DeepSeek-R1
DeepSeek-R1 provides customers a state-of-the-art reasoning model, optimized for general reasoning tasks, math, science, and code generation.
text → text · made by DeepSeek
$0.4→$0.4per Mtok in / out
Hyperbolic · 19 sellers
Sold by 24 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | standard | $1.35per Mtok in$5.4per Mtok outaws.amazon.com · read 2026-08-24 |
| AWS Bedrock cloud | in-region | $1.35per Mtok in$5.4per Mtok outpricing.us-east-1.amazonaws.com · read 2026-08-24 |
| Microsoft Azure AI cloud | standard | $1.35per Mtok in$5.4per Mtok outmodels.dev · read 2026-09-16 |
| Snowflake Cortex cloud | standard | $1.35per Mtok in$5.4per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Hyperbolic aggregator | standard | $0.4per Mtok in$0.4per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| ElectronHub aggregator | standard | $0.5per Mtok in$3per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Hugging Face Inference Providers 2 ways | $0.7per Mtok in$2.5per Mtok out | |
| Hugging Face Inference Providers aggregatornot on the seller's list today | deepinfra | $0.5per Mtok in$2.15per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | standard | $0.7per Mtok in$2.5per Mtok outmodels.dev · read 2026-09-16 |
| Hugging Face Inference Providers aggregator | novita | $0.7per Mtok in$2.5per Mtok outrouter.huggingface.co · read 2026-08-25 |
| SiliconFlow aggregator | standard | $0.5per Mtok in$2.18per Mtok outmodels.dev · read 2026-09-16 |
| DeepInfra aggregator | standard | $0.7per Mtok in$2.4per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Nous Research aggregator | standard | $0.7per Mtok in$2.5per Mtok outinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter aggregator | standard | $0.7per Mtok in$2.5per Mtok outopenrouter.ai · read 2026-08-24 |
| Requesty 2 ways | $0.85per Mtok in$2.5per Mtok out$0.85per Mtok cached | |
| Requesty aggregator | deepinfra | $0.85per Mtok in$2.5per Mtok out$0.85per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | novita | $4per Mtok in$4per Mtok out$4per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Novita AI aggregatornot on the seller's list today | alt | $0.89per Mtok in$0.89per Mtok outapi.novita.ai · read 2026-08-25 |
| Novita AI aggregator | standard | $4per Mtok in$4per Mtok outapi.novita.ai · read 2026-08-25 |
| Vercel AI Gateway aggregator | standard | $1.35per Mtok in$5.4per Mtok outai-gateway.vercel.sh · read 2026-08-25 |
| IO.NET aggregator | standard | $2per Mtok in$8.75per Mtok out$1per Mtok cached$4per Mtok cache writemodels.dev · read 2026-09-16 |
| PPIO aggregator | standard | $2per Mtok in$8per Mtok outapi.ppinfra.com · read 2026-09-16 |
| Fireworks AI aggregator | standard | $3per Mtok in$8per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Together AI aggregator | standard | $3per Mtok in$7per Mtok outmodels.dev · read 2026-09-16 |
| Replicate aggregator | standard | $3.75per Mtok in$10per Mtok outreplicate.com · read 2026-08-25 |
| SambaNova Cloud aggregator | standard | $5per Mtok in$7per Mtok outraw.githubusercontent.com · read 2026-09-16 |
Measured 25 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 7thof 18 | Algotune — Epoch AI | Score | 1.7 |
| 7thof 54 | Live bench — Epoch AI | Global average | 71.57 |
| 8thof 10 | Humanity's Last Exam | Accuracy (%) | 8.5 |
| 10thof 36 | Balrog — Epoch AI | Average progress | 0.349 |
| 12thof 49 | Lech mazur writing — Epoch AI | Mean score | 8.3 |
| 14thof 25 | AgentBench Leaderboard (new) | Success Rate (pass@1) AVG | 49.3 |
| 19thof 108 | Math level 5 — Epoch AI | mean_score | 93.051 |
| 27thof 69 | Aider polyglot coding leaderboard | Percent correct | 56.9 |
| 30thof 50 | Metr time horizons — Epoch AI | average_score | 0.519 |
| 32ndof 72 | Aider polyglot — Epoch AI | Percent correct | 56.9 |
| 32ndof 81 | Forecastbench — Epoch AI | Overall score | 60 |
| 38thof 42 | Fictionlivebench — Epoch AI | 120k token score | 0.333 |
| 72ndof 105 | Vectara Hallucination Leaderboard | Hallucination Rate | 11.3 |
| 81stof 102 | Simplebench — Epoch AI | Score (AVG@5) | 0.309 |
| 114thof 177 | Critpt — Epoch AI | Accuracy | 1.1 |
| 129thof 143 | Artificial Analysis · Agentic Index | Index | 1.1 |
| 134thof 170 | Weirdml — Epoch AI | Accuracy | 36.49 |
| 138thof 168 | Scicode — Epoch AI | Score | 35.714 |
| 140thof 184 | Artificial Analysis · Coding Index | Index | 24.6 |
| 151stof 402 | LMArena · Text | Score (Elo) | 1398 |
| 177thof 313 | GPQA Diamond | mean_score | 69.223 |
| 178thof 290 | OTIS Mock AIME 2024-2025 | mean_score | 53.333 |
| 185thof 227 | Arc agi 2 — Epoch AI | Score | 1.3 |
| 214thof 244 | Arc agi — Epoch AI | Score | 15.8 |
| 461stof 656 | Epoch capabilities index — Epoch AI | ECI Score | 138.99 |
About
DeepSeek-R1 — a text model from DeepSeek, sold by 19 companies from $0.4 in and $0.4 out per million tokens, placed 7th of 54 on Live bench — Epoch AI.
It takes text and returns text, with a context window of 128,000 tokens. It was published in 2025, trained on material up to July 2024. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning, code and agents. Nineteen companies sell it. The cheapest is $0.4 in and $0.4 out per million tokens at Hyperbolic. Beside the standard rate there are regional and separately routed lanes. It has been measured on 25 boards, and stands best at 7th of 54 on Live bench — Epoch AI.
Every current figure
- Maker
- DeepSeek
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 128,000 tokens
- Published
- 2025
- Knowledge to
- July 2024
- Parameters
- 685 billion
- Licence
- not read
- Sellers
- 19
- Maker's own price
- not read
- Price
- $0.4 in and $0.4 out per million tokens — Hyperbolic
- Boards
- 25
- Best place
- 7th of 54 — Live bench — Epoch AI
Known as 10 names
DeepSeek-R1 (2025-05-28)DeepSeek-R1*R1deepseek.r1-v1:0deepseek-ai/DeepSeek-R1deepseek/deepseek-r1deepseek/deepseek-r1/communitydeepseek/deepseek-v3/communitydeepinfra/deepseek-ai/DeepSeek-R1novita/deepseek/deepseek-r1