DeepSeek V3.1

by DeepSeekChat

DeepSeek chat model for instruction following, coding, and analysis

Context
164K tokens
Max output
131,072 tokens
Parameters
685B total, 37B active
Released
2025-08-21
Weights
Open
Licence
mit

FeedWeights on Hugging Face

deepseek/deepseek-v3-1 · also seen as deepseek.v3-v1:0, deepseek-ai/DeepSeek-V3.1, deepseek-ai/DeepSeek-V3.1:thinking, accounts/fireworks/models/deepseek-v3p1

Specifications

Full facts as recorded, incl. what is unknown.

Released
2025-08-21
Weights
Opennot gated
License
mit
Input
Text
Output
Text
Context window
164,000 max across endpoints
Max output
131,072
Providers
18 + 8 gateways, not counted as providers
Epoch Capabilities Index
139.9 ± 3.7 against price
Direct price range
$0.190–$0.672 in · $0.71–$2.02 out per 1M tokens · 14 of 18 providers have a comparable price
More details
Last updated
2026-01
Knowledge cutoff
2025-08
Weights link
Hugging Face · deepseek-ai/DeepSeek-V3.1
Parameters
685B total, 37B active
Base model
deepseek-ai/DeepSeek-V3.1-Base
Developer country
China
Training compute
3.6×10²⁴ FLOP

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel tools
  • Structured output
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messages
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Price history

Atom feed

No change since 19 Oct 2026. The cheapest direct price has been $0.19 in / $0.71 out per 1M tokens at TokenGo on every data refresh since then.

Tracked from 19 Oct 2026, the earliest refresh this model's headline price can be rebuilt from. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON

Cost calculator

Loading endpoints…

Similarly priced models

Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).

ModelBlended/1MIn/1MOut/1MContextvs DeepSeek V3.1
Seed 1.6 VisionByteDance Seed$0.286$0.114$1.14256K+1%
Gemma Sea Lion V4 27B ItAI Singapore$0.28$0.24$0.48131K−1% cheaper
Qwen-VL MaxAlibaba (Qwen)$0.288$0.23$0.58131K+2%
Seed 1.6 VisionByteDance Seed$0.292$0.12$1.15256K+3%
Mercury 2.5Inception$0.292$0.20$0.75260K+3%
deepseek-v3-0324DeepSeek$0.295$0.20$0.77164K+4%
Doubao Seed 2.0 LiteByteDance Seed$0.267$0.146$0.874256K−6% cheaper
Nemotron Nano 12B v2 VLNVIDIA$0.267$0.20$0.60131K−6% cheaper

More from DeepSeek

Newest DeepSeek models in the catalogue. All DeepSeek models

ModelReleasedContextListed price
DeepSeek V4 Flash2026-10-171.05Mfrom $0.07
DeepSeek V4.1 Flash 10172026-10-171Mfrom $0.08
DeepSeek V4 Flash Vision Exp2026-10-171.05Mfrom $0.14
DeepSeek V4.1 Flash2026-09-101.05Mfrom $0.09
DeepSeek V4 Pro 08132026-08-121Mfrom $0.88
DeepSeek V4 Flash Latest2026-07-311.05Mfrom $0.04
DeepSeek Pro Latest2026-07-061Munpriced
DeepSeek Latest2026-05-031.05M$0.145 via NanoGPT
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model