DeepSeek V3 671B
DeepSeek V3 671B is DeepSeek's language model with a 131K context window and up to 16K output tokens, starting at $0.287 / 1M input and $1.15 / 1M output. The full 671B-parameter release of DeepSeek V3, a MoE LLM with 37B activated parameters per token for efficient large-scale inference.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
| $0.287 | $1.15 | $0.143 | $0.574 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek V3.2 Reasoning | — | — | — | — | Available |
| DeepSeek V3.1 Terminus Reasoning | — | — | — | — | Available |
| DeepSeek V3.1 Reasoning | — | — | — | — | Available |
| DeepSeek V3 671B | — | 131K | $0.287 | $1.15 | Current |
| DeepSeek V3 2SP | — | — | $0.580 | $1.68 | Available |
| DeepSeek V3 Community | — | — | — | — | Available |