Скорость вывода
9205.7 tok/s
10204.4 tok/s
11Devstral Small203.2 tok/s
12201.7 tok/s
devstral-small
Разработчик: Mistral AI
Mistral AI Devstral Small is a code-specialized variant in the Mistral series, optimized for code generation, debugging, and software development tasks.
Также известна как
Devstral Small by Mistral AI is available through 13 API providers on LMSpeed. Compare API pricing from $0.100 to $75.00 per million input tokens across providers.
Рейтинги основаны на тестах, предоставленных сообществом, и периодических зондах работоспособности. Носит рекомендательный характер, не является официальными данными.Artificial Analysis
Compare Devstral Small API pricing across 13 providers. Input prices range from $0.100 to $75.00 per million input. WAADRI offers the lowest rate at $0.100/M.
| Провайдер | Вариант модели | Аудит | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен |
|---|---|---|---|---|---|---|
钱多多 API100% | devstral-small-2507 | — | $0.490 | $1.47 | — | — |
| devstral-small-latest | — | $0.490 | $1.47 | — | — | |
IXIOCCAPI99.9% | chutesai/Devstral-Small-2505 | — | $75.00 | $75.00 | — | — |
| devstral-small-2505 | — | $75.00 | $75.00 | — | — | |
| devstral-small-latest | — | $75.00 | $75.00 | — | — | |
| mistralai/devstral-small | — | $75.00 | $75.00 | — | — | |
| mistralai/devstral-small-2505 | — | $75.00 | $75.00 | — | — | |
| mistralai/devstral-small-2505:free | — | $75.00 | $75.00 | — | — | |
AI API99.8% | mistralai/devstral-small | — | $0.200 | $0.600 | — | — |
| devstral-small-2505 | — | $0.100 | $0.300 | — | — | |
| devstral-small-2507 | — | $0.100 | $0.300 | — | — | |
| devstral-small-latest | — | $2.00 | $2.00 | — | — | |
CHB API28.4% | mistralai/Devstral-Small-2505 | — | $1.03 | $1.03 | — | — |
Данные о ценах из публичных API 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.
gpt-5
OpenAI GPT-5 is OpenAI frontier general-purpose model with improved reasoning depth, coding reliability, and multimodal understanding for production assistants and agent workflows.
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.
deepseek-r1
DeepSeek R1 is a reasoning-focused language model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.
glm-4-7
Zhipu GLM-4.7 is a flagship GLM release from Zhipu AI with advanced Chinese-English reasoning, coding, and agent features.
gpt-oss
GPT-OSS is an open-source language model offering advanced reasoning, code generation, and multimodal capabilities.
