deepseek-chat-v3.1 by deepinfra - AI Model Details, Pricing, and Performance Metrics
deepseek-chat-v3.1
completionsDeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.
| Provider | Input | Output |
|---|---|---|
 | $0.3 / 1M tokens | $1 / 1M tokens |
 | $0.64 / 1M tokens | $1.65 / 1M tokens |
| Providers | Context | Input Price | Output Price | Input Formats | Output Formats |
|---|---|---|---|---|---|
| 163840 tokens | $0.3 / 1M tokens | $1 / 1M tokens | text | text |
| 163840 tokens | $0.64 / 1M tokens | $1.65 / 1M tokens | text | text |
Access deepseek-chat-v3.1 through LangDB AI Gateway
Integrate with deepseek's deepseek-chat-v3.1 and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.
Free tier available • No credit card required
Statistics
Category Scores
Benchmark Tests
| Metric | AA Coding Index | AAII | AA Math Index | GPQA | HLE | LiveCodeBench | MMLU-Pro | SciCode |
|---|---|---|---|---|---|---|---|---|
| Score | 47.2 | 44.8 | 49.7 | 73.5 | 6.3 | 57.7 | 83.3 | 36.7 |
Compare with Similar Models
Code Examples
Integration samples and API usage
Related Models
Similar models from deepinfra