DeepSeek V3.1
4967°
Run this model
Offers / Ads
DeepSeek | 163,840 token context | $0.25/M input, $0.95/M output. DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docsOpens in new tab The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable…DeepSeek | 163,840 token context | $0.25/M input, $0.95/M output. DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docsOpens in new tab The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the DeepSeek V3-0324 model and performs well on a variety of tasks.
Guides for this model
Best local LLM by use case (October 2026): the right open model for every job
How much VRAM do I actually need for local AI?
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
DeepSeek V3.1 is a 671B mixture-of-experts model from DeepSeek that runs 37B parameters at inference time and supports both thinking and non-thinking modes in a single set of weights. Its thinking mode reaches quality comparable to DeepSeek R1 while responding faster, and its tool-calling and agent capabilities have been substantially improved over V3. At under a dollar per million output tokens it is a serious option for anyone running agentic or long-document pipelines on a budget.
Known for
- Hybrid thinking/non-thinking mode switchable via chat template, no separate model needed.
- Tool calling and agent workflows significantly improved over DeepSeek V3.
- 128K context window built through a two-phase long-context training process.
- Thinking-mode quality comparable to DeepSeek R1, with faster response times.
- Open weights available on Hugging Face; FP8 microscaling for efficient inference.
Watch out for
- 671B total parameters means local deployment requires serious hardware; most users will hit an API.
- Tool calling is supported in non-thinking mode only — you cannot combine structured tool use with reasoning mode.
- The chat template changed from V3; existing prompts and integrations may need updating.
Prompts to try
Multi-step code agent
You have access to a Python interpreter. Write a script that fetches the latest exchange rates for USD, EUR and GBP from a public API, calculates the cross rates for all three pairs, and prints a formatted table. Use tool calls to run each step, check the output, and fix any errors before returning the final result.
Hard reasoning puzzle
Five engineers join a project on different days: Monday through Friday. Alice joined before Bob. Carol joined the day after Dave. Eve joined on Wednesday. Bob did not join on Thursday. Dave joined earlier in the week than Carol but later than Eve. List each engineer's start day and show your reasoning step by step.
Long document extraction
I am pasting a lengthy contract below. Read it carefully and produce: (1) a one-paragraph plain-English summary of the main obligations of each party, (2) a bullet list of every deadline or notice period mentioned, and (3) any clauses that could create unexpected liability for the buyer. Flag anything ambiguous. [Paste contract text here]
Compare with
- DeepSeek Flash LatestAPI-only model1,048,576 token context · $0.04/M input, $0.68/M output
- DeepSeek V4 Flash LatestAPI-only model1,048,576 token context · $0.01/M input, $1.28/M output
- DeepSeek Pro LatestAPI-only model1,048,576 token context · $0.25/M input, $5.00/M output
- DeepSeek V4.1 FlashOpen-weights model1,048,576 token context · $0.04/M input, $0.68/M output
More text models from deepseek
Questions people ask
- Can I run DeepSeek V3.1 locally?
- The weights are open and available on Hugging Face, so yes — but the model is 671B parameters total, which demands substantial hardware to run at full precision; most people will use a quantized version or an API.
- What does DeepSeek V3.1 cost and what is the context window?
- Via API it is priced at $0.25 per million input tokens and $0.95 per million output tokens, with a 163,840-token context window.
- How is V3.1 different from DeepSeek V3 and DeepSeek R1?
- V3.1 adds a hybrid thinking mode (so one model covers both fast chat and step-by-step reasoning), improves tool calling and agent tasks, and extends the context to 128K through additional long-context training; in thinking mode it reaches quality comparable to R1 while being faster.
Captain's verdictA rare model that earns its place on both the budget shortlist and the agentic-workflow shortlist — the hybrid thinking mode is genuinely useful rather than a marketing checkbox.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
DeepSeek V3.1 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153