DeepSeek V4 Pro pricing and specs

Pricing per 1M tokens

Note: Prices are DeepSeek's peak rates. Off-peak rates are half of peak (input 0.66, output 1.98, cache hit 0.022 per 1M): peak hours are 01:00-04:00 and 06:00-10:00 UTC Monday to Friday excluding Chinese public holidays, all other hours (weekends and Chinese public holidays in full) are off-peak. input is the cache-miss price and cache read the cache-hit price; no separate cache write or batch price is published. Previous generation, still sold: the 2026-09-10 launch post said deepseek-v4-pro would route to V4.1-Flash from 2026-09-14, but the change log entry for the same date says DeepSeek will keep serving V4 Pro after 2026-09-14 with billing unchanged, and the pricing page still lists it. Current API version is DeepSeek-V4-Pro-0813 (GA 2026-08-13); release date is the V4 Preview API launch on 2026-04-24 per the change log. Text only (vision not supported). Context stated as 1M (exact token count not given); max_tokens upper bound 384K (393216) per the Chat Completions API reference. Hugging Face repo (MIT) holds the preview weights and does not mention the 0813 GA checkpoint. deepseek/deepseek-v4-pro-0813 is also listed on the gateway.

Specs

Context window

1,000,000 tokens

Max output

393,216 tokens

Release date

April 24, 2026

Provider

DeepSeek

API model id

deepseek-v4-pro

Vercel AI Gateway id

deepseek/deepseek-v4-pro

Weights

Open weights

License

MIT

Weights download

huggingface.co

What DeepSeek V4 Pro costs in practice

Worked from the standard list rates above, with the math shown so you can swap in your own token counts.

Compare with

Compare

Side-by-side pages with both models' prices, specs, cost examples and like-for-like benchmark rows.

• DeepSeek V4 Pro vs Gemini 4 ArgonOpen weights vs closed
• DeepSeek V4 Pro vs Mistral Large 4Similar price, same tier
• DeepSeek V4 Pro vs GPT-6.1 SolOpen weights vs closed
• DeepSeek V4 Pro vs Claude Sonnet 5.5Open weights vs closed
• DeepSeek V4 Pro vs Claude Opus 5.5Open weights vs closed
• DeepSeek V4 Pro vs Gemini 3.8 FlashSimilar price, same tier
• DeepSeek V4 Pro vs GLM-5.3Similar price, same tier
• DeepSeek V4 Pro vs Grok Build 0.1Similar price, same tier
• DeepSeek V4 Pro vs Mistral Medium 3.5Similar price, same tier
• DeepSeek V4 Pro vs GPT-5.4 MiniSimilar price, same tier
• DeepSeek V4 Pro vs Kimi K2.7 CodeSimilar price, same tier

Related reading

• The Mid-Tier Shootout: GPT-5.4 vs Gemini 3.1 Pro vs DeepSeek V4 ProGPT-5.4 vs Gemini 3.1 Pro vs DeepSeek V4: pricing, benchmarks, context behavior, and license terms for the mid-tier models that carry most production traffic.
• DeepSeek V4.1-Flash-1017: Benchmarks vs Opus 5, Pricing, Switch?DeepSeek V4.1-Flash-1017 jumps 11 points on Terminal-Bench 4.0 at the same deepseek-flash price. Benchmarks vs Opus 5, K3, GLM-5.3 and when to switch.
• DeepSeek 4.1 Flash as a Daily Coding Model: Cache, Peak Hours and LimitsDeepSeek 4.1 Flash as a daily coding model: what a session costs, how peak hours double the bill, why caching matters, and where the subsidy argument holds.
• Where to Run DeepSeek V4.1 Flash Free and CheapDeepSeek V4.1 Flash replaced V4 Flash. Official API: $0.15 input, $0.60 output off-peak. OpenRouter hosts start near $0.05. MIT weights are on Hugging Face.
• DeepSeek V4 Flash Vision Exp: Experimental Vision, Limits, and How to Run It in OpenCodeDeepSeek V4 Flash Vision Exp guide: supported image formats, three input methods, the 384-token per-image cap, and how to run it in OpenCode today.
• We Read DeepSeek Harness: What 453K Lines of Agent Runtime Actually SayDeepSeek Harness (dsh) code read: a 453K-line plugin runtime on a vendored Cordis fork, three patterns worth stealing, and the gaps the launch does not mention.

FAQ