DeepSeek V3 Turbo
DeepSeek V3 Turbo is DeepSeek's language model with a 64K context window and up to 16K output tokens, available from 2 providers, starting at $0.400 / 1M input and $1.30 / 1M output. A turbo-speed variant of DeepSeek V3 optimized for faster inference, pre-trained on nearly 15 trillion tokens with strong coding and instruction-following abilities.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities2/13
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
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 Hugging Face | $0.400 | $1.30 |
 Novita | $0.400 | $1.30 |
Cost Calculator
Preset:
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| DeepSeek V3.2 Speciale | — | 164K | $0.287 | $0.431 | |
| DeepSeek V3.2 Thinking | — | 128K | $0.620 | $1.85 | |
| DeepSeek V3.2 Exp Reasoning | — | — | — | — | — |
| DeepSeek V3.2 Exp | — | — | — | — | — |
| DeepSeek V3.1 671B | — | — | 164K | — | — |
| DeepSeek V3 324B | — | — | — | — | — |
| DeepSeek V3.2 Reasoning | — | — | — | — | — |
| DeepSeek V3.1 Terminus Reasoning | — | — | — | — | — |
| DeepSeek V3.1 Reasoning | — | — | — | — | — |
| DeepSeek V3 2SP | — | — | — | $0.580 | $1.68 |