Thinking Machines: Inkling (256K)
Inkling (256K) is a reasoning model from Thinking Machines released on Jul 15, 2026. It reads text and images and writes text, with a 262K token context window and up to 262K tokens per reply.
Show moreShow less
It costs $3.74 per million input tokens and $9.36 per million output tokens. Cached input bills at $0.748, 80% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
22 providers serve it, including Deep Infra, Baseten and Fireworks AI. The lowest input price is $0.95 per million tokens at Deep Infra.
- Modalities
- In / out price
- $3.74 / $9.36 per 1M
- Context
- 262K
- Max output
- 262K
- Released
- Jul 15, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Inkling (256K) pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $3.74 / 1M tokens | |
|---|---|---|
| Output | $9.36 / 1M tokens | |
| Cached input (read) | $0.748 / 1M tokens | 80% off input |
Inkling (256K) providers
22 providers serve it, including Deep Infra, Baseten and Fireworks AI. The lowest input price is $0.95 per million tokens at Deep Infra. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Thinking Machines First party | $3.74 | $9.36 | $0.748 | 262K | 262K |
| Deep Infra | $0.95 | $4.05 | $0.16 | 524K | 1.05M |
| Baseten | $1 | $4.05 | – | 1.05M | 33K |
| Fireworks AI | $1 | $4.05 | $0.17 | 1.05M | 1.05M |
| Hugging Face | $1 | $4.05 | – | 1.05M | 1.05M |
| Together AI | $1 | $4.05 | $0.17 | 524K | 131K |
| Vercel AI Gateway | $1 | $4.05 | $0.17 | 256K | 256K |
| DevPass (LLM Gateway) | $0.95 | $4.05 | $0.16 | 524K | 1.05M |
| Eden AI | $0.95 | $4.05 | $0.16 | 524K | 1.05M |
| Kilo Gateway | $0.95 | $4.05 | $0.16 | 524K | 472K |
| LLM Gateway | $0.95 | $4.05 | $0.16 | 524K | 262K |
| Merge Gateway | $1 | $4.05 | $0.17 | 1.05M | 32K |
Showing 12 of 22 providers: the lab first, then the major clouds, then the cheapest resellers.
What Inkling (256K) costs per month
Pick a workload close to yours or type your own volumes.
Independent benchmarks
Measured by third parties, not reported by Thinking Machines. Each links to its source and shows the date I checked it.
Human preference: people compare two anonymous answers and pick the better one. Ratings from the Text Arena overall board, style control on.
Arena (formerly LMArena), checked Oct 10, 2026
Abstract reasoning on visual puzzles the model has not seen, semi private set. Hard to memorise, so it tracks reasoning more than knowledge.
ARC Prize, checked Oct 10, 2026
Benchmarks Thinking Machines reports (8)
- swe-bench-verified (SWEBench Verified, effort=0.99)77.6%
- swe-bench-pro (SWEBench Pro (Public), effort=0.99)54.3%
- terminal-bench-2.1 (Terminal Bench 2.1 (Best Harness), effort=0.99)63.8%
- gpqa-diamond (GPQA Diamond, effort=0.99)87.2%
- hle-no-tools (HLE (text only), effort=0.99)29.7%
- aime-2026 (AIME 2026, effort=0.99)97.1%
- mmmu-pro (MMMU Pro (Standard 10))73.5%
- simpleqa (SimpleQA Verified)43.9%
Labs pick their own settings and harnesses, so compare these only within one lab.
Supported request parameters
What you can set when you call Inkling (256K) through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning - Temperature
temperature
Alternatives to Inkling (256K)
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 42.1
Reads text, images and files. Tool calling, structured output, reasoning. Served by 38 providers.
by openaiJul 9, 20261.05M context$2/M input tokens$12/M output tokens38 providers
- Index 29.7
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 31 providers.
by googleFeb 18, 20261.05M context$2/M input tokens$12/M output tokens31 providers
- Index 51.8
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 29, 20261.05M context$2/M input tokens$10/M output tokens27 providers
- Index 56
Reads text, images and files. Tool calling, structured output, reasoning. Served by 26 providers.
by anthropicSep 26, 20261M context$2/M input tokens$10/M output tokens26 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 22, 2026$2/M input tokens$10/M output tokens27 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 38 providers.
by anthropicJun 29, 2026$2/M input tokens$10/M output tokens38 providers
More from Thinking Machines
- 524K context
Reads text, images and audio. Tool calling, structured output, reasoning. Served by 11 providers.
by thinkingmachinesJul 30, 2026$0.50/M input tokens$1.20/M output tokens11 providers
Inkling (256K) questions
How much does the Inkling (256K) API cost?
$3.74 per million input tokens and $9.36 per million output tokens, with cached input at $0.748. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Inkling (256K)?
262,144 tokens of input, and it can write up to 262,144 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Inkling (256K)?
22 providers serve it, including Deep Infra, Baseten and Fireworks AI. The lowest input price is $0.95 per million tokens at Deep Infra. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Inkling (256K) support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Inkling (256K) open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was Inkling (256K) released?
Jul 15, 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. Independent scores from my hand checked rankings, sources linked above. The summary is written from these facts.
Building on Inkling (256K)?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting