Cloud reference
GPT 5.6 Sol
Cloud reference
- Hardware
- Cloud reference—
- Memory
- —
- Tasks
- Moorhuhn
- Quantisations
- —
About the model
OpenAI documents neither a parameter count nor a layer count nor an architecture type for GPT-5.6 Sol. The API documentation states a context window of 1,050,000 tokens, of which at most 922,000 are input tokens and 128,000 output tokens, along with a knowledge cutoff of February 16, 2026. Inputs are text and image, output is text, and compute effort is controlled via reasoning.effort with the levels none, low, medium, high, xhigh and max. The system card dated July 9, 2026 places Sol in a family of three models, alongside Terra and Luna, and likewise gives no information about the internal structure.
- Context window
- 1,050,000 tokens
- Maximum input tokens
- 922,000
- Maximum output tokens
- 128,000
- Knowledge cutoff
- 16 February 2026
- Input modalities
- Text, image
- Output modality
- Text
- Reasoning levels
- none, low, medium (default), high, xhigh, max
- Reasoning modes
- standard, pro
The numbers at a glance
This run is still pending. Only the brief exists, no measurement and no artefact.
Assessment
not yet assessed
The grade is a personal, and therefore subjective, assessment.
There is no artefact to assess for this run, so it carries no grade.
What went wrong
No self-corrections were logged.
Sources
- Vendor siteopenai.com
- Measurement repositorygithub.com/KaiFelixBennett/local-ai-amd-benchmark
Try it yourself
- Download the weights
- Start llama-server with the parameters above
- Register the endpoint in VS Code as a custom model and pick the agent
Prompt, agent files and tools: Agent Test Harness
Citation: Kai Felix Bennett, “Usability test of local AI on AMD hardware”, benchmark.securesight.ai, run gpt56-sol. Measurement data CC-BY-4.0.
Measurement data CC-BY-4.0, code MIT.