LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

DeepSeek-R1

deepseek·deepseek/deepseek-r1·GA·Open weights·deepseek-thinking series
Classic open reasoning model for transparent math, coding, and deliberate problem solving

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·D.Run (China)Gateway
$0.55 / $2.20
Blended $0.96 · 6× spread
Context
128,000
Output limit
8,192
Knowledge cutoff
2024-07
Released / updated
2025-01-20 / 2025-05-29
Capabilities
✓ Reasoning✓ Tool useStructured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Weights
Hugging Face

DeepSeek-R1 is offered by 15 providers on this page. Public prices are shown for 14 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is D.Run (China) at $0.55 / $2.20 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 6.0× across the providers that host it.

Median output speed is 159 tokens per second, with 1.02s to the first token.

The context window is 128,000 tokens at the reference host, but hosts report different limits, from 64,000 to 163,840, so the usable window depends on the provider you pick. It supports reasoning and tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-07.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed159 tok/s
TTFT1.02 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 15 providers14 with public prices

  • ProviderInput / Output
  • D.Run (China)Gateway
    $0.55 / $2.20
    Context 131,072 ⚠Output limit 32,000
  • Alibaba (China)First-party
    $0.57 / $2.29
    Context 131,072 ⚠Output limit 16,384deprecated
  • QiniuGateway
    $0.58 / $2.32
    Context 128,000Output limit 32,000deprecated
  • Eden AIGateway
    deepinfra/deepseek-ai/DeepSeek-R1
    $0.70 / $2.40
    Context 163,840 ⚠Output limit 32,768
  • Novita AIGateway
    deepseek/deepseek-r1-turbo
    $0.70 / $2.50
    Context 64,000 ⚠Output limit 16,000
  • Hugging FaceCloud
    deepseek-ai/DeepSeek-R1
    $0.70 / $2.50
    Context 64,000 ⚠Output limit 32,768
  • Cloudflare Workers AICloud
    @cf/deepseek-ai/deepseek-r1-distill-qwen-32b
    $0.50 / $4.88
    Context 80,000 ⚠Output limit 80,000deprecated
  • Amazon BedrockCloud
    us.deepseek.r1-v1:0
    $1.35 / $5.40
    Context 128,000Output limit 32,768deprecated
  • Amazon BedrockCloud
    deepseek.r1-v1:0
    $1.35 / $5.40
    Context 128,000Output limit 32,768deprecated
  • Merge GatewayGateway
    $1.35 / $5.40
    Context 163,840 ⚠Output limit 40,960
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
D.Run (China)Gateway$0.55$2.20——131,072 ⚠32,000
Alibaba (China)First-party$0.57$2.29——131,072 ⚠16,384deprecated
QiniuGateway$0.58$2.32——128,00032,000deprecated
Eden AI
deepinfra/deepseek-ai/DeepSeek-R1
Gateway$0.70$2.40——163,840 ⚠32,768
Novita AI
deepseek/deepseek-r1-turbo
Gateway$0.70$2.50——64,000 ⚠16,000
Hugging Face
deepseek-ai/DeepSeek-R1
Cloud$0.70$2.50——64,000 ⚠32,768
Cloudflare Workers AI
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b
Cloud$0.50$4.88——80,000 ⚠80,000deprecated
Amazon Bedrock
us.deepseek.r1-v1:0
Cloud$1.35$5.40——128,00032,768deprecated
Amazon Bedrock
deepseek.r1-v1:0
Cloud$1.35$5.40——128,00032,768deprecated
Merge GatewayGateway$1.35$5.40——163,840 ⚠40,960

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = noneeffort = loweffort = higheffort = max

Interleaved thinking (reasoning between tool calls) is declared by 1 of 15 providers.

14 / 15 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1D.Run (China)$220.00
2Alibaba (China)$229.50
3Qiniu$231.88
4Eden AI$260.00
5Novita AI$265.00
6Hugging Face$265.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.96$02026-08-052026-10-22
2026-10-22Input list —Output list —Min blended $0.96

Benchmark4 items

NameConditionsScoreMetricSource
Aider Polyglot—56.9percent correctSource ↗
Artificial Analysis Coding Index—15.9indexSource ↗
SciCode—35.7percent correctSource ↗
Terminal-Bench Hard—6.1success rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

DeepSeek V4 Pro 0813same series$0.66 / $1.98DeepSeek V4 Prosame series—DeepSeek V4 Pro 0423same series—DeepSeek Pro Latestsame lab—DeepSeek R1 0528same lab—
Data partly from models.dev (MIT)