This model was retired on 2026-08-13. The pricing below is the last-known rate, kept for migration reference.
Context
164K
Max output
164K
Serving providers
13
Cheapest input
$0.40 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisHeadline indices
Intelligence Index
20.4
of 100
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| CritPt | 1% | default | — | |
| EvalComputeProxy | 185.5 | default | — | |
| GPQA Diamond | 81% | default | — | |
| Humanity's Last Exam | 16% | default | — | |
| IFBench | 40% | default | — | |
| LiveCodeBench | 77% | default | — | |
| Long-Context Reasoning | 57% | default | — | |
| MMLU-Pro | 85% | default | — | |
| Omniscience | -27.4 | default | — | |
| Omniscience Accuracy | 0.3 | default | — | |
| Omniscience Non Hallucination | 0.2 | default | — | |
| SciCode | 40% | default | — | |
| TerminalBench Hard | 16% | default | — | |
| τ²-bench | 37% | default | — |
Pricing by serving provider
last-known · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Hyperbolic | $0.40 | $0.40 | 1 | ||||||||||||||||
| |||||||||||||||||||
| DeepSeek | $0.55 | $2.19 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Vercel AI Gateway | $0.55 | $2.19 | 1 | ||||||||||||||||
| |||||||||||||||||||
| DeepInfra | $0.70 | $2.40 | 1 | ||||||||||||||||
| |||||||||||||||||||
| OpenRouter | $0.70 | $2.50 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Nebius | $0.80 | $2.40 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Azure | $1.35 | $5.40 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Snowflake | $1.35 | $5.40 | 1 | ||||||||||||||||
| |||||||||||||||||||
| SambaNova is dearest at $5.00 / $7.00 | |||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 27% since first tracked
Cost calculator
estimate your monthly spend on this model$112
estimated / month
Model IDs
copy the exact identifier for your platformhyperbolic/deepseek-ai/DeepSeek-R1deepseek/deepseek-r1vercel_ai_gateway/deepseek/deepseek-r1deepinfra/deepseek-ai/DeepSeek-R1deepseek/deepseek-r1nebius/deepseek-ai/DeepSeek-R1azure_ai/deepseek-r1snowflake/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 availabilityIs R1 still available?
R1 was retired on 2026-08-13. The pricing on this page is the last-known rate, kept for migration reference.
How much did R1 cost?
R1's last-known pricing, before it was retired on 2026-08-13, was $0.40 per 1M input tokens and $0.40 per 1M output tokens.
What was the context window of R1?
R1 had a 164K token context window and could return up to 164K output tokens.
What could R1 do?
R1 supported tool use, reasoning, prompt caching and structured output.
Other DeepSeek models
compare pricing across the DeepSeek lineupDeepSeek V4 Flash 0423$0.09/1M · 12 providersDeepSeek V3 0324$0.20/1M · 11 providersR1 Distill Llama 70B$0.20/1M · 10 providersDeepSeek V4 Pro 0423$0.43/1M · 10 providersDeepSeek$0.20/1M · 9 providersR1 0528$0.20/1M · 8 providersDeepSeek V3 1$0.25/1M · 8 providersDeepSeek V4 Flash 0731$0.04/1M · 7 providers
Popular comparisons
head-to-head pages featuring R1
R1 vs GPT-4o Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI