OverpayingForAIPricing desk

Lesson 2 of 8 · 10 min read · Beginner → Intermediate

DeepSeek models explained

The V3, V4 and R1 lines, what each is for, context windows, and a live price ladder so you can see what the choice costs.

In this lesson you will

  • Name the current DeepSeek model families and what each is optimised for
  • Choose between a chat model and a reasoner model for a given task
  • Read the live price ladder and translate it into a cost per request
  • Know what context window sizes mean for your bill

DeepSeek's line-up is small compared with OpenAI's, which makes it easier to learn. There is a chat family that gets a new version number every few months, a reasoner family that started with R1, and a handful of variants — Flash, Pro, Terminus, distilled models — that sit alongside. This lesson maps them and shows what each costs on the official API and on third-party hosts.

Current DeepSeek models: $ per 1M tokensLive from the OverpayingForAI catalogue · last verified 2026-09-04 · sorted by output priceInputOutputDeepSeek R164K context$0.7$2.5R1 0528164K context$0.5$2.15DeepSeek V4 Pro1.0M context$1.01$2.02DeepSeek V4 Pro 08131.0M context$0.579$1.74DeepSeek V3.1164K context$0.55$1.65DeepSeek V3.1 Terminus164K context$0.27$1DeepSeek V3.2164K context$0.269$0.4DeepSeek V4 Flash 07311.3M context$0.065$0.18Batch, fast-mode and free variants are excluded. Prices change; the figure re-draws from the catalogue on every build.
Figure 1.Live prices from our catalogue. Bars show input and output cost per 1M tokens. Rows labelled with a date suffix are specific checkpoints served by third-party hosts.

The chat line: V3 to V4

The chat models are what you get by default in the app and as deepseek-chat on the API. DeepSeek V3 was the breakthrough release; V3.1 and V3.2 refined it, and V3.1 Terminus is a stability-focused checkpoint. The V4 family splits into V4 Flash, a small, very cheap model for high-volume work, and V4 Pro, the larger flagship for harder tasks.

At the time of writing our catalogue shows V4 Flash around $0.07–$0.09 per 1M input and roughly $0.18 per 1M output tokens depending on host, V3.2 at about $0.27 in and $0.40 out, and V4 Pro between roughly $0.58 and $1.01 in and $1.74 to $2.02 out depending on checkpoint and host. Those are all far below the closed-model flagships you see on /models.

The reasoner line: R1

DeepSeek R1 is the model that made reasoning models a mainstream topic. It is served as deepseek-reasoner on the official API, and the R1 0528 checkpoint is what most third-party hosts carry. In our catalogue R1 sits at roughly $0.50–$0.70 per 1M input and $2.15–$2.50 per 1M output tokens at the time of writing — still cheap in absolute terms, but note that output is five to six times the price of V3.2's output, and a reasoner produces a lot more of it.

Which DeepSeek model for which job (prices are live in the ladder above)
ModelAPI nameBest forWatch out for
DeepSeek V4 Flashdeepseek-chat (or host-specific id)Bulk summarising, classification, extraction, simple chatWeaker on hard reasoning; check quality on a sample first
DeepSeek V3.2deepseek-chatGeneral writing, coding, everyday assistant workSuperseded by V4 on some hosts; prices shift often
DeepSeek V4 Prodeepseek-chat (host id varies)Complex coding, long documents, agentic tasksRoughly 2–4x the price of V3.2; confirm you need it
DeepSeek R1 / R1 0528deepseek-reasonerMaths, logic puzzles, tricky debugging, planningLong hidden reasoning inflates output tokens and latency
R1 Distill Llama 70Bhost-specific idCheap reasoning on hosts that carry itNot an official DeepSeek endpoint; 8K context on some hosts

Context windows

Context window is how much text a model can hold at once, counting your prompt, any documents you paste, and the answer. Our catalogue lists the V3 line at about 164K tokens, R1 checkpoints between 64K and 164K, and the V4 family at roughly 1M tokens or more. One million tokens is around 750,000 words, enough for a full codebase or a shelf of reports.

Worked example: one task, three models

Suppose you need to classify 1,000 support tickets. Each request is about 2,000 input tokens (instructions plus ticket) and 500 output tokens (a structured label and a one-line reason). That is 2M input and 0.5M output tokens in total. Using the catalogue prices at the time of writing:

  • V3.2: 2 × $0.27 + 0.5 × $0.40 ≈ $0.74 for all 1,000 tickets.
  • V4 Pro 0813: 2 × $0.58 + 0.5 × $1.74 ≈ $2.03.
  • R1 0528: 2 × $0.50 + 0.5 × $2.15 ≈ $2.08 — and in practice more, because the reasoner will spend extra output tokens thinking about each ticket.

None of those numbers is scary, which is the point of DeepSeek. But the pattern is the one you will see everywhere in this course: a chat model is usually the right default, and you escalate to Pro or a reasoner only for the subset of requests that fail on the cheap model. Run your own numbers in the calculator.

Knowledge check

You need to summarise 50,000 short product reviews into one-line summaries. Which model should you try first?

Lesson FAQ

What is the difference between deepseek-chat and deepseek-reasoner?

deepseek-chat routes to the current chat model (V3/V4 line) and answers directly. deepseek-reasoner routes to the current reasoning model (R1 line), which generates a hidden chain of thought first. The reasoner costs more per request because that thinking is billed as output tokens.

Which DeepSeek model is the cheapest?

At the time of writing the V4 Flash checkpoints are the cheapest rows in our catalogue at well under $0.10 per 1M input tokens. Prices change, so check the live ladder on this page or the [DeepSeek pricing page](/pricing/deepseek-pricing).

Does DeepSeek have a 1M token context window?

Our catalogue lists the V4 family at roughly 1M tokens on the hosts we track. The V3 line and R1 sit around 164K. Confirm the limit on the specific host you use, because hosts sometimes serve a smaller window than the model supports.

Finished reading?

Mark it done to track your progress through the course.

Compare, calculate, decide — for DeepSeek

If our calculators helped you cut down on hidden AI wallet leaks, consider buying us a coffee. A tiny fraction of your savings keeps our pricing indexes updated daily.

Not sure which AI is cheapest for your use case? Find out in 30 seconds — no signup required.

AI cost intelligence

Stop overpaying for AI tools

Join the OverpayingForAI list for pricing updates, cheaper alternatives, and practical buying guidance.

Now tracking 50+ AI tools, models, platforms, subscriptions, coding tools, and automation products.

We use your email only for OverpayingForAI updates. Unsubscribe anytime.