DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus is DeepSeek's language model with a 164K context window and up to 66K output tokens, available from 6 providers, starting at $0.270 / 1M input and $0.950 / 1M output. An update to DeepSeek V3.1 that addresses language consistency and agent capability issues while preserving the model's core performance.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
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 | Cache Read $ / 1M | |
 DeepInfra | $0.270 | $1.00 | $0.216 |
 Hugging Face | $0.270 | $1.00 | N/A |
 Novita | $0.270 | $1.00 | $0.135 |
 OpenRouter | $0.270 | $0.950 | $0.130 |
 Vercel AI Gateway | $0.270 | $1.00 | $0.135 |
 Fireworks AI | $0.560 | $1.68 | N/A |
Cost Calculator
Preset:
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| DeepSeek V3.1 | — | 164K | $0.135 | $0.500 | |
| DeepSeek V3.1 | — | 164K | $0.210 | $0.790 | |
| DeepSeek V3 0324 | — | 164K | $0.200 | $0.770 | |
| DeepSeek V3 | — | 400K | $0.200 | $0.200 | |
| DeepSeek V3 324 | — | — | 164K | $0.200 | $0.400 |
| DeepSeek Prover V2 | — | — | 164K | $1.20 | $1.20 |
| Kimi K2 Instruct | — | — | 262K | $0.500 | $2.00 |
| DeepSeek R1 528 | — | 164K | $0.200 | $0.250 | |
| DeepSeek R1 | — | 164K | $0.280 | $0.400 | |
| DeepSeek R1 Basic | Basic | — | 128K | $0.550 | $2.19 |