Models / Thinking Machines / Inkling
Thinking Machines · ling
Inkling
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
$1.87 in · $4.68 out
per 1M tokens · first-party price. Reference price from Thinking Machines, the lab's own listing.
Provider input prices run from $0.95 to $3.74 per 1M tokens. Output prices run from $4.05 to $9.36.
- Context
- 1,048,576
- Max output
- 1,048,576
- Cache read
- $0.37
- Cache write
- —
- Reasoning
- Yes
- Tool calls
- Yes
- Structured output
- Unknown
- Vision
- Yes
- Open weights
- Yes
- License
- Apache-2.0
- Released
- Jul 15, 2026
- Updated in source
- Jul 15, 2026
- Knowledge
- —
- Providers
- 24
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| Deep Infra | $0.95 | $4.05 | $0.16 | — | — |
| DevPass | $0.95 | $4.05 | $0.16 | — | — |
| Eden AI | $0.95 | $4.05 | $0.16 | — | — |
| Kilo Gateway | $0.95 | $4.05 | $0.16 | — | — |
| LLM Gateway | $0.95 | $4.05 | $0.16 | — | — |
| Baseten | $1.00 | $4.05 | — | — | — |
| Fireworks AI | $1.00 | $4.05 | $0.17 | — | — |
| Hugging Face | $1.00 | $4.05 | — | — | — |
| Merge Gateway | $1.00 | $4.05 | $0.17 | — | — |
| NanoGPT | $1.00 | $4.05 | $0.17 | — | — |
| Neon | $1.00 | $4.05 | $0.17 | — | — |
| OpenRouter | $1.00 | $4.05 | $0.17 | — | — |
| Together AI | $1.00 | $4.05 | $0.17 | — | — |
| Vercel AI Gateway | $1.00 | $4.05 | $0.17 | — | — |
| Charm Hyper | $1.09 | $4.41 | $0.19 | — | — |
| Modal | $1.20 | $5.00 | $0.27 | — | — |
| Venice AI | $1.25 | $5.06 | $0.21 | — | — |
| AI/ML API | $1.38 | $5.57 | $0.23 | — | — |
| Impossibl | $1.87 | $4.68 | $0.37 | — | — |
| LLMTR | $1.87 | $4.68 | — | — | — |
| Requesty | $1.87 | $4.68 | $0.37 | — | — |
| Thinking Machinesreference | $1.87 | $4.68 | $0.37 | — | — |
| Abacus | $3.74 | $9.36 | $0.75 | — | — |
| Nvidia | $0 | $0 | — | — | deprecated |