R1 pricing & benchmarks
R1 is available from DeepSeek at $0.700 per million input tokens and $2.50 per million output tokens ($1.15 blended at 3:1). It accepts up to 163,840 tokens of context. 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....
Pricing
Per million tokens · OpenRouter
Input$0.700
Output$2.50
Blended (3:1)$1.15
Specification
deepseek/deepseek-r1
Context window164K
Max output16K
ReleasedJan 2025
LicenceOpen weights
Modalitiesin:text, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 71.7% ±3.1 | — | 2025-05-26 | Independently run · Epoch AI |
| OTIS Mock AIME | 53.3% ±7.5 | — | 2025-02-26 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| gpt-oss-120b | OpenAI | $0.070 (−94%) | 75.8% | Compare → |
| DeepSeek V4 Flash 0731 | DeepSeek | $0.113 (−90%) | 91.0% | Compare → |
| Gemma 4 31B | $0.160 (−86%) | 75.8% | Compare → | |
| GPT-5.6 Luna | OpenAI | $0.225 (−80%) | 91.6% | Compare → |
| GLM 5.2 | Zhipu AI | $0.387 (−66%) | 91.9% | Compare → |
Where to run R1
2 hosts · 2.3× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| Novita ⚠ 64K context, not 164K |
$1.15 | $0.700 / $2.50 | 64K | fp8 | 100.0% |
| Azure | $2.60 | $1.48 / $5.94 | 164K | — | 0.0% |
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare R1
FAQ
How much does R1 cost?
R1 costs $0.700 per million input tokens and $2.50 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $1.15 per million tokens.
What is R1's context window?
R1 accepts up to 163,840 tokens of context, and can generate up to 16,000 output tokens.
How good is R1 on benchmarks?
R1 scores 71.7% on GPQA Diamond, independently run and published by Epoch AI. 2 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as R1?
Yes — 5 models in our catalogue cost less per token than R1 and score at least as high on the same benchmark. The cheapest is gpt-oss-120b at $0.070 per million tokens blended.