Inkling pricing
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,... This page tracks 5 listings in total. Highlighted lows are $0.950 per million input and $4.05 per million output (see table for which seller matches each).
Pricing across providers
All figures are list prices per million tokens unless a column says otherwise. 5 offers are listed for Inkling. Best input in this view: DeepInfra.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
B Baseten | $1.00 | $4.05 | $0.170 | — |
D DeepInfra | $0.950 | $4.05 | $0.160 | — |
FA Fireworks AI | $1.00 | $4.05 | $0.170 | — |
O Openrouter | $1.00 | $4.05 | $0.170 | — |
TA Together AI | $1.00 | $4.05 | $0.170 | — |
Input vs output · per provider
Cost calculator
The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Inkling cost scales with traffic.
Provider
0.100000¢ / req
0.202500¢ / req
Model specifications
These fields describe Inkling as we store it (source: Thinkingmachines). They sit next to price so buyers can check limits and tools in one place.
- Context window
- 1,048,576 tokens
- Max output
- N/A
- Vision (images)
- Yes
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Jul 2026
- Primary provider
- Thinkingmachines
- Model family
- N/A
Compare Inkling
Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for Inkling.
Locked
Compare with
Pick a model on both sides.
Popular Inkling comparisons
- Inkling vs GPT-4o
Compare pricing side by side
- Inkling vs Claude Sonnet 4.6
Compare pricing side by side
- Inkling vs Gemini 2.0 Flash
Compare pricing side by side
- Inkling vs Llama 3.1 70B
Compare pricing side by side
- Inkling vs Mistral 7B
Compare pricing side by side
- Inkling vs GLM 4.7
Compare pricing side by side
Frequently asked questions
Answers pull from the same numbers you see on this page. The short model note from our index: Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,....
Related models
Models close to Inkling by family, provider, and context window — each with live pricing in our catalog.