Same open weights, served by 1 provider.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2024-06-19 | Gryphe/MythoMax-L2-13b-turbo | standardFP8 | $0.13 | $0.13 | — | $0.13 | Verified 5h ago · Changed 7h ago | |
DeepInfra | Gryphe/MythoMax-L2-13b | standardFull precision | $0.40 | $0.40 | — | $0.40 | Verified 5h ago · Changed 7h ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| DeepInfra fp8 | $15.6/mo |
| DeepInfra fp16 | $48/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.