GPT-6 Rosalind vs Inkling-Small
Comparing GPT-6 Rosalind and Inkling-Small across benchmarks, pricing, and capabilities.
OpenAI · Thinking Machines Lab · Updated for 2026
Which is better?
GPT-6 Rosalind and Inkling-Small trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.
On price, Inkling-Small is roughly 57.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose GPT-6 Rosalind
- you want the most recent training data — it shipped Oct 2026
Choose Inkling-Small
- cost matters — it's about 57.1x cheaper per token
- you need open weights you can self-host or fine-tune
At a glance
The differences that matter most.
Individual benchmarks
0 reported for GPT-6 Rosalind · 24 for Inkling-Small
GPT-6 Rosalind and Inkling-Smalldon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, GPT-6 Rosalind ($15.00/1M tokens) is 50.0x more expensive than Inkling-Small ($0.30/1M tokens).
For output processing, GPT-6 Rosalind ($75.00/1M tokens) is 62.5x more expensive than Inkling-Small ($1.20/1M tokens).
In conclusion, GPT-6 Rosalind is more expensive than Inkling-Small.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
Only Inkling-Small specifies input context (256,000 tokens). Only Inkling-Small specifies output context (256,000 tokens).
Input capabilities
Documented input modalities across available providers
Both GPT-6 Rosalind and Inkling-Small support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
GPT-6 Rosalind
Inkling-Small
License
Usage and distribution terms
GPT-6 Rosalind is licensed under a proprietary license, while Inkling-Small uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
Proprietary
Closed source
Apache 2.0
Open weights
Release Timeline
When each model was launched
GPT-6 Rosalind was released on 2026-10-30, while Inkling-Small was released on 2026-07-30.
GPT-6 Rosalind is 3 months newer than Inkling-Small.
Oct 30, 2026
1 weeks ago
3mo newerJul 30, 2026
3 months ago
Knowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
GPT-6 Rosalind is available from OpenAI. Inkling-Small is available from Thinking Machines Lab, DeepInfra.
GPT-6 Rosalind
Inkling-Small
Outputs Comparison
Judge for yourself.
Run your own prompts against GPT-6 Rosalind and Inkling-Small side-by-side, then vote on the output you prefer.
FAQ
Common questions about GPT-6 Rosalind vs Inkling-Small.