Codestral by Mistral AI is available through 12 API providers on LMSpeed. Compare API pricing from $0.010 to $75.00 per million input tokens across providers. Context window: 256,000. In speed benchmarks, the fastest provider reaches 151 tok/s.
Также известна как
Compare Codestral API pricing across 12 providers. Input prices range from $0.010 to $75.00 per million input. 素墨API offers the lowest rate at $0.010/M.
| Провайдер | Вариант модели | Аудит | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен |
|---|---|---|---|---|---|---|
素墨API100% | codestral-2501 | — | $0.010 | $0.010 | — | — |
钱多多 API100% | codestral-2405 | — | $1.47 | $4.41 | — | — |
| codestral-2412 | — | $1.47 | $4.41 | — | — | |
| codestral-2501 | — | $1.47 | $4.41 | — | — | |
| codestral-2508 | — | $1.47 | $4.41 | — | — | |
| codestral-latest | — | $1.47 | $4.41 | — | — | |
IXIOCCAPI99.9% | codestral-2412 | — | $75.00 | $75.00 | — | — |
| codestral-2501 | — | $75.00 | $75.00 | — | — | |
| codestral-latest | — | $75.00 | $75.00 | — | — | |
| mistralai/codestral-2501 | — | $75.00 | $75.00 | — | — | |
| mistralai/codestral-2508 | — | $75.00 | $75.00 | — | — | |
SWT-API98.3% | codestral-2501 | — | $0.037 | $0.037 | — | — |
Данные о ценах из публичных API провайдеров
Сравните производительность по скорости и задержке у всех API-провайдеров.
| Провайдер | Скорость | Задержка | Тесты |
|---|---|---|---|
Mistral AI codestral-latest | 151.00 tok/s | 0.38s | 5 |
Показано 1–1 из 1 провайдеров
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.
qwen3
Alibaba Qwen3 is the Qwen family's flagship LLM series with dense and MoE variants, seamless thinking/non-thinking modes, and leading open-source performance in math, code, and agent tasks.
glm-4-5-air
Zhipu AI GLM-4.5 Air is a fast and efficient language model in the GLM series, optimized for quick responses and high throughput.
kimi-k2
Moonshot Kimi K2 is a trillion-parameter MoE model from Moonshot AI, built for long-context chat, agentic tool use, and high-quality Chinese-English bilingual generation.
qwen3-coder
Alibaba Qwen3 Coder is a code-specialized variant in the Qwen 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.
