Same open weights, served by 4 providers. Weights: thinkingmachines/Inkling.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | thinkingmachines/Inkling | standardFP8 | $0.95 | $4.05 | $0.16 | $1.72 | Verified 3h ago · Changed 6h ago | |
Together AI | thinkingmachines/Inkling | standardQuantization not disclosed | $1.0 | $4.05 | $0.17 | $1.76 | Verified 5h ago · Changed 5h ago | |
Fireworks AI | accounts/fireworks/models/inkling | standardQuantization not disclosed | $1.0 | $4.05 | $0.17 | $1.76 | Verified 5h ago · Changed 5h ago | |
Azure AI Foundry Fireworks on Azure | inkling | standarddata zone (US)Quantization not disclosed | $1.1 | $4.46 | $0.19 | $1.94 | Verified 3h ago · Changed 6h 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 | $176/mo |
| Together AI | $181/mo |
| Fireworks AI | $181/mo |
| Azure AI Foundry data zone (US) | $199.2/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.