DeepSeek-R1

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.

MIT licensed: Distill & commercialize freely!

deepseek/deepseek-r1

Organization: DeepSeek
Family: deepseek-thinking
Providers: 12
Context: 128,000
Output limit: 32,768
Knowledge: 2024-07
Release: 2025-01-20
Updated: 2025-05-29
Weights: Open
Input: text
Output: text
Capabilities: Tools, Reasoning, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

13 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Amazon Bedrock	us.deepseek.r1-v1:0	128,000	32,768	$1.35 / $5.40	Yes	No	—	View
Amazon Bedrock	deepseek.r1-v1:0	128,000	32,768	$1.35 / $5.40	Yes	No	—	View
Cloudflare Workers AI	@cf/deepseek-ai/deepseek-r1-distill-qwen-32b	80,000	80,000	$0.497 / $4.881	Yes	No	No	View
Eden AI	deepinfra/deepseek-ai/DeepSeek-R1	163,840	32,768	$0.70 / $2.40	Yes	Yes	No	View
Hugging Face	deepseek-ai/DeepSeek-R1	64,000	32,768	$0.70 / $2.50	Yes	Yes	Yes	View
Kilo Gateway	deepseek/deepseek-r1	64,000	16,000	$0.70 / $2.50	Yes	Yes	No	View
Melious	deepseek-r1-0528	164,000	32,768	$0.69552 / $2.78208	Yes	Yes	—	View
Merge Gateway	deepseek/deepseek-r1	163,840	40,960	$1.35 / $5.40	Yes	No	No	View
NanoGPT	deepseek-r1	128,000	8,192	$0.40 / $1.70	Yes	Yes	No	View
Novitavia OpenRouter	deepseek/deepseek-r1 fp8	64,000	16,000	$0.70 / $2.50	Yes	Yes	No	View
Snowflake Cortex	deepseek-r1	128,000	32,768	— / —	Yes	Yes	—	View
TensorX	deepseek/deepseek-r1-0528	164,000	8,192	$0.66 / $2.60	Yes	Yes	—	View
Vercel AI Gateway	deepseek/deepseek-r1	128,000	32,768	$1.35 / $5.40	Yes	No	—	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.40Per 1M input tokens

Output from$1.70Per 1M output tokens

Available offers13Across 12 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 1 lowest-priced configuration

InputOutput

Novitanovita/fp8

$0.70$2.50

deepseek/deepseek-r1Observed Oct 4, 2026, 11:31 AM UTC

Input: $0.70
Output: $2.50

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Novitanovita/fp8	$0.70	$2.50	—	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

Novitanovita/fp8

1,155.5–7,720.98 ms

All latency percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
Novitanovita/fp8	1,155.5 ms	1,476.25 ms	2,094.7 ms	7,720.98 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

Novitanovita/fp8

25–47 t/s

All throughput percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
Novitanovita/fp8	25 t/s	35 t/s	40 t/s	47 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 1 endpoint

Endpoint5 minutes30 minutes24 hours

Novitanovita/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

deepseek/deepseek-r1Observed Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 30

Coding

24.6

Agentic

1.1

Intelligence

11.4

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation	Configuration	Source	Results	Details
Composite indices	DeepSeek R1 (Jan '25)deepseek/deepseek-r1	Artificial Analysis	Intelligence 11.4 · Coding 24.6 · Agentic 1.1	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	deepseek/deepseek-r1	2–9 turns	$0.041355	Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

deepseek/deepseek-r1Observed Oct 4, 2026, 11:31 AM UTC

Context: 64,000
Maximum output: 16,000
Tokenizer: DeepSeek
Input: text
Output: text
Moderation: No
Instruction format: deepseek-r1
Knowledge cutoff: 2024-07-31
Added to OpenRouter: 2025-01-20

Base URLhttps://openrouter.ai/api/v1

Model IDdeepseek/deepseek-r1

Version IDdeepseek/deepseek-r1

Weights IDdeepseek-ai/DeepSeek-R1

Reasoning

Required: Yes
Enabled by default: Not reported
Default effort: —
Supported efforts: —

Supported parameters

frequency_penalty
include_reasoning
max_tokens
presence_penalty
reasoning
repetition_penalty
response_format
seed
stop
temperature
tool_choice
tools
top_k
top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does DeepSeek-R1 cost?

Listed rates start at $0.40 per million input tokens and $1.70 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer DeepSeek-R1?

There are 13 cataloged offers across 12 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 128,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Resources

Hugging Face ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · 0f03ab2ae876
Sep 12, 2026 · 2301231b2d5c