AI Rate CardQwen Max vs llama-2-70b: API price and specs
Qwen Max is 30% cheaper than llama-2-70b on input price.
llama-2-70b is 64% cheaper than Qwen Max on output price.
llama-2-70b is 4% cheaper than Qwen Max on a 1M-in / 200k-out workload.
| Field | Qwen Max | llama-2-70b |
|---|---|---|
| Lowest input, per 1M | $0.35 | $0.50 +43.7% |
| Median input, per 1M | $0.71 | $0.72 +1.8% |
| Lowest output, per 1M | $1.38 +176% | $0.50 |
| Median output, per 1M | $2.84 +293.1% | $0.72 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.62 +4% | $0.60 |
| Context | 128K | — |
| Max output | 8K | — |
| Providers | 7 | 2 +71.4% |
| Regions | GLOBAL | — |
| Accepts | text | — |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | qiniu-ai | aihubmix |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
Frequently asked questions
Which is cheaper, Qwen Max or llama-2-70b?
Qwen Max is 30% cheaper than llama-2-70b on input price. llama-2-70b is 64% cheaper than Qwen Max on output price. llama-2-70b is 4% cheaper than Qwen Max on a 1M-in / 200k-out workload.
Where can I use both Qwen Max and llama-2-70b?
aihubmix, aiml