DeepSeek R1 Turbo vs Kimi K2 Instruct
Kimi K2 Instruct is 1.2× cheaper for input tokens: DeepSeek R1 Turbo costs $0.70 per M and Kimi K2 Instruct costs $0.57 per M. They cost about the same for output tokens: DeepSeek R1 Turbo $2.50 per M, Kimi K2 Instruct $2.30 per M. Kimi K2 Instruct reads more: DeepSeek R1 Turbo takes up to 64,000 tokens of context and Kimi K2 Instruct up to 131,072.
| DeepSeek R1 Turbo | Kimi K2 Instruct | |
|---|---|---|
| Model id | deepseek/deepseek-r1-turbo | moonshotai/kimi-k2-instruct |
| Input | $0.70 per M | $0.57 per M |
| Output | $2.50 per M | $2.30 per M |
| Context length | 64,000 tokens | 131,072 tokens |
| Accepts | text | text |
| Produces | text | text |
| Served by | novita | novita |
Prices are the providers' list prices per million tokens, as of . Both run on your own provider key through one OpenAI-compatible endpoint, with no fee on the tokens.