DeepSeek V3.1
DeepSeek V3.1 is DeepSeek's language model with a 164K context window and up to 33K output tokens, starting at $0.21 / 1M input and $0.79 / 1M output. DeepSeek's 671B-parameter hybrid reasoning MoE LLM that supports both thinking and non-thinking modes via prompt templates, extending the V3 base.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill✓
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $0.21 | $0.79 | $0.13 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek V3.1 | 164K | $0.210 | $0.790 | Current | |
| DeepSeek V3 0324 | 131K | $0.200 | $0.770 | Available | |
| Kimi K2 Instruct | — | 262K | $0.500 | $2.00 | Available |