DeepSeek-R1 (DI)
Open-weights reasoning model with chain-of-thought trained via RL. Comparable to o1 on math benchmarks at a fraction of the price.
DeepSeek-R1 (DI) is a reasoning AI model from DeepInfra. It costs $0.550 per million input tokens and $2.190 per million output tokens (blended $1.042/M), with a 64,000-token context window.
Profile inherited from upstream DeepSeek-R1 ↗ — this is a hosted variant of the same open-weights model.
- Open-weights reasoning
- Visible chain-of-thought
- Math & code
- Cheap
- Reasoning agents
- Math/STEM tools
- Self-hosted reasoning
Benchmarks
More from DeepInfra
See all 11 →Frequently asked questions
How much does DeepSeek-R1 (DI) cost?
DeepSeek-R1 (DI) costs $0.550 per million input tokens and $2.190 per million output tokens, for a blended reference rate of $1.042 per million tokens.
What is DeepSeek-R1 (DI)'s context window?
DeepSeek-R1 (DI) supports up to 64,000 tokens of context in a single request.
What is DeepSeek-R1 (DI) best for?
DeepSeek-R1 (DI) is well suited to Open-weights reasoning, Visible chain-of-thought and Math & code.
Who makes DeepSeek-R1 (DI)?
DeepSeek-R1 (DI) is developed and served by DeepInfra.