DeepSeek Chat V3.1 API Benchmarks, Pricing & Provider Data
Compare DeepSeek Chat V3.1 with another model
Choose a model to open its comparison page.
На странице также приведены измеренная скорость API и задержка первого токена.
DeepSeek Chat V3.1 is an instruction-tuned variant in the DeepSeek series, optimized for following instructions and conversational tasks.
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Возможности
Technical Details
- Вход
- Выход
- Выпущена
- Aug 2025
- Срез знаний
- 2025-03-31
- Токенизатор
- DeepSeek
- Архитектура
- text->text
- Тип инструкций
- deepseek-v3.1
- Модерация
- Нет
- Поддерживаемые параметры
- frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Эндпоинты OpenRouter
8 эндпоинтовСторонние данные эндпоинтов OpenRouter показаны отдельно от измерений LMSpeed. Некоторые 30-минутные live-метрики появляются только после синхронизации с OpenRouter API key.
| Provider endpoint | Вход | Вывод | Доступность 1 день | Задержка 30м | Пропускная способность 30м | Контекст / вывод |
|---|---|---|---|---|---|---|
CoreWeave coreweave/fp8 | $0.550/M | $1.65/M | 100.0% | — | — | undefined токенов / undefined токенов |
Novita novita/fp8 | $0.270/M | $1/M | 100.0% | — | — | undefined токенов / undefined токенов |
DeepInfra deepinfra/fp4 | $0.250/M | $0.950/M | 99.9% | — | — | undefined токенов / undefined токенов |
SambaNova sambanova/fp8 | $0.650/M | $1.50/M | 99.0% | — | — | undefined токенов / undefined токенов |
AtlasCloud atlas-cloud/fp8 | $0.300/M | $0.950/M | 96.4% | — | — | undefined токенов / undefined токенов |
SiliconFlow siliconflow/fp8 | $0.270/M | $1/M | 95.5% | — | — | undefined токенов / undefined токенов |
Mara mara | $0.600/M | $1.70/M | 94.8% | — | — | undefined токенов / undefined токенов |
Google google-vertex/us-west2 | $0.600/M | $1.70/M | 0% | — | — | undefined токенов / undefined токенов |
Альтернативы и похожие модели
Gemini 2.5 Pro
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.
Qwen3
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.
Kimi K2
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
qwen3-coder
Alibaba Qwen3 Coder is a code-specialized variant in the Qwen series, optimized for code generation, debugging, and software development tasks.
GPT-5.4
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
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.