OptimToken › Models by maker › Thinking Machines
Thinking Machines (Inkling) API pricing
As of 2026-11-14, the OptimToken catalogue holds 3 Thinking Machines models. By price tier, 1 is Mid-range and 2 Budget. The cheapest is Inkling 2 Small at $0.30 per 1M input tokens and $1.00 per 1M output tokens. The most expensive is Inkling at $1.00 input and $4.05 output, 4.0x the cheapest on blended price (30% input, 70% output). These are the prices we quote: a model sold by several hosts has other rates, listed on its own page.
Thinking Machines models and prices
| Model | Input | Output | Batch (in / out) | Cache read | Context | Licence |
|---|---|---|---|---|---|---|
| Inkling 2 Small | $0.30 | $1.00 | not published | $0.03 | 1M | Unknown |
| Inkling Small | $0.45 | $1.20 | $0.36 / $0.96 | $0.10 | 524K | Open source (Apache 2.0) |
| Inkling | $1.00 | $4.05 | not published | $0.17 | 524K | Open source (Apache 2.0) |
Published discounts: a prompt-cache read rate for all 3 and a batch rate for 1 of the 3. The most recent by release date is Inkling 2 Small (2026-11). Arena ELO scores (as of 2026-11-09) exist for 2 of the 3; the highest is Inkling at 1444.
Licences
Of the 3, 2 are open source: their weights are published under the Apache 2.0 licence, OSI-approved with no field-of-use limit, so they can be self-hosted as well as bought by the token. No licence is recorded for the other 1, so this page does not say whether it can be self-hosted. Licences are as recorded in this catalogue: check the maker's own terms before relying on one.
Price changes since tracking began
Our daily price archive began on 2026-08-15 and holds a record for all 3 models. The price we quote has changed for 1 of them, 5 times in all, 2 of those changes flagged as a change of quoted host rather than a repricing. The most recent was to Inkling on 2026-10-07: +0.5% on the blended price (30% input, 70% output) (quoted host changed, not a repricing). One model joined after tracking began: Inkling 2 Small, on 2026-11-14. Last checked against the 2026-11-14 snapshot.
Each row is a model's most recent change. Its own page has the full history.
| Model | Date | Old price (in / out) | New price (in / out) | Blended change | Changes in all |
|---|---|---|---|---|---|
| Inkling | 2026-10-07 | $0.95 / $4.05 | $1.00 / $4.05 | +0.5% (quoted host changed, not a repricing) | 5 |
Other makers
- AionLabs API pricing
- Alibaba (Qwen) API pricing
- Amazon (Nova) API pricing
- Anthropic (Claude) API pricing
- ByteDance (Seed) API pricing
- Cohere (Command) API pricing
- DeepSeek API pricing
- Google (Gemini) API pricing
- inclusionAI (Ling) API pricing
- Meta (Muse) API pricing
- MiniMax API pricing
- Mistral API pricing
- Moonshot (Kimi) API pricing
- Nex AGI API pricing
- Nvidia (Nemotron) API pricing
- OpenAI (GPT) API pricing
- Perplexity (Sonar) API pricing
- Sakana (Fugu) API pricing
- StepFun API pricing
- Tencent (Hy) API pricing
- xAI (Grok) API pricing
- Xiaomi (MiMo) API pricing
- Zhipu (GLM) API pricing
Models by maker: every model in the catalogue, including makers with fewer than 3.
Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Get a FinOps review