Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audioInkling by thinkingmachines is offered by 24 providers on this page. Its official list price is $1.87 per 1M input tokens and $4.68 per 1M output tokens. The lowest paid channel is Eden AI at $0.95 / $4.05 per 1M, about 1.5× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 12.5 on the Intelligence Index, with 24.7 for Economics, its strongest domain. Against its lowest blended price of $1.73 per 1M, that is roughly 7 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 140 tokens per second, with 2.22s to the first token. Running one task of the Artificial Analysis suite costs about $1.3520, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 65,536 tokens at the reference host, but hosts report different limits, from 65,536 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Audio, and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Eden AI deepinfra/thinkingmachines/Inkling | Gateway | $0.95 | $4.05 | $0.16 | — | 524,288 ⚠ | 524,288 | |
| Deep Infra thinkingmachines/Inkling | Cloud | $0.95 | $4.05 | $0.16 | — | 524,288 ⚠ | 524,288 | deprecated |
| Thinking MachinesOfficial thinkingmachines/Inkling:peft:262144:sampling-nvfp4 | First-party | $1.00 | $4.05 | $0.17 | — | 262,144 ⚠ | 262,144 | |
| Together AI thinkingmachines/Inkling | Cloud | $1.00 | $4.05 | $0.17 | — | 524,288 ⚠ | 131,072 | |
| CommandCode | Gateway | $1.00 | $4.05 | $0.17 | — | 256,000 ⚠ | 256,000 | |
| NanoGPT thinkingmachines/inkling:thinking | Gateway | $1.00 | $4.05 | $0.17 | — | 1,040,000 ⚠ | 32,768 | |
| NanoGPT | Gateway | $1.00 | $4.05 | $0.17 | — | 1,040,000 ⚠ | 32,768 | |
| Merge Gateway | Gateway | $1.00 | $4.05 | $0.17 | — | 1,048,000 ⚠ | 32,000 | |
| OpenRouter | Gateway | $1.00 | $4.05 | $0.17 | — | 524,288 ⚠ | 471,859 | |
| Eden AI together_ai/thinkingmachines/Inkling | Gateway | $1.00 | $4.05 | $0.17 | — | 524,288 ⚠ | 524,288 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 2 of 24 providers.
4 / 24 providers expose no reasoning control (reasoning_options: []).
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.