R1
ModelOpen sourceActiveby DeepSeek · family “r”
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.... (description from the OpenRouter listing)
in: textout: textReasoningTool useStructured output
Epoch Capabilities Index
139.0 #118 of 268
90% CI 136.0 – 140.4
Released
20 Jan 2025
Context window
64K tokens
Max output
16K tokens
Input $ / 1M tokens
$0.70
Output $ / 1M tokens
$2.50
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source
Benchmark results (12)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| ARC-AGI-2 | reasoning | 1.3% | 1% | — | — | External ↗ |
| METR Time Horizons | agents | 51.9% | 61% | — | — | External ↗ |
| Fiction.LiveBench | long-context | 69.4% | 71% | — | — | External ↗ |
| Lech Mazur Writing | other | 83.0% | 97% | — | — | External ↗ |
| WeirdML | coding | 36.5% ±0.0 | 39% | — | — | External ↗ |
| Aider polyglot | coding | 56.9% | 65% | — | — | External ↗ |
| OTIS Mock AIME 2024-2025 | math | 53.3% ±7.5 | 53% | — | 26 Feb 2025 | Eval log ↗ |
| Balrog | games | 34.9% | 51% | — | — | External ↗ |
| SimpleBench | reasoning | 30.9% | 38% | — | — | External ↗ |
| GPQA diamond | science | 71.7% ±3.1 | 75% | — | 26 May 2025 | Eval log ↗ |
| MATH level 5 | math | 93.1% ±0.7 | 95% | — | 31 Jan 2025 | Epoch ↗ |
| ARC-AGI | reasoning | 15.8% | 16% | — | — | External ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
13 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.
Events
No events recorded yet.