DeepSeek V3.1 Pricing
FastDeepSeek · 164K tokens context
DeepSeek V3.1 from DeepSeek costs $0.210 per 1 million input tokens and $0.790 per 1 million output tokens as of June 2026 (live OpenRouter data). The model supports a 163,840-token context window (approximately 122,880 words) with a 33K-token maximum output. A typical 1,000-token request costs $0.0002 in input charges; a 10,000-token request costs $0.0021.
| Input price | $0.210 / 1M tokens |
|---|---|
| Output price | $0.790 / 1M tokens |
| Output / input ratio | 3.8× |
| Context window | 163,840 tokens (~122,880 words) |
| Maximum output | 32,768 tokens |
| Cost per 1K tokens (input) | $0.0002 |
| Tier | Fast |
| Last verified |
DeepSeek-V3. 1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.
Input Price
$0.210
per 1 million tokens
Output Price
$0.790
per 1 million tokens
Context Window
164K tokens
max 33K output
Cost Examples
| Request Type | Tokens | Input Cost | Output Cost |
|---|---|---|---|
| 1,000 word article | 1,333 | $0.00028 | $0.000316 |
| 10-page document (2,500 words) | 3,333 | $0.0007 | $0.00079 |
| 1,000 lines of code | 5,000 | $0.00105 | $0.00119 |
| 100K token document | 100,000 | $0.021 | $0.0237 |
Output cost estimated at 30% of input token count. Use the calculator for exact figures.
Strengths
- ✓Affordable at $0.21/1M input tokens
- ✓Low latency for high-throughput workloads
- ✓Cost-effective at scale
Limitations
- –Less capable than flagship models on complex reasoning
- –Quality and availability can vary by hosting provider
Best Use Cases
Calculate DeepSeek V3.1 Costs
Use the TokenRate calculator to convert any budget, token count, or text into exact DeepSeek V3.1 costs — and compare across all models.
Open Calculator →DeepSeek V3.1 — FAQ
Related Models
Related Guides