Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
Qwen3.6 35B A3BQwen3.8 Max PrimeA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| Qwen3.6 35B A3B | Qwen3.8 Max Prime | |
|---|---|---|
| Input per 1M | $0.05 | $4 |
| Output per 1M | $0.7 | $12 |
| Cached input | n/a | $0.5 |
| Batch in / out | n/a | n/a |
| Blended (3:1) | $0.213 | $6 |
| Context | 262K | 1M |
| Routes | 9 | 1 |
| Released | Apr 27, 2026 | Sep 23, 2026 |
| Leadersboard score | n/a | n/a |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper
Every route
Qwen3.6 35B A3B
- Darkbloomfp4, fp4$0.05 / $0.7$0.213 blended
- AkashMLfp8, fp8+41%$0.1 / $0.9cached $0.05
DeepInfrafp8, fp8+47%$0.1 / $0.95$0.313 blended
Venicefp8, fp8+53%$0.1 / $1$0.325 blended
Parasailfp8, fp8+71%$0.15 / $1cached $0.05
- AtlasCloudfp8, fp8+97%$0.186 / $1.11cached $0.186
- Phaladefault region+120%$0.2 / $1.27$0.468 blended
CoreWeavefp8, fp8+135%$0.25 / $1.25cached $0.25
SiliconFlowfp8, fp8+196%$0.24 / $1.8cached $0.15
Qwen3.8 Max Prime
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.