HASTATAgent stack guide ling
Inkling
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context1.05M
Output1.05M
Providers18
CapabilitiesTool calling, Reasoning, Image input
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 Nvidiathinkingmachines/inkling | $0.00 | $0.00 | Unavailable | 1.05M | 2026-07-15 |
 NanoGPTthinkingmachines/inkling | $1.00 | $4.05 | $0.17 | 1.05M | 2026-07-15 |
 Deep Infrathinkingmachines/Inkling | $0.95 | $4.05 | $0.16 | 512K | 2026-07-15 |
 Hugging Facethinkingmachines/Inkling | $1.00 | $4.05 | Unavailable | 1.05M | 2026-07-15 |
 Impossiblthinkingmachines/inkling | $1.87 | $4.68 | $0.37 | 64K | 2026-07-15 |
 OpenRouterthinkingmachines/inkling | $0.95 | $4.05 | $0.16 | 1.05M | 2026-07-15 |
 LLMTRthinkingmachines/inkling | $1.87 | $4.68 | Unavailable | 256K | 2026-07-15 |
 Merge Gatewaythinkingmachines/inkling | $1.00 | $4.05 | $0.17 | 1.05M | 2026-07-15 |
 Together AIthinkingmachines/Inkling | $1.00 | $4.05 | $0.17 | 512K | 2026-07-15 |
 Neoninkling | Unavailable | Unavailable | Unavailable | 1.05M | 2026-07-15 |
 Thinking Machinesthinkingmachines/Inkling | $1.87 | $4.68 | $0.37 | 64K | 2026-07-15 |
 Basetenthinkingmachines/inkling | $1.00 | $4.05 | Unavailable | 1.05M | 2026-07-15 |
 Vercel AI Gatewaythinkingmachines/inkling | $1.00 | $4.05 | $0.17 | 256K | 2026-07-15 |
 Eden AIdeepinfra/thinkingmachines/Inkling | $0.95 | $4.05 | $0.16 | 512K | 2026-07-15 |
Eden AItogether_ai/thinkingmachines/Inkling | $1.00 | $4.05 | $0.17 | 512K | 2026-07-15 |
 Kilo Gatewaythinkingmachines/inkling | $0.95 | $4.05 | $0.16 | 512K | 2026-07-15 |
 Venice AIinkling | $1.25 | $5.06 | $0.21 | 512K | 2026-07-17 |
 Fireworks AIaccounts/fireworks/models/inkling | $1.00 | $4.05 | $0.17 | 1.05M | 2026-07-15 |
 Abacusthinkingmachines/Inkling | $3.74 | $9.36 | $0.75 | 256K | 2026-07-15 |
Lowest reported provider price in USD per 1M tokens; unavailable is not free. Provider documentation remains authoritative. Catalogue presence is not an uptime, security, or quality endorsement.
Source metadata and limitations
Capabilities are source-reported. Tool calling does not prove quality in a particular harness. Prices and limits can change.
Modalities: text, image, audio → text