DeepSeek: R1
by DeepSeekDeepSeek: R1 is a large language model from DeepSeek. It costs $0.700 per million input tokens and $2.50 per million output tokens. Its context window is 64K tokens.
- Input / 1M tokens
- $0.700
- Output / 1M tokens
- $2.50
- Cached input / 1M
- -
- Context window
- 64K
Not supported
tokens
Who serves it cheapest
1 hosts serve R1. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| NovitaCheapestfp8 | $0.700 | $2.50 | 64K | - | 100.0% |
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 11.4
- Coding index
- 24.6
- Agentic index
- 1.1
About R1
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....
Specifications
| Model ID | deepseek/deepseek-r1 |
|---|---|
| Provider | DeepSeek |
| Context window | 64K tokens |
| Max output | 16K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | 2024-07-31 |
| Open weights | Yes - deepseek-ai/DeepSeek-R1 |
| Released | January 20, 2025 |
Cheaper alternatives
Models that cost less than R1 while keeping at least half its context window and every input modality it supports.
Seed-2.0-Code
$0.500 in · $3.00 out
about the same cheaperNano Banana 2 (Gemini 3.1 Flash Image)
$0.500 in · $3.00 out
about the same cheaperNano Banana 2 (Gemini 3.1 Flash Image Preview)
$0.500 in · $3.00 out
about the same cheaperGemini 3 Flash Preview
$0.500 in · $3.00 out
about the same cheaperKimi K2 Thinking
$0.600 in · $2.50 out
1.1× cheaperFrequently asked
How much does DeepSeek: R1 cost?
$0.700 per million input tokens and $2.50 per million output tokens.
What is the context window of DeepSeek: R1?
64K tokens, with up to 16K tokens of output per request.
Confirm against the source: DeepSeek official pricing.