DeepSeek · Rate Limits

Deepseek Rate Limits

DeepSeek does not publish fixed numerical rate limits. Instead, the API dynamically caps user concurrency based on current server load and returns HTTP 429 once a caller's concurrency ceiling is reached. There is no hard requests-per-minute or tokens-per-minute cap published on the public docs; sustained throughput is therefore best-effort and varies in real time. Inference connections that have not begun streaming within ten minutes of being accepted are closed by the server.

Deepseek Rate Limits is the machine-readable rate-limit profile for DeepSeek on the APIs.io network, in the API Commons Rate Limits shape.

It captures 2 rate-limit definitions, measuring concurrent_requests and seconds_to_first_token.

An exhausted limit returns HTTP 429.

This profile was written by API Evangelist and has not been verified against a page the provider published; treat every limit as unconfirmed until a dated transcription replaces it.

The profile also includes 4 backoff/retry policies defined and response codes documented for throttled and serviceUnavailable.

Tagged areas include AI, Artificial Intelligence, Chat, LLM, and Large Language Models.

2 Limits Exhausted: HTTP 429
Method: generated, dated 2026-05-05.
Written by API Evangelist on 2026-05-05 and not verified against a page the provider published. Treat every limit as unconfirmed until a dated transcription replaces it.
View Source
AIArtificial IntelligenceChatLLMLarge Language ModelsRate Limiting

Limits

Dynamic concurrency cap api-key
concurrent_requests
dynamic — varies with current server load
DeepSeek throttles by concurrent in-flight requests rather than RPS. The exact ceiling is not published and shifts with load.
Inference connection timeout connection
seconds_to_first_token · second
600
If inference does not start within 10 minutes after the connection is accepted, the server closes the connection. Affects very long queues during load spikes.

Policies

Backoff Strategy
On HTTP 429, callers should back off and retry with exponential delay and jitter. DeepSeek does not document a Retry-After header, so clients must use their own retry budget.
Keep-Alive Signaling
While a request is queued the server returns empty lines (non-streaming) or SSE keep-alive comments (streaming). Clients must tolerate these placeholder frames.
Connection Lifetime
Drop and re-establish connections that have been idle for more than 10 minutes without any token output, since the server will close them.
Concurrency Sizing
Because limits are dynamic, callers should target a configurable concurrency budget per API key and reduce parallelism when 429 responses spike.

Sources

Work with this as data

Every rate limit here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for rate limits

4 MCP tools reach this
  • find_rate_limitsBrowse and filter every rate limit in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This rate limit 
curl "https://apis.io/api/v1/rate-limits/deepseek-rate-limits"
All rate limits 
curl "https://apis.io/api/v1/rate-limits?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.