Thinking Machines: Inkling Small
Inkling Small is a model from Thinking Machines that accepts text, image, and audio inputs, which lets one endpoint handle mixed-media requests without separate transcription or vision services. It offers a 524,288-token context window and can return up to 262,144 tokens in a single completion, so long documents and lengthy generated outputs both fit. It supports tool calling and reasoning. Structured output support and open-weights availability are not specified, so teams that depend on either should confirm before committing. At $0.45 per million input tokens and $1.20 per million output tokens, it is priced for workloads where large inputs or high request volumes make cost a deciding factor. It is worth shortlisting for long-context, multimodal, or tool-driven pipelines. It has no independent benchmark coverage yet, so its quality is unproven; run your own evaluations against established alternatives before relying on it.
- Model ID
- thinkingmachines/inkling-small
- Vendor
- thinkingmachines
- Released
- July 2026
- Tokenizer
- Other
- Input Modalities
- text, image, audio
- Output Modalities
- text
- Max Output
- 262,144 tokens
- Tool Calling
- ✓ supported
- Structured Output
- not supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- ✓ accepts audio
- Moderated
- no
What it costs in practice
Computed from the current $0.45/M input and $1.20/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.02 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.29 |
| A month of a busy support chatbot | 5M in / 2M out | $4.65 |
Price & spec history
Tracked daily by PicksByModel since 2026-08-01.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-09-26 | $0.45 | $1.20 | 524,288 |
| 2026-08-21 | $0.45 | $1.20 | 1,048,576 |
| 2026-08-08 | $0.45 | $1.20 | 524,288 |
| 2026-08-01 | $0.50 | $1.20 | 524,288 |
Category rankings
Where Thinking Machines: Inkling Small places across the 3 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #9 | TranscriptionVoice · of 25 ranked | 123 |
| #14 | TTS ReplacementVoice · of 25 ranked | 115 |
| #23 | Audio SummarizationVoice · of 25 ranked | 139 |
Similar models
Quick answers
- How much does Thinking Machines: Inkling Small cost?
- $0.45 per million input tokens and $1.20 per million output tokens.
- What is Thinking Machines: Inkling Small's context window?
- 524,288 tokens, roughly 786 pages of text in a single request.
- Does Thinking Machines: Inkling Small support tool calling?
- It supports tool calling, a reasoning mode.
- Can Thinking Machines: Inkling Small process images?
- Yes, it accepts image input.