DeepSeek V3.1
deepseek/deepseek-v3.1- DeepSeek
- Family · DeepSeek V3
- Released 21 Aug 2025
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context160K
Max output144K
Input / 1M$0.25
Output / 1M$0.953.8× input
Scores · standing
Intelligence13.7#187/489
Usage
Tokens / day7.0B▼ 3.3% 7d
Usage rank#101
Requests / day1.7M
Tool calls / req0.01
Per request · 30 days
Avg input2.6K0.2× median
Avg output1050.2× median
Cache hit40%0.6× median
Reasoning share6.3%0.1× median
Tool-call failures2.9%1.5× median
Consumption
Peak 8.2B 12 OctLow 4.7B 1 NovRank today #101
News & trends
5 mentions this week ▼ 37%DeepSeek V3 family · videos, posts, articles · 30 days
Trending · 14 days · DeepSeek V3 family
- What Did DeepSeek V3's $5.6 Million Cost Leave Out? #deepseek #nvidia #ai #mixtureofexperts1.8K views
- Best provider for deepseek v3.2?17 upvotes
- Free Claude Code CLI Setup: Use DeepSeek V3 & Gemini API (1-Click Windows Installer)29 views
News · latest from DeepSeek
- Tell HN: Mistrap Pro includes DeepSeek v4.1 Flash 1017docs.mistral.ai · 1 Nov
- Show HN: DeepSeek v4.1 Flash-1017 Safety Evaluationtwitter.com · 26 Oct
- DeepSeek V4 Pro 0813 vs Claude Fable 5 on DeepSWE: Cost, Coding, and RoutingTogether AI · 17 Aug
- DeepSeek-V4 Flash 0731 vs GPT-5.6 Luna on DeepSWE: Cost and CodingTogether AI · 6 Aug
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 5 providers, latest day
Output speed#108/33487 tok/s1.3× faster than median
Fastest provider95 tok/sbest of 5 providers
First token#1360.86 s1.2× quicker than median
#12 cheapest of 28 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Family progress
Intelligence Index
- Family releases21.5
Technical details
- Tokenizer
- DeepSeek
- Knowledge cutoff
- 2025-03-31
- License
- MIT
- Parameters
- 685B
- Moderation
- none
- Downloads · likes
- 271.4K · 864
Request parameters 19
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- min_p
+9 more
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
Interesting facts
- 2.3× the output room of similar models (147.5K against a 65.5K median).
- 2nd of 5 DeepSeek V3 models by tokens last month.
When to use
Best for
- Math and general knowledge questions
- Code generation for everyday tasks
- Open-weight self-hosted assistants
- Tool-calling with JSON output
Think twice for
- Image input (text-only)
- Terminal-style coding agents
- New builds where newer DeepSeek releases fit better
Research papers
- Ideological Stance Detection in a Low-Resource Language: Polarization in Bangladeshi Public vs Private University Discourse on Social Media3 Oct
- Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning26 Sep
- Mitigating Emergent Collusion in LLM Pricing Agents11 Sep
- RS-Claw-Evolution: Environment-Feedback-Driven Evolution for Lightweight Remote Sensing Agents in Long-Horizon Tasks6 Sep
- VPP: Virtual Pipeline Parallelism for Efficient Chunked Prefill in Long-Context LLM Inference27 Aug
- Reinforcement Learning on Benign Facts Amplifies Leakage of Memorized Private Data22 Aug
- PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents21 Jul
- Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts14 Jul
Same family
DeepSeek V3- 21.5
- 8.5
- 16.6
- 9.7
Alternatives
other vendors · similar capability- 11.6
- 13.1
- 18.2
- 15.6
Want DeepSeek V3.1 on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.