How much does prompt caching save on DeepSeek-R1?

Prompt caching on DeepSeek-R1 bills cached input at $0.14 per 1,000,000 token instead of $0.55 per 1,000,000 token for standard input. The saving applies to the cached prefix only; the rest of the request is billed normally.

What is the max output length for DeepSeek-R1?

DeepSeek-R1 returns up to 16,000 output tokens per request, within a 64,000-token context window. Cap the response with the max_tokens parameter so a single call cannot run past your budget.

Does DeepSeek-R1 have a free tier?

DeepSeek-R1 is billed per use and the record publishes no free-tier allowance. The current published rates are input $0.5500 per 1M tokens and output $0.5500 per 1M tokens. Trial credit or promotional quota is tied to your account rather than to the model, so check the console before planning around a free tier.

Can you call DeepSeek-R1 with the OpenAI SDK you already use?

Yes. DeepSeek-R1 is reachable through an OpenAI-compatible endpoint, so an existing OpenAI SDK client works after pointing the base URL at MixRoute and setting the model parameter to deepseek-r1 . Keep your current request and response handling.

When was DeepSeek-R1 released, and is it still maintained?

DeepSeek-R1 was released on 2025-01-20. Its catalog status is stable. Check the model page for deprecation notices before you build a long-lived integration on it.

Model detail

DeepSeek-R1

Provided by DeepSeek

Delisted Pay-as-you-go

DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120). MIT licensed: Distill & commercialize freely!

Model specs

Model ID: deepseek-r1

Context length: 64K
Max output: 16K
I/O modalities
Released: 2025-01

API endpoints

One MixRoute gateway, OpenAI-compatible

OpenAI-compatible /v1/chat/completions POST

Pricing

Flat rate, unit: /1M Tokens

Input

$0.5500 /1M Tokens

Completion

$0.5500 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

DeepSeek R1 is here: Performance on par with OpenAI o1

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model & technical report.

What should you check before using it?

64,000 context, 16,000 output tokens

Model type: text. Verify supported features and quotas with the provider documentation. Knowledge cutoff: 2024-07-31. Released 2025-01-20.

Why use it through MixRoute?

DeepSeek-R1 runs tools and structured output here

Tool calling and structured output run on that route as well. MixRoute serves DeepSeek-R1 on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID deepseek-r1 and re-run your integration tests.

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Tool calling

DeepSeek-R1 supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.

Structured output

DeepSeek-R1 can produce JSON-formatted output on demand.

EX response_format: { type: "json_schema" } forces valid JSON output.

Streaming

DeepSeek-R1 supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.

Prompt caching

DeepSeek-R1 supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.

OpenAI SDK

Call DeepSeek-R1 through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Input tokens Max per request 64K

Output tokens Max per request 16K

Requests / month

Cache hit rate –

This model has no cache-read price; caching is not counted

FAQ

Before switching production traffic to DeepSeek-R1, run a pilot on a representative slice of your traffic and check output quality, latency at peak concurrency, and cost per request. Verify the error and retry behaviour, and confirm the request limits you depend on match your plan.

Get started

01

Create an API key

Generate a key in the Console; one key calls every model.
02

Set the base URL

Fully OpenAI SDK-compatible; just swap the URL to connect.

https://api.mixroute.ai/v1
03

Specify the model ID

In the request's model field, enter:

deepseek-r1

Create an API key

New users get $5 in free credits

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs