Scheduled for retirement on Mar 30, 2027. Still available at the prices below until then.

R1

DeepSeekReleased Jan 1, 2025KnowledgeJul 2024

Tool use Reasoning Prompt caching Structured output

Compare R1 Count tokens for R1

Context

164K

Max output

164K

Serving providers

Cheapest input

$0.40 /1M

On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis

Speed & latency

Output speed

152 t/s

tokens / second

Time to first token

1.09s

latency

Headline indices

Intelligence Index

11.4

of 100

Individual benchmarks · click a row for effort variants

Benchmark	Best score	Effort	Cost / task
ARC-AGI-2ARC Prize did not report this score in its latest run on Oct 14, 2026	1%	—	—
Automation Bench	0.0	default	—
CritPt	1%	default	—
GDPval (normalized)Frozen Aug 18, 2026	0%	default	—
GPQA Diamond	71%	default	—
Humanity's Last Exam	9%	default	—
IFBench	39%	default	—
LiveCodeBench	62%	default	—
Long-Context Reasoning	58%	default	—
Omniscience	-32.2	default	—
Omniscience Accuracy	0.3	default	—
Omniscience Non Hallucination	0.1	default	—
SciCode	38%	default	—
Terminal Bench40	0	default	—
TerminalBench Hard	6%	default	—
TerminalBench v2.1	19%	default	—
τ-bench Banking	6%	default	—
τ²-bench	11%	default	—

Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $0.40 to $5.00 per 1M tokens across 14 providers, so the dearest route costs 1150% more than the cheapest for the same model.

Serving provider

Input /1M

Output /1M

Endpoints

HyperbolicCheapest

$0.40

Standardhyperbolic/deepseek-ai/DeepSeek-R1

Component	Unit	Standard
Text input	/1M tok	$0.40
Text output	/1M tok	$0.40

DeepSeek

$0.55

$2.19

DeepInfra

$0.70

$2.40

OpenRouter

$0.70

$2.50

Nebius

$0.80

$2.40

Azure

$1.35

$5.40

Amazon Bedrock

$1.35

$5.40

Snowflake

$1.35

$5.40

SambaNova is dearest at $5.00 / $7.00

Price history

listed seller prices, input and output per 1M tokens

Input Output

Input down 70% since first tracked

Cost calculator

estimate your monthly spend on this model

Input tokens / call

Output tokens / call

Calls / month

Serving provider

$112

estimated / month

Model IDs

copy the exact identifier for your platform

hyperbolic/deepseek-ai/DeepSeek-R1deepseek/deepseek-r1deepinfra/deepseek-ai/DeepSeek-R1deepseek/deepseek-r1nebius/deepseek-ai/DeepSeek-R1azure_ai/deepseek-r1snowflake/deepseek-r1deepseek.r1-v1:0deepseek/deepseek-r1fireworks_ai/accounts/fireworks/models/deepseek-r1together_ai/deepseek-ai/DeepSeek-R1replicate/deepseek-ai/deepseek-r1novita/deepseek/deepseek-r1sambanova/DeepSeek-R1

Frequently asked questions

R1 pricing, context and availability

Is R1 still available?

Yes. R1 is scheduled for retirement on 2027-03-30.

How much does R1 cost?

R1 costs $0.40 per 1M input tokens from Hyperbolic, and $0.40 per 1M output tokens from Hyperbolic. Across 14 serving providers, input prices range from $0.40 to $5.00 per 1M tokens.