Qwen/Qwen3.8-Max vs AI21: Jamba Large 1.7
Qwen/Qwen3.8-Max is 1.2× cheaper for input tokens: Qwen/Qwen3.8-Max costs $1.65 per M and AI21: Jamba Large 1.7 costs $2.00 per M. Qwen/Qwen3.8-Max is 1.6× cheaper for output tokens: Qwen/Qwen3.8-Max costs $4.95 per M and AI21: Jamba Large 1.7 costs $8.00 per M. Both read up to 256,000 tokens of context.
| Qwen/Qwen3.8-Max | AI21: Jamba Large 1.7 | |
|---|---|---|
| Model id | Qwen/Qwen3.8-Max | ai21/jamba-large |
| Input | $1.65 per M | $2.00 per M |
| Output | $4.95 per M | $8.00 per M |
| Context length | 256,000 tokens | 256,000 tokens |
| Accepts | text | text |
| Produces | text | text |
| Served by | deepinfra | ai21 |
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.