DeepSeek V4 Pro
DeepSeek V4 Pro is a reasoning model from DeepSeek released on Apr 24, 2026. It reads text and writes text, with a 1.05M token context window and up to 16K tokens per reply.
Show moreShow less
It costs $1.74 per million input tokens and $3.48 per million output tokens. Cached input bills at $0.145, 92% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
52 providers serve it, including Hugging Face, Vercel AI Gateway and Deep Infra. The lowest input price is $0.435 per million tokens at Hugging Face.
On the Artificial Analysis Intelligence Index it scores 36, which places it at number 21 among the 43 models I track with independent scores.
- Modalities
- In / out price
- $1.74 / $3.48 per 1M
- Context
- 1.05M
- Max output
- 16K
- Released
- Apr 24, 2026
- Knowledge cutoff
- May 2025
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
DeepSeek V4 Pro pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $1.74 / 1M tokens | |
|---|---|---|
| Output | $3.48 / 1M tokens | |
| Cached input (read) | $0.145 / 1M tokens | 92% off input |
DeepSeek V4 Pro providers
52 providers serve it, including Hugging Face, Vercel AI Gateway and Deep Infra. The lowest input price is $0.435 per million tokens at Hugging Face. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| DeepSeek First party | $0.66 | $1.98 | $0.022 | 1M | 393K |
| Hugging Face | $0.435 | $0.87 | $0.0036 | 1.05M | 393K |
| Vercel AI Gateway | $0.66 | $1.98 | $0.022 | 1M | 384K |
| Deep Infra | $1.30 | $2.60 | $0.10 | 1.05M | 16K |
| Cloudflare Workers AI | $1.32 | $3.96 | $0.044 | 1.05M | 1.05M |
| Together AI | $1.32 | $3.96 | $0.13 | 1.05M | 384K |
| Volcengine Ark | $1.34 | $4.01 | $0.0445 | 1M | 384K |
| SiliconFlow | $1.50 | $3.13 | $0.135 | 1M | 384K |
| Novita AI | $1.60 | $3.20 | $0.135 | 1.05M | 393K |
| Azure | $1.74 | $3.48 | – | 1M | 384K |
| Baseten | $1.74 | $3.48 | $0.145 | 1.05M | 262K |
| Nebius Token Factory | $1.75 | $3.50 | $0.15 | 1.05M | 1.05M |
Showing 12 of 52 providers: the lab first, then the major clouds, then the cheapest resellers.
What DeepSeek V4 Pro costs per month
Pick a workload close to yours or type your own volumes.
Independent benchmarks
Measured by third parties, not reported by DeepSeek. Each links to its source and shows the date I checked it.
A composite of 10 independent evaluations (agents 30%, coding 20%, scientific reasoning 20%, general 30%), run by Artificial Analysis on each model, version 4.3.2.
Artificial Analysis, checked Oct 10, 2026
Human preference: people compare two anonymous answers and pick the better one. Ratings from the Text Arena overall board, style control on.
Arena (formerly LMArena), checked Oct 10, 2026
Abstract reasoning on visual puzzles the model has not seen, semi private set. Hard to memorise, so it tracks reasoning more than knowledge.
ARC Prize, checked Oct 10, 2026
Expert level questions across many fields, no tools allowed. The Diamond set is 1,000 questions. Few models are on it yet.
Scale Labs, checked Oct 10, 2026
Median output tokens per second measured by Artificial Analysis on the provider API, for the same model setting as its index score.
Artificial Analysis, checked Oct 10, 2026
Benchmarks DeepSeek reports (7)
- hle-no-tools (HLE without tools)42.7%
- hle-with-tools (HLE with tools)60%
- terminal-bench-2.1 (Terminal Bench 2.1)87.9%
- deepswe (DeepSWE)62.7%
- toolathlon-verified (Toolathlon-Verified)74.1%
- nl2repo-bench (NL2Repo)61.5
- gpqa-diamond (GPQA Diamond (Pass@1), Max reasoning effort, "DS-V4-Pro" column of the V4.1-Flash comparison table)92.4%
Labs pick their own settings and harnesses, so compare these only within one lab.
Supported request parameters
What you can set when you call DeepSeek V4 Pro through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning - Temperature
temperature
Alternatives to DeepSeek V4 Pro
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 44.8
Reads text. Tool calling, structured output, reasoning. Served by 68 providers.
by z-aiAug 14, 20261M context$1.40/M input tokens$4.40/M output tokens68 providers
- Index 48.1
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 13 providers.
by metaSep 2, 20261.05M context$1.25/M input tokens$4.25/M output tokens13 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 15 providers.
by metaAug 5, 2026$1.25/M input tokens$4.25/M output tokens15 providers
- 200K context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 36 providers.
by anthropicOct 1, 2025$1/M input tokens$5/M output tokens36 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 29 providers.
by x-aiApr 17, 2026$1.25/M input tokens$2.50/M output tokens29 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 11 providers.
by x-aiMar 9, 2026$1.25/M input tokens$2.50/M output tokens11 providers
More from DeepSeek
- 1.05M context
Reads text and images. Tool calling, reasoning.
by deepseekOct 13, 2026$0.15/M input tokens$0.60/M output tokens
- Index 39.5
Reads text and images. Tool calling, structured output, reasoning. Served by 56 providers.
by deepseekSep 10, 20261M context$0.15/M input tokens$0.60/M output tokens56 providers
- 1.05M context
Reads text and images. Tool calling, structured output, reasoning. Served by 14 providers.
by deepseekAug 21, 2026$0.44/M input tokens$1.32/M output tokens14 providers
- 1M context
Reads text. Tool calling, structured output, reasoning.
by deepseekAug 2, 2026$0.05/M input tokens$0.16/M output tokens
- 1.05M context
Reads text. Tool calling, structured output, reasoning. Served by 48 providers.
by deepseekJul 31, 2026$0.14/M input tokens$0.28/M output tokens48 providers
- 1.05M context
Reads text. Tool calling, structured output, reasoning.
by deepseekMay 3, 2026$0.48/M input tokens$1.98/M output tokens
DeepSeek V4 Pro questions
How much does the DeepSeek V4 Pro API cost?
$1.74 per million input tokens and $3.48 per million output tokens, with cached input at $0.145. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of DeepSeek V4 Pro?
1,048,576 tokens of input, and it can write up to 16,384 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve DeepSeek V4 Pro?
52 providers serve it, including Hugging Face, Vercel AI Gateway and Deep Infra. The lowest input price is $0.435 per million tokens at Hugging Face. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does DeepSeek V4 Pro support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is DeepSeek V4 Pro open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was DeepSeek V4 Pro released?
Apr 24, 2026, with training data up to May 2025.
How good is DeepSeek V4 Pro compared with other models?
It scores 36 on the Artificial Analysis Intelligence Index and 1465 on the Arena text leaderboard. Benchmarks are a shortlist, not a verdict: test the top two or three candidates on your own tasks before you commit.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. Independent scores from my hand checked rankings, sources linked above. The summary is written from these facts.
Building on DeepSeek V4 Pro?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting