DeepSeek V3.1 (Reasoning) API Pricing
DeepSeek · released 2025-08-21
Also searched as: DeepSeek V3.1 pricing
DeepSeek V3.1 (Reasoning) price
0.058¢ / 1K
0.168¢ / 1K
0.085¢ / 1K
What it actually costs
| Workload | Tokens | Cost |
|---|---|---|
| Short chat reply | 500 in / 300 out | 0.0794¢ |
| RAG query | 4,000 in / 500 out | 0.316¢ |
| Long document summary | 50,000 in / 1,000 out | $0.0307 |
| Code review of a 2k-line file | 30,000 in / 2,000 out | $0.0208 |
| 1,000 chat replies/day for 30 days | 30,000 × (500 in / 300 out) | $23.82 |
Cost = (input tokens ÷ 1,000,000 × $0.58) + (output tokens ÷ 1,000,000 × $1.68).
Benchmarks
#203 of 547
#26 of 249
Similar intelligence, lower price
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Qwen3.5 4B (Reasoning) | 13.1 | $0.06 |
| Nemotron 3.5 Lightning | 12.9 | $0.095 |
| Granite 4.2 8B | 11.1 | $0.107 |
| GPT-5 nano (High) | 13.0 | $0.138 |
| Gemma 4 12B (Reasoning) | 14.2 | $0.15 |
Leaderboard neighbours
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Apriel-v1.5-15B-Thinker | 13.8 | — |
| DeepSeek V3.1 (Non-reasoning) | 13.7 | $0.84 |
| Nova 2.0 Omni (Medium) | 13.6 | $0.85 |
| DeepSeek V3.1 (Reasoning) | 13.5 | $0.855 |
| Apriel-v1.6-15B-Thinker | 13.4 | — |
| Nova 2.0 Lite (High) | 13.4 | $0.935 |
| Qwen3 VL 235B A22B (Reasoning) | 13.4 | — |
More from DeepSeek
| Model | Intelligence | Blended $/1M |
|---|---|---|
| DeepSeek V4.1 Flash (Max) | 39.5 | $0.525 |
| DeepSeek V4 Pro 0813 (Max) | 36.0 | $1.98 |
| DeepSeek V4 Flash Vision (Max) | 34.8 | $0.66 |
| DeepSeek V4 Flash 0731 (Max) | 34.3 | $0.66 |
| DeepSeek V4 Pro 0424 (Max) | 30.4 | $0.544 |
| DeepSeek V4 Flash 0420 (High) | 24.4 | $0.142 |
| DeepSeek V3.2 (Reasoning) | 21.5 | $0.315 |
| DeepSeek V3.2 Exp (Reasoning) | 16.6 | $0.315 |
Count tokens & estimate cost for DeepSeek V3.1 (Reasoning) See DeepSeek V3.1 (Reasoning) on the leaderboard
Source: Artificial Analysis · last synced 2026-10-15
FAQ
Who develops DeepSeek V3.1 (Reasoning)?
DeepSeek V3.1 (Reasoning) is developed by DeepSeek, released 2025-08-21.
How much does DeepSeek V3.1 (Reasoning) cost per million tokens?
DeepSeek V3.1 (Reasoning) costs $0.58 per 1M input tokens and $1.68 per 1M output tokens ($0.855 blended), per Artificial Analysis's official pricing data.
What is the DeepSeek V3.1 (Reasoning) API price?
The DeepSeek V3.1 (Reasoning) API price is $0.58 per 1M input tokens and $1.68 per 1M output tokens ($0.855 per 1M blended).
How much does DeepSeek V3.1 (Reasoning) cost for a typical request?
A short chat reply (500 in / 300 out tokens) costs about 0.0794¢ on DeepSeek V3.1 (Reasoning), at $0.58/1M input and $1.68/1M output.
Is DeepSeek V3.1 (Reasoning) free?
DeepSeek V3.1 (Reasoning)'s official API list price is $0.58 per 1M input tokens and $1.68 per 1M output tokens. This site tracks list prices only, not free tiers or trial credits — check DeepSeek's site for those.
How does DeepSeek V3.1 (Reasoning) rank on benchmarks?
DeepSeek V3.1 (Reasoning) scores 13.5 on the Artificial Analysis Intelligence Index, ranking #203 of 547 models we track.
Is there a cheaper model with similar intelligence to DeepSeek V3.1 (Reasoning)?
Yes — Qwen3.5 4B (Reasoning) scores similar intelligence (13.1) at $0.06/1M blended, versus $0.855/1M for DeepSeek V3.1 (Reasoning).
Where does this data come from?
Pricing and benchmark data for DeepSeek V3.1 (Reasoning) comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-10-15.