DeepSeekOpen-weight·64K context·671B params·MIT

R1deepseek/deepseek-r1

Name: R1 API
Brand: DeepSeek
Availability: InStock

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....

Cheapest blended:$1.15 / 1M tokenson DeepSeek · 2 providers listed

Pricing across providers

Sort by:

Provider	Input /1M	Output /1M	Blended /1M	Latency p50	Format	Freshness	Action
DeepSeek deepseek-r1	$0.70	$2.50	$1.15	920ms	OpenAI-compatible	Needs 27d ago	Try →
Together.ai deepseek-ai/DeepSeek-R1	$3.00	$7.00	$4.00	350ms	OpenAI-compatible	Price 1mo ago	Try →

Affiliate disclosure: We may earn a commission from qualified signups. Pricing independence is enforced at the data layer — see our Editorial Independence Policy.

Works with

Point any of these clients at a hosting's base URL — they all speak at least one of this model's endpoint protocols (OPENAI_COMPATIBLE).

Capabilities

reasoning
math
coding
chain_of_thought

Languages: en, zh

Benchmarks

MMLU5-shot · official · source
90.3%
HumanEval0-shot pass@1 · official · source
89.1%

Code samples

Example using DeepSeek — the cheapest hosting for this model as of last verification. Swap base_url and model to use a different provider from the matrix above.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.deepseek.com/v1",
)

response = client.chat.completions.create(
    model="deepseek-r1",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Technical specs

Context: 64K
Max output: 16K
Parameters: 671B
Release: 2025-01-20
Training cutoff: 2024-10-01
License: MIT

Paper →Hugging Face →

Similar models

Compare with

R1 vs DeepSeek V3.1
Comparison planned — not yet published
R1 vs DeepSeek V3
Compare side-by-side →
R1 vs GLM 5
Comparison planned — not yet published

Frequently asked

How much does R1 cost?+

The cheapest public hosting is $1.15 per 1M blended tokens on DeepSeek. 2 total providers are listed above with per-input / per-output / cached pricing.

How do I access R1 from outside China?+

All hostings listed above support global access. The official API (e.g. api.deepseek.com, dashscope-intl.aliyuncs.com) accepts international credit cards and does not require a Chinese mobile number. For privacy-sensitive workloads, third-party aggregators like Together.ai host the model on US/EU infrastructure.

Is R1 open-source? Can I fine-tune it?+

Yes. R1 is open-weight under the MIT license. Weights are available on Hugging Face for local inference, fine-tuning, and commercial use (see license for specific terms).

Is R1 OpenAI-compatible?+

Most listed hostings expose an OpenAI-compatible API, so you can point an existing openai SDK client at the Provider's base_url and use the Provider's model name. See the Code Samples above for a copy-pasteable example.

What's the maximum context window for R1?+

The model supports up to 64,000 tokens of context (input + output). Some hosted versions may impose a smaller limit — check the "Context" column in the pricing matrix for each provider.