# Inkling

Model tracker · checked 2026-10-17 · https://dbggr.dev/models/inkling/

Inkling is an everyday open-weight model from Thinking Machines Lab, released 15 July 2026. At Together AI it costs $1.00 per million input tokens and $4.05 per million output tokens, with a 524K-token context window. 2 providers serve it, and Together AI is the cheapest.

- Made by: Thinking Machines Lab
- Released: 2026-07-15
- Status: Generally available
- Tier: Everyday
- Weights: Open
- Context window: 524,288 tokens
- Input: text
- API id: thinkingmachines/Inkling
- Docs: https://docs.together.ai/docs/serverless/models

## Inkling price at 2 providers

US dollars per million tokens. Blended is 3 input tokens for every output token, one number to compare on. The cheapest blended price is highlighted.

| Provider | Input | Output | Cached input | Blended | Batch | Checked |
|---|---|---|---|---|---|---|
| Together AI | $1.00 | $4.05 | $0.17 | $1.76 | – | [2026-10-17](https://www.together.ai/pricing) |
| Modal Labs | $1.20 | $5.00 | $0.27 | $2.15 | – | [2026-10-17](https://modal.com/library/thinking-machines/inkling) |

- Together AI: Open weights (975B total, 41B active) under Apache 2.0. Served in NVFP4 with a 524,288-token context; Together lists it among chat models, not vision models.
- Modal Labs: Modal Shared Endpoint, billed per token; NVFP4. Open weights (975B total, 41B active) under Apache 2.0.

## Inkling benchmarks

| Benchmark | Score | What it measures | Reported by |
|---|---|---|---|
| SWE-bench Verified | 77.6% | real GitHub issues fixed | [Thinking Machines Lab](https://thinkingmachines.ai/news/introducing-inkling/) |

Scores reported by a model's maker aren't independently checked.

## Models like Inkling

| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| Inkling | $1.00 | $4.05 | 524K | Open |
| [DeepSeek V4 Pro](https://dbggr.dev/models/deepseek-v4-pro/) | $1.32 | $3.96 | 1M | Open |
| [Muse Spark Open](https://dbggr.dev/models/muse-spark-open/) | $1.25 | $4.25 | 1M | Open |
| [Muse Spark 1.3](https://dbggr.dev/models/muse-spark-1-3/) | $1.25 | $4.25 | 1M | Closed |
| [GLM-5.3](https://dbggr.dev/models/glm-5-3/) | $1.40 | $4.40 | 1M | Open |
| [Step 5 Preview](https://dbggr.dev/models/step-5-preview/) | $1.00 | $2.70 | 1M | Closed |

## FAQ

### How much does Inkling cost?

Inkling costs $1.00 per million input tokens and $4.05 per million output tokens at Together AI, and $0.17 per million cached input tokens. Prices are list prices in US dollars, last checked 17 October 2026.

### What is Inkling's context window?

Inkling takes up to 524,288 tokens in one request.

### Is Inkling open weight?

Yes. Thinking Machines Lab publishes the weights, so you can run Inkling yourself or at any host that serves it.

### Where can I use Inkling?

Inkling is available from Together AI and Modal Labs. At Together AI, call it as `thinkingmachines/Inkling`.