AI Model Watch
Models / DeepSeek

deepseek-reasoner (legacy alias)

Deprecated

Legacy model-name alias, NOT a separate model. Official docs: 'deepseek-chat & deepseek-reasoner will be fully retired and inaccessible after Jul 24th, 2026, 15:59 (UTC Time). (Currently routing to deepseek-v4-flash non-thinking/thinking).' deepseek-reasoner = THINKING mode of deepseek-v4-flash. Exact retirement timestamp: 2026-07-24 15:59 UTC. Replacement: use explicit name deepseek-v4-flash (thinking mode). Pricing shown matches deepseek-v4-flash since it routes there. This alias historically mapped to DeepSeek-R1 / V3-series thinking; as of the V4 Preview it routes to V4-Flash thinking.

deepseek-reasoner (legacy alias) by DeepSeek costs $0.14 per 1M input tokens and $0.28 per 1M output tokens ($0.175/1M blended), with a 1M (1.000.000-token) context window. It is deprecated, shutting down 24 Jul 2026; the recommended replacement is DeepSeek-V4-Flash. Its weights are publicly downloadable, so it can be self-hosted on your own infrastructure.

Last verified: 13 Aug 2026 · sourced from official provider documentation

Lifecycle warning

This model is deprecated. Scheduled shutdown: 24 Jul 2026. Recommended migration: DeepSeek-V4-Flash.

Read the deepseek-reasoner (legacy alias) migration guide → replacement & cheapest alternatives

Provider
DeepSeek
Status
Deprecated
Input price
$0.14 / 1M tokens
Output price
$0.28 / 1M tokens
Cached input
$0.003 / 1M tokens
Blended price
$0.175 / 1M tokens
Context window
1.000.000 tokens (1M)
Max output
384.000 tokens
Modality
text
Open weights
Yes — self-hostable
Knowledge cutoff
—
Released
—
API string
deepseek-reasoner

Source: DeepSeek official documentation ↗

See also

Explore more

All DeepSeek models→

Prices, context windows and lifecycle status for every DeepSeek model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

deepseek-reasoner (legacy alias) — questions & answers

How much does deepseek-reasoner (legacy alias) cost?

deepseek-reasoner (legacy alias) is priced at $0.14 per 1M input tokens and $0.28 per 1M output tokens ($0.175/1M blended at a 3:1 input-to-output ratio), with cached input at $0.003 per 1M tokens.

What is the context window of deepseek-reasoner (legacy alias)?

deepseek-reasoner (legacy alias) has a 1.000.000-token context window (1M), with up to 384.000 output tokens per request.

Is deepseek-reasoner (legacy alias) being deprecated or retired?

deepseek-reasoner (legacy alias) is deprecated. Its scheduled shutdown date is 24 Jul 2026. The recommended migration is DeepSeek-V4-Flash.

Does deepseek-reasoner (legacy alias) support image or vision input?

Our catalog lists deepseek-reasoner (legacy alias)'s modalities as text; image/vision input is not among them.

Can I self-host deepseek-reasoner (legacy alias)?

Yes — deepseek-reasoner (legacy alias) is an open-weight model: its weights are publicly downloadable, so you can run it on your own infrastructure (subject to its license) instead of only calling DeepSeek's API.

What is the API model string for deepseek-reasoner (legacy alias)?

The API model identifier for deepseek-reasoner (legacy alias) is "deepseek-reasoner" when calling DeepSeek's API.