Inkling
by Thinking MachinesChat
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
- Context
- 65.5K tokens
- Max output
- 65,536 tokens
- Parameters
- 952B total, 41B active
- Released
- 2026-07-15
- Weights
- Open
- Licence
- apache-2.0
thinkingmachines/inkling · also seen as accounts/fireworks/models/inkling, thinkingmachines/inkling:thinking, deepinfra/inkling, thinkingmachines/Inkling-NVFP4, +7 more
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-07-15
- Weights
- Opennot gated
- License
- apache-2.0
- Input
- Text, Image, Audio
- Output
- Text
- Context window
- 65,536 max across endpoints
- Max output
- 65,536
- Providers
- 12 + 13 gateways, not counted as providers
- Epoch Capabilities Index
- 148.6 ± 2.2 against price
- Direct price range
- $0.95–$1.87 in · $4.05–$5.57 out per 1M tokens · 8 of 12 providers have a comparable price
More details
- Last updated
- 2026-09-05
- Knowledge cutoff
- Weights link
- Hugging Face · thinkingmachines/Inkling
- Parameters
- 952B total, 41B active
- Developer country
- United States of America
- Training compute
- 1.1×10²⁵ FLOP
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel tools
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.95 in / $4.05 out per 1M tokens at Deep Infra on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Inkling |
|---|---|---|---|---|---|
| Seed EvolvingByteDance Seed | $1.47 | $0.884 | $4.42 | 256K | +0% |
| Sakana NamazuSakana AI | $1.46 | $0.95 | $4.00 | 262K | −1% cheaper |
| Grok 4.20 Multi Agent BetaSpaceXAI | $1.46 | $1.25 | $2.50 | 2M | −1% cheaper |
| Grok 4.20 Non-ReasoningSpaceXAI | $1.46 | $1.25 | $2.50 | 2M | −1% cheaper |
| Grok 4.20 Beta Non-ReasoningSpaceXAI | $1.46 | $1.25 | $2.50 | 2M | −1% cheaper |
| Grok 4.20 ReasoningSpaceXAI | $1.46 | $1.25 | $2.50 | 2M | −1% cheaper |
| Grok 4.20 Beta ReasoningSpaceXAI | $1.46 | $1.25 | $2.50 | 2M | −1% cheaper |
| Grok 4.20xAI | $1.46 | $1.25 | $2.50 | 1M | −1% cheaper |
More from Thinking Machines
Newest Thinking Machines models in the catalogue. All Thinking Machines models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Inkling Small | 2026-07-30 | 1.05M | from $0.45 |