API текстовых моделей на APIMart: страница для моделей генерации текста и чат-моделей, которые еще не входят в отдельную серию, чтобы новые модели можно было сначала быстро опубликовать.
О чем вы думаете?
Спросите APIMart
Прозрачные цены без скрытых комиссий. Платите только за то, что используете.
| Вариант | Ввод | Вывод |
|---|---|---|
claude-haiku-5-5 | 0.8Credits(~$0.08)/M | 4Credits(~$0.4)/M |
gpt-6.1-sol | 16Credits(~$1.6)/M | 80Credits(~$8)/M |
claude-sonnet-5-5 | 16Credits(~$1.6)/M | 80Credits(~$8)/M |
gpt-6-luna | 0.8Credits(~$0.08)/M | 4Credits(~$0.4)/M |
gpt-6-sol | 16Credits(~$1.6)/M | 80Credits(~$8)/M |
claude-opus-5-5 | 32Credits(~$3.2)/M | 160Credits(~$16)/M |
grok-4.7 | 16Credits(~$1.6)/M | 48Credits(~$4.8)/M |
deepseek-v4.1-flash | 2.2857Credits(~$0.2286)/M | 9.1429Credits(~$0.9143)/M |
qwen3.8-max-0902 | 13.7143Credits(~$1.3714)/M | 41.1429Credits(~$4.1143)/M |
qwen3.8-flash | 0.9143Credits(~$0.0914)/M | 3.0857Credits(~$0.3086)/M |
qwen3.8-27b | 3.4286Credits(~$0.3429)/M | 13.7143Credits(~$1.3714)/M |
qwen3.7-flash | 0.2286Credits(~$0.0229)/M | 0.9143Credits(~$0.0914)/M |
qwen3.8-2.4t-a95b | 13.7143Credits(~$1.3714)/M | 41.1429Credits(~$4.1143)/M |
glm-5.3 | 11.2Credits(~$1.12)/M | 35.2Credits(~$3.52)/M |
glm-5.3-flash | 0.6Credits(~$0.06)/M | 2Credits(~$0.2)/M |
gpt-6-astra | 80Credits(~$8)/M | 400Credits(~$40)/M |
gemini-3.8-flash | 6Credits(~$0.6)/M | 30Credits(~$3)/M |
claude-fable-5.1 | 80Credits(~$8)/M | 400Credits(~$40)/M |
gemini-3.7-flash | 6Credits(~$0.6)/M | 30Credits(~$3)/M |
qwen3.8-max | 13.7143Credits(~$1.3714)/M | 41.1429Credits(~$4.1143)/M |
grok-4.6 | 16Credits(~$1.6)/M | 48Credits(~$4.8)/M |
kimi-k3 | 24Credits(~$2.4)/M | 120Credits(~$12)/M |
claude-opus-5 | 40Credits(~$4)/M | 200Credits(~$20)/M |
gemini-3.5-flash-lite | 2.4Credits(~$0.24)/M | 19.992Credits(~$1.9992)/M |
gemini-3.6-flash | 12Credits(~$1.2)/M | 60Credits(~$6)/M |
kimi-k2.7-code-highspeed | 14.8576Credits(~$1.4858)/M | 61.659Credits(~$6.1659)/M |
glm-5.2 | 9.1424Credits(~$0.9142)/M | 31.9984Credits(~$3.1998)/M |
grok-4.3 | 10Credits(~$1)/M | 20Credits(~$2)/M |
grok-4.5 | 16Credits(~$1.6)/M | 32Credits(~$3.2)/M |
qwen3.6-plus | 2.2864Credits(~$0.2286)/M | 13.7184Credits(~$1.3718)/M |
qwen3.7-plus | 2.2864Credits(~$0.2286)/M | 9.1456Credits(~$0.9146)/M |
step-3.7-flash | 1.5424Credits(~$0.1542)/M | 9.2544Credits(~$0.9254)/M |
minimax-m2.7 | 2.4Credits(~$0.24)/M | 9.6Credits(~$0.96)/M |
kimi-k2.7-code | 7.4288Credits(~$0.7429)/M | 30.8295Credits(~$3.083)/M |
minimax-m3 | 2.4Credits(~$0.24)/M | 9.6Credits(~$0.96)/M |
qwen3.6-flash | 1.3712Credits(~$0.1371)/M | 8.2272Credits(~$0.8227)/M |
mimo-v2.5-pro | 3.4288Credits(~$0.3429)/M | 6.8576Credits(~$0.6858)/M |
kimi-k2.6 | 7.4288Credits(~$0.7429)/M | 30.8295Credits(~$3.083)/M |
qwen3.7-max | 13.7136Credits(~$1.3714)/M | 41.1408Credits(~$4.1141)/M |
grok-build-0.1 | 8Credits(~$0.8)/M | 16Credits(~$1.6)/M |
gpt-5.6-terra | 16Credits(~$1.6)/M | 96Credits(~$9.6)/M |
gpt-5.6-luna | 1.6Credits(~$0.16)/M | 9.6Credits(~$0.96)/M |
