deepseek-v4-pro
deepseek The API that serves this model and sets the prices shown here. deepseek-v4-pro The model identifier to send in API requests. LLM Generates text from a prompt, so it can be compared with other LLMs on price and capability. Large The most capable general-purpose tier of a model family.Provider: DeepSeek
Nothing to act on today. The cost is the checking: someone has to remember to look again next month, and the month after. Coolhand watches this model for you and automatically updates your agents to the most compatible replacement the moment a retirement is announced — one less thing on your list, permanently.
Sticker prices & cost-per-token
List rates as published by DeepSeek, before any volume or enterprise discounts.
$0.66
$1.98
1,000,000 tokens
384,000
tokens per response (includes reasoning tokens)
Open weights (permissive license)
MIT
$0.022
$1.98
Tiered / volume pricing
| Condition | Input cost | Output cost | Notes |
|---|---|---|---|
| Mon–Fri 01:00–04:00, 06:00–10:00 UTC | $1.32 / 1M | $3.96 / 1M | DeepSeek peak hours. Chinese public holidays are off-peak but not modelled here. |
Get this data free
Want to stay updated on price changes on this model? Pull this data free (no API key required) here:
curl "https://coolhandlabs.com/api/v2/inference_apis?q%5Bmodel_eq%5D=deepseek-v4-pro&q%5Bsource_api_eq%5D=deepseek"Pricing History
No pricing history recorded yet.
History
Last change detected October 5, 2026 (3 days ago) by an automated scan.
| Date | Changed by | What changed |
|---|---|---|
| Sep 19, 2026 | Unknown | Initial record created |
Source
https://api-docs.deepseek.com/quick_start/pricingComparable models
No comparable models identified yet.
Reliability
No reliability incidents recorded in the last 90 days.
Frequently asked questions
deepseek-v4-pro (DeepSeek) costs $0.66 per 1M input tokens and $1.98 per 1M output tokens, as last published by DeepSeek.
deepseek-v4-pro has a context window of 1,000,000 tokens (the maximum combined input and output it can handle in a single request).
deepseek-v4-pro sits in the large size tier. Size tiers run from micro (small enough to run on a device) through small, medium and large to extra large (frontier flagships), and are assigned from the model's family, naming and limits rather than its price.
deepseek-v4-pro can generate up to 384,000 tokens in a single response. Reasoning (thinking) tokens count toward this limit.
deepseek-v4-pro accepts text as input and produces text as output, as recorded in the Coolhand catalog.
Yes — the weights of deepseek-v4-pro can be downloaded under the MIT license. Check the license terms for any limits on commercial use.
No, deepseek-v4-pro is currently active with no announced deprecation date.
Call GET https://coolhandlabs.com/api/v2/inference_apis?q[source_api_eq]=deepseek&q[model_eq]=deepseek-v4-pro — free, no API key required, and scoped to just this model since source_api and model together are unique. See https://coolhandlabs.com/docs for the full REST API reference.
Track LLM pricing and deprecations automatically.
Start free