OpenAI

Tier A · Strong with clear operating rules.

GPT-6.1 Sol

A tier for scoped implementation and debugging with review.

API pricing

USD per million tokens · OpenAI API Standard (≤272K input tokens)
Input
$2
Output
$10
Cached input
$0.1
Context window
1.05M
Pricing details and specifications

Try the active visual tests

Open the generated scene to test it, or compare that prompt with another model.

0 runs

Editorial verdict

Where this model fits

Back to all benchmarks →

GPT-6.1 Sol takes the A-tier Sol slot. OpenAI reports stronger software engineering results than GPT-6 Sol on DeepSWE v1.1. Superbash has yet to publish a visual run set for this exact version.

Best for

  • Scoped feature implementation
  • Debugging and maintenance
  • Prototyping against a clear brief

Watch out

  • The coding comparison comes from OpenAI’s launch evaluation
Ranking rationale and evidence
  1. OpenAI reports a 6.4 percentage point gain over GPT-6 Sol’s best DeepSWE v1.1 result at a lower reasoning effort and cost.
  2. A tier is an editorial placement for implementation work with a clear brief and review.

Evidence

2026-11-18

Superbash editorial model ranking

Takeaway: GPT-6.1 Sol is currently placed in Tier A.

The November 2026 editorial roster places GPT-6.1 Sol at rank 5.

Open source →
2026-09-29

Introducing GPT-6.1 Sol

Takeaway: OpenAI published software engineering results for GPT-6.1 Sol.

The launch report identifies DeepSWE v1.1 and describes the comparison settings.

Open source →
Sources, pricing details and methodology

Verified model facts

Model specifications

Pricing source · checked 2026-11-18 ↗
Status
Current
API model ID
gpt-6.1-sol
Context
1.05M
Max output
128K
License
Not publicly verified
Access route
OpenAI API, Codex and ChatGPT Work.
Modalities
text input, image input, text output
Hardware
Not publicly verified
OpenAI API Standard (≤272K input tokens) · USD / 1M tokens
$2 input · $0.1 cached input · $2.5 cache write · $10 output

Above 272K input tokens, input and cache rates double and output rates increase by 50% for the full request.