Same model, served by 1 provider. Weights: thinkingmachines/Inkling-2-Small.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Promo pricing | thinkingmachines/Inkling-2-Small | standardFP4 | $0.30 | $1.0 | $0.03 | $0.475 | Verified 12h ago ยท Changed 9d 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 fp4 | $50/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.