Context
164K
Max output
164K
Serving providers
12
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
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| CritPt | 1% | default | — | |
| EvalComputeProxy | 73.6 | default | — | |
| GPQA Diamond | 81% | default | — | |
| Humanity's Last Exam | 15% | default | — | |
| IFBench | 40% | default | — | |
| LiveCodeBench | 77% | default | — | |
| Long-Context Reasoning | 55% | default | — | |
| MMLU-Pro | 85% | default | — | |
| Omniscience | -27.1 | default | — | |
| SciCode | 40% | default | — | |
| TerminalBench Hard | 16% | default | — | |
| τ²-bench | 37% | default | — |
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.40 to $5.00 per 1M tokens across 12 providers, so the dearest route costs 1150% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HyperbolicCheapest | $0.40 | $0.40 | 1 | ||||||||||||||||
| |||||||||||||||||||
| DeepSeek | $0.55 | $2.19 | 1 | ||||||||||||||||
| |||||||||||||||||||
| OpenRouter | $0.55 | $2.19 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Vercel AI Gateway | $0.55 | $2.19 | 1 | ||||||||||||||||
| |||||||||||||||||||
| DeepInfra | $0.70 | $2.40 | 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-r1openrouter/deepseek/deepseek-r1vercel_ai_gateway/deepseek/deepseek-r1deepinfra/deepseek-ai/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-r1sambanova/DeepSeek-R1
Frequently asked questions
R1 pricing, context and availabilityHow much does R1 cost?
R1 costs $0.40 per 1M input tokens and $0.40 per 1M output tokens at its cheapest provider via Hyperbolic. Across 12 serving providers, input prices range from $0.40 to $5.00 per 1M tokens.
What is the context window of R1?
R1 accepts up to 164K tokens of context and can return up to 164K output tokens.
Which providers serve R1?
R1 is available from 12 serving providers, each with its own pricing and model ID. Hyperbolic is currently the cheapest.
What can R1 do?
R1 supports tool use, reasoning, prompt caching and structured output.
Other DeepSeek models
compare pricing across the DeepSeek lineupPopular 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