gpt-5.6-sol | 32Credits(~$3.2)/M | 160Credits(~$16)/M |
claude-sonnet-5 | 16Credits(~$1.6)/M | 80Credits(~$8)/M |
claude-fable-5 | 80Credits(~$8)/M | 400Credits(~$40)/M |
claude-opus-4-8 | 40Credits(~$4)/M | 200Credits(~$20)/M |
gemini-3.5-flash | 12Credits(~$1.2)/M | 72Credits(~$7.2)/M |
deepseek-v4-pro | 10.2857Credits(~$1.0286)/M | 30.8571Credits(~$3.0857)/M |
deepseek-v4-flash | 3.4286Credits(~$0.3429)/M | 10.2857Credits(~$1.0286)/M |
gpt-5.4-mini | 6Credits(~$0.6)/M | 36Credits(~$3.6)/M |
gpt-5.1-codex-max | 10Credits(~$1)/M | 80Credits(~$8)/M |
gpt-5.4-nano | 1.6Credits(~$0.16)/M | 10Credits(~$1)/M |
gpt-5.4-pro | 240Credits(~$24)/M | 1440Credits(~$144)/M |
gpt-5.5 | 40Credits(~$4)/M | 240Credits(~$24)/M |
claude-opus-4-7 | 40Credits(~$4)/M | 200Credits(~$20)/M |
glm-5.1 | 8Credits(~$0.8)/M | 14.4Credits(~$1.44)/M |
deepseek-ocr | 0.456Credits(~$0.0456)/M | 2.052Credits(~$0.2052)/M |
glm-4.6 | 3.6Credits(~$0.36)/M | 14.4Credits(~$1.44)/M |
minimax-m2.1 | 2.16Credits(~$0.216)/M | 8.64Credits(~$0.864)/M |
kimi-k2-thinking | 4Credits(~$0.4)/M | 16.8Credits(~$1.68)/M |
deepseek-v3.2-exp | 2.056Credits(~$0.2056)/M | 3.084Credits(~$0.3084)/M |
deepseek-v3.1-terminus | 4.08Credits(~$0.408)/M | 12.24Credits(~$1.224)/M |
kimi-k2-instruct | 4Credits(~$0.4)/M | 16.8Credits(~$1.68)/M |
glm-4.7 | 4Credits(~$0.4)/M | 16.8Credits(~$1.68)/M |
gpt-5.3-codex | 14Credits(~$1.4)/M | 112Credits(~$11.2)/M |
gpt-5.4 | 20Credits(~$2)/M | 120Credits(~$12)/M |
deepseek-r1-0528 | 4.08Credits(~$0.408)/M | 12.3216Credits(~$1.2322)/M |
claude-sonnet-4-6-thinking | 24Credits(~$2.4)/M | 120Credits(~$12)/M |
claude-opus-4-6 | 40Credits(~$4)/M | 80Credits(~$8)/M |
gemini-3.1-pro-preview | 16Credits(~$1.6)/M | 96Credits(~$9.6)/M |
claude-sonnet-4-6 | 24Credits(~$2.4)/M | 120Credits(~$12)/M |
claude-opus-4-6-thinking | 40Credits(~$4)/M | 200Credits(~$20)/M |
minimax-m2.5 | 2.4Credits(~$0.24)/M | 9.6Credits(~$0.96)/M |
glm-5 | 8Credits(~$0.8)/M | 12.8Credits(~$1.28)/M |
kimi-k2.5 | 4.112Credits(~$0.4112)/M | 5.5512Credits(~$0.5551)/M |
gpt-5.2-codex | 14Credits(~$1.4)/M | 112Credits(~$11.2)/M |
o4-mini-2025-04-16 | 8.8Credits(~$0.88)/M | 35.2Credits(~$3.52)/M |
gpt-4-1106-preview | 80Credits(~$8)/M | 160Credits(~$16)/M |
gpt-5.1-chat-latest | 10Credits(~$1)/M | 80Credits(~$8)/M |
gemini-3-flash-preview-nothinking | 4Credits(~$0.4)/M | 24Credits(~$2.4)/M |
gpt-4.1-mini-2025-04-14 | 3.2Credits(~$0.32)/M | 12.8Credits(~$1.28)/M |
gpt-5.1 | 10Credits(~$1)/M | 80Credits(~$8)/M |
gpt-4o-transcribe | 20Credits(~$2)/M | 80Credits(~$8)/M |
gpt-5.1-2025-11-13 | 10Credits(~$1)/M | 80Credits(~$8)/M |
gpt-5.2-pro | 168Credits(~$16.8)/M | 1344Credits(~$134.4)/M |
gpt-5.1-codex-mini | 2Credits(~$0.2)/M | 16Credits(~$1.6)/M |
o1-mini-2024-09-12 | 8.8Credits(~$0.88)/M | 35.2Credits(~$3.52)/M |
o3-mini-2025-01-31 | 8.8Credits(~$0.88)/M | 35.2Credits(~$3.52)/M |
gpt-5-2025-08-07 | 10Credits(~$1)/M | 80Credits(~$8)/M |
deepseek-v3.2 | 2.056Credits(~$0.2056)/M | 3.084Credits(~$0.3084)/M |
