Frontier-class open-weight models at commodity prices — plus an off-peak window that halves them again. Real per-million-token rates, a calculator for your workload, and the comparison against closed rivals.
| MODEL | INPUT $/1M | CACHED IN | OUTPUT $/1M | BLENDED | CONTEXT | YOUR COST |
|---|---|---|---|---|---|---|
DeepSeek V4 Pro deepseek-v4-pro · off-peak −50% | $1.32 | $0.044 | $3.96 | $1.98 | 1M | $3.30 |
DeepSeek V4.1 Flash deepseek-flash · off-peak −50% | $0.30 | $0.006 | $1.20 | $0.525 | 1M | $0.90 |
USD per 1M tokens from DeepSeek’s official pricing page as of October 16, 2026. Blended assumes a 3:1 input:output ratio. Get keys at the DeepSeek console.
DeepSeek keeps the menu short: V4 Pro, the frontier reasoning model, at $1.32 input / $3.96 output per 1M tokens with a 1M context, and V4.1 Flash — released September 10, cheaper than the V4 Flash it replaced — at $0.30 / $1.20 for volume work. V4 Pro is text-only; V4.1 Flash adds image input. Both ship open weights, so you can also self-host or buy them from any inference provider.
The signature mechanic is the off-peak discount, and it got much wider in September: peak hours are now just 01:00–04:00 and 06:00–10:00 UTC on weekdays, and everything else — evenings, nights, weekends, and Chinese public holidays — bills at half price. Schedule batch jobs, evaluations, and backfills into that window and you get a batch-API-grade discount without a batch API — V4 Pro effectively drops to $0.66 / $1.98.
Cache hits are the other outlier: repeated prompt prefixes bill at $0.044 per 1M tokens on V4 Pro — about a thirtieth of the fresh rate — and just $0.006 on V4.1 Flash, a fiftieth. Agents with long stable system prompts run absurdly cheap here.
DeepSeek V4 Pro costs $1.32 input / $3.96 output per 1M tokens, and V4.1 Flash $0.30 / $1.20 — with everything at half price outside weekday peak hours and cache hits at a thirtieth to a fiftieth of the fresh input rate.
Peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday. Requests processed at any other time — including all weekend and on Chinese public holidays — bill at 50% of the standard rate, input and output alike. There is nothing to configure — the discount applies automatically based on when the request lands. Time-shift bulk workloads into the window and your effective price halves.
V4 Pro sits in the frontier class on reasoning and coding benchmarks while costing a fraction of closed rivals — around $1.98/1M blended versus $4 for GPT-6 Sol and $8 for Claude Opus 5.5. The trade-offs: text-only input, and you are buying from a Chinese lab, which matters for some compliance postures.
Yes — the V4 models ship open weights, so you can run them on your own GPUs or through any inference provider. The prices on this page are DeepSeek’s first-party API rates, which are usually hard to beat at small scale once you count GPU costs.
V4.1 Flash now accepts images; V4 Pro is still text-only, and neither takes audio or video. If your workload needs audio or video input at a similar price point, look at MiMo-V2.6-Flash, Qwen3.8-Omni-Flash, or Gemini Flash-Lite — the matchup table below includes the closest alternatives.
Also see: OpenAI API pricing · Claude API pricing · Gemini API pricing · Grok API pricing · Kimi API pricing · GLM API pricing · MiniMax API pricing · MiMo API pricing · all 68 models
ReqKey gives every key a credit balance — validate, deduct, enforce limits, and watch per-consumer DeepSeek spend in real time.