DeepSeek V3.1 (Reasoning) API Pricing

DeepSeek · released 2025-08-21

Pricing

$0.59
input / 1M tokens
0.059¢ / 1K
$1.69
output / 1M tokens
0.169¢ / 1K
$0.865
blended / 1M tokens
0.086¢ / 1K

What it actually costs

WorkloadTokensCost
Short chat reply500 in / 300 out0.0802¢
RAG query4,000 in / 500 out0.321¢
Long document summary50,000 in / 1,000 out$0.0312
Code review of a 2k-line file30,000 in / 2,000 out$0.0211
1,000 chat replies/day for 30 days30,000 × (500 in / 300 out)$24.06

Cost = (input tokens ÷ 1,000,000 × $0.59) + (output tokens ÷ 1,000,000 × $1.69).

Benchmarks

13.5
Intelligence
#194 of 533
Coding
89.7
Math
#26 of 249
Tokens/sec
Time to first token

Similar intelligence, lower price

ModelIntelligenceBlended $/1M
Qwen3.5 4B (Reasoning)13.1$0.06
Nemotron 3.5 Lightning12.9$0.095
Granite 4.2 8B11.1$0.107
GPT-5 nano (high)13.0$0.138
Gemma 4 12B (Reasoning)14.2$0.15

Leaderboard neighbours

ModelIntelligenceBlended $/1M
DeepSeek V3.1 (Non-reasoning)13.7$0.848
Qwen3.5 9B (Reasoning)13.7$0.151
Nova 2.0 Omni (medium)13.6$0.85
DeepSeek V3.1 (Reasoning)13.5$0.865
Apriel-v1.6-15B-Thinker13.4
Nova 2.0 Lite (high)13.4$0.85
Qwen3 VL 235B A22B (Reasoning)13.4$1.30

More from DeepSeek

ModelIntelligenceBlended $/1M
DeepSeek V4.1 Flash (Reasoning, Max Effort)39.5$0.525
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)36.0$1.98
DeepSeek V4 Flash Vision (Reasoning, Max Effort)34.8$0.66
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)34.3$0.66
DeepSeek V4 Pro 0424 (Reasoning, Max Effort)30.4$0.544
DeepSeek V4 Flash 0420 (Reasoning, High Effort)26.0$0.168
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 2026-09-22

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 $0.59 per 1M input tokens and $1.69 per 1M output tokens ($0.865 blended), per Artificial Analysis's official pricing data.

How does DeepSeek V3.1 (Reasoning) rank on benchmarks?

DeepSeek V3.1 (Reasoning) scores 13.5 on the Artificial Analysis Intelligence Index, ranking #194 of 533 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 $0.865/1M 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 2026-09-22.