$0.95 per 1M input tokens and $4.05 per 1M output tokens (cheapest host: DeepInfra).
Is Inkling free to use?›
There is no free API; the cheapest paid price is $0.95 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Inkling, and what is it best at?›
#74 of 334 in Chat & Knowledge, #54 of 132 in Coding, #84 of 133 in Agents & Tool Use, #83 of 195 in Writing & Language, #60 of 124 in Vision & Documents. Strongest at: Reasoning, Science, Knowledge.
Is Inkling better than GPT-5.4 Mini (2026-03-17)?›
On FrontierMath Tier 4 (v2), Inkling scores 4.9 vs 9.8 — lower.
How can I use Inkling?›
Through the API of DeepInfra, Together.
What is the context window of Inkling?›
256K tokens.
When was Inkling released? Is there a newer version?›
Released 2026-07-15. It is the current version in its line.
Is Inkling open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Inkling locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Inkling read images?›
It accepts text and images, audio as input.
What is Inkling?›
Inkling is an open-weights language model from Thinking Machines, released Jul 2026.
What are the best alternatives to Inkling?›
GPT-5.6 Luna (cheaper), GPT-6 Luna (better), GLM 5.2 (open weights).
CheaperGPT-5.6 Lunamax×12.5-74%$0.18
OpenGLM 5.2max×6+25%$1.47No image input
CheaperClaude Haiku 5.5max×9.5-88%$0.21Remove sampling parameters+5
CheaperGemini 3.6 Flashhigh×4.5-13%*$1.60
Grok 4.3high×3-9%$0.21
DeepSeek V4 Pro 0813maxOpen×5.5+15%$0.67Memory (4-bit): 571 GB → 990 GB+6
Kimi K2.6unstatedOpen×5.3same$0.95 / $4Memory (4-bit): 571 GB → 616 GBTInkling SmallxhighOpen×3.5-63%$0.45 / $1.20