deepseek-chat-v3.1
by deepseekDeepSeek-V3.1 is a 671B-parameter hybrid reasoning model (37B active), supporting both "thinking" and "non-thinking" modes via prompt templates. It extends DeepSeek-V3 with two-phase long-context training (up to 128K tokens) and uses FP8 microscaling for efficient inference. The model excels in tool use, code generation, and reasoning, with performance comparable to DeepSeek-R1 but with faster responses. It supports structured tool calling, code agents, and search agents, making it ideal for research and agentic workflows. Successor to DeepSeek V3-0324, it delivers strong performance across diverse tasks.
Pricing
Pay-as-you-go rates for this model. More details can be found here.
Input Tokens (1M)
$0.10
Output Tokens (1M)
$0.40
Capabilities
Input Modalities
Output Modalities
Rate Limits
Requests per minute (RPM) and per day (RPD) by tier. More about tiers here
| Tier | RPM | RPD |
|---|---|---|
| Free | 2 | 50 |
| Tier 1 | 10 | — |
| Tier 2 | 15 | — |
| Tier 3 | 25 | — |
| Tier 4 | 50 | — |
Usage Analytics
Token usage across the last 30 active days