o1-2024-12-17 | 120Credits(~$12)/M | 480Credits(~$48)/M |
claude-sonnet-4-5-20250929-thinking | 24Credits(~$2.4)/M | 120Credits(~$12)/M |
gpt-4o-mini-transcribe | 10Credits(~$1)/M | 40Credits(~$4)/M |
gpt-5.2-chat-latest | 14Credits(~$1.4)/M | 112Credits(~$11.2)/M |
claude-opus-4-5-20251101-thinking | 40Credits(~$4)/M | 200Credits(~$20)/M |
qwen-turbo | 2.4Credits(~$0.24)/M | 24Credits(~$2.4)/M |
gpt-5-pro-2025-10-06 | 120Credits(~$12)/M | 960Credits(~$96)/M |
gpt-5-mini-2025-08-07 | 2Credits(~$0.2)/M | 16Credits(~$1.6)/M |
gpt-5.2 | 14Credits(~$1.4)/M | 112Credits(~$11.2)/M |
gpt-3.5-turbo-16k | 24Credits(~$2.4)/M | 72Credits(~$7.2)/M |
* Фактические расходы зависят от конечного результата.
Тестируйте больше LLM и моделей генерации текста через единый API. Новые чат-модели можно размещать здесь без предварительного создания отдельной категории.
50K+
Активные пользователи
99.9%
Время работы
2x
Быстрее
70%
Экономия
Гибкая точка входа для новых или пока не классифицированных языковых моделей
Типовые способы оценивать и запускать больше языковых моделей
Начните тестировать больше LLM за несколько минут
Зарегистрируйтесь в APIMart и пополните баланс кредитами.
Создайте API Key в панели управления для авторизованных запросов.
Используйте playground или интегрируйтесь через Chat Completions API.
Популярные вопросы о доступе к текстовым моделям
Здесь отображаются модели генерации текста и чат-модели, у которых пока нет отдельной страницы серии.
Да. Ссылка на модель может содержать параметр id, и при открытии страницы будет выбрана соответствующая модель.
Цена зависит от выбранной модели, а соответствующая информация о тарификации отображается в таблице цен на странице.
Многие текстовые модели поддерживают OpenAI-совместимые вызовы chat completions. Перед интеграцией проверьте данные конкретной модели.
Откройте для себя другие модели в той же категории.
Kimi K3
Kimi-K3 is a next-generation large language model launched by Moonshot AI. It features ultra-long context, multimodal understanding, and strong coding capabilities, making it suitable for complex reasoning, software development, knowledge analysis, and agent automation tasks.
Claude Opus 5
Claude Opus 5 is Anthropic’s next-generation flagship large language model, featuring enhanced capabilities in code development, complex reasoning, knowledge analysis, and agent execution, making it ideal for large-scale project development and professional work scenarios.
Gemini 3.5 Flash Lite
A lightweight multimodal model launched by Google that emphasizes low cost, low latency, and high throughput. It is suitable for document parsing, data extraction, structured output, and large-scale agent workflows, delivering faster response times while maintaining core reasoning capabilities.
Gemini 3.6 Flash
Gemini 3.6 Flash is a faster, more token-efficient, and more code-capable version of the Gemini Flash model, suitable for everyday development, AI agents, and high-concurrency applications.