meta-llama/Meta-Llama-3.3-70B-Instruct vs Kimi K2 Instruct
They cost about the same for input tokens: meta-llama/Meta-Llama-3.3-70B-Instruct $0.60 per M, Kimi K2 Instruct $0.57 per M. meta-llama/Meta-Llama-3.3-70B-Instruct is 1.9× cheaper for output tokens: meta-llama/Meta-Llama-3.3-70B-Instruct costs $1.20 per M and Kimi K2 Instruct costs $2.30 per M. Both read up to 131,072 tokens of context.
| meta-llama/Meta-Llama-3.3-70B-Instruct | Kimi K2 Instruct | |
|---|---|---|
| Model id | meta-llama/Meta-Llama-3.3-70B-Instruct | moonshotai/kimi-k2-instruct |
| Input | $0.60 per M | $0.57 per M |
| Output | $1.20 per M | $2.30 per M |
| Context length | 131,072 tokens | 131,072 tokens |
| Accepts | text | text |
| Produces | text | text |
| Served by | sambanova | 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.