DeepSeek V3 671B
DeepSeek V3 671B is DeepSeek's language model with a 131K context window and up to 16K output tokens. 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:
Cheapest Instances to Run It
Cloud GPU instances that can host DeepSeek V3 671B, ranked by cheapest on-demand price. The model needs about 1610 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region |
|---|---|---|---|---|---|
| p6-b300.48xlarge |  AWS | 8× B300 | 2149 GB | $142.42/hr | us-east-1 |
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 | — | — | Current |
| DeepSeek V3 2SP | — | — | $0.580 | $1.68 | Available |
| DeepSeek V3 Community | — | — | — | — | Available |