-flash | — | $0.300 | $2.50 | — | — |
| gemini-2.5-flash-nothinking | — | $0.300 | $2.50 | — | — |
Данные о ценах из публичных API провайдеров
Сравните производительность по скорости и задержке у всех API-провайдеров.
| Провайдер | Скорость | Задержка | Тесты |
|---|---|---|---|
Lido LLM gcli/gemini-2.5-flash | 225.13 tok/s | 8.61s | 5 |
gemini-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 | 189.12 tok/s | 11.43s | 5 |
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 | 116.32 tok/s | 17.34s | 5 |
gemini-2.5-flash | 54.24 tok/s | 10.36s | 10 |
gemini-2.5-flash | 34.41 tok/s | 17.36s | 5 |
Показано 1–14 из 14 провайдеров
gemini-2-5-pro
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.
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.
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
