Llama3 70B Instruct vs Qwen MT Plus
Qwen MT Plus is 2× cheaper for input tokens: Llama3 70B Instruct costs $0.51 per M and Qwen MT Plus costs $0.25 per M. They cost about the same for output tokens: Llama3 70B Instruct $0.74 per M, Qwen MT Plus $0.75 per M. Qwen MT Plus reads more: Llama3 70B Instruct takes up to 8,192 tokens of context and Qwen MT Plus up to 16,384.
| Llama3 70B Instruct | Qwen MT Plus | |
|---|---|---|
| Model id | meta-llama/llama-3-70b-instruct | qwen/qwen-mt-plus |
| Input | $0.51 per M | $0.25 per M |
| Output | $0.74 per M | $0.75 per M |
| Context length | 8,192 tokens | 16,384 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.