DeepSeek-V3.1 pricing & specs
DeepSeek · released 2025-08-21 · ● verified 2026-10-11
input / 1M$0.25via DeepInfra
output / 1M$0.95via DeepInfra
context163.8K
max output8.2K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs DeepSeek-V3.1 |
|---|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −88.2% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −87.1% |
| Qwen Turbo | $0.05 | $0.20 | 1M | −79.4% |
| DeepSeek V4 Flash 0731 | $0.06 | $0.18 | 1.05M | −78.8% |
| GPT OSS 120B | $0.05 | $0.25 | 131.1K | −76.5% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| DeepInfra | $0.25 | $0.95 |
| Amazon Bedrock | $0.58 | $1.68 |
// faq
How much does DeepSeek-V3.1 cost?
DeepSeek-V3.1 costs $0.25 per million input tokens and $0.95 per million output tokens (cheapest tracked host: DeepInfra). At 50M input and 10M output tokens per month that is about $22.00.
What is the context window of DeepSeek-V3.1?
163.8K tokens, with up to 8.2K output tokens per request.
Does DeepSeek-V3.1 support prompt caching?
Yes. Cached input tokens cost $0.13 per million.
What are cheaper alternatives to DeepSeek-V3.1?
Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen Turbo ($0.05 in / $0.20 out) offer the same input types and capabilities for less.
Is DeepSeek-V3.1 open weights?
Yes. It is available from 2 tracked hosts; the cheapest is DeepInfra at $0.25 input and $0.95 output per million tokens.
// spec sheet
- input / 1M
- $0.25
- output / 1M
- $0.95
- cache read / 1M
- $0.13
- blended (3:1)
- $0.425
- context
- 163.8K
- max output
- 8.2K
- input types
- text
- reasoning
- yes
- tool calling
- yes
- structured output
- yes
- open weights
- yes
- knowledge cutoff
- n/a
- price source
- DeepInfra
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Qwen Turbo | $0.05 | $0.20 | $4.50 |
| DeepSeek-V3.1 | $0.25 | $0.95 | $22.00 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.