Distinguish GPT-6 Sol from the later GPT-6.1 Sol release. Pricing depends on input length, caching and processing tier; keep those choices in the evaluation record.
Responses and Chat Completions are supported; the Decisions API was added in beta on October 6, 2026. Evaluate that endpoint separately and recheck prices and token tiers.
These models launched together September 22, 2026, with text and image inputs. Start with identical tasks, endpoints and reasoning settings; record enough cases to expose retries and wrong answers.
Re-run image cases after the lifecycle update
OpenAI announced an image-encoding fix for both models on September 25, 2026. Results from before that fix are a distinct evaluation snapshot. Use the same image resolution, preprocessing and ground truth in a new test.
Keep input length and processing tier explicit
The launch pricing examples were scoped to prompts up to 272K input tokens. Caching, longer prompts and other tiers can change the estimate. Build the bill from actual token usage and the selected rate.
Three criteria for this comparison
Correct answers on identical labeled cases
Image-task behavior after the September 25 fix
Total accepted-result cost at fixed output budgets
Run a fair comparison
Use the same representative inputs and a written answer rubric. Pin the model version and record the endpoint, thinking configuration, quantization when known, context length, output allowance and concurrency. Preserve native request differences in an adapter rather than silently dropping fields.
Measure full request time, error rate and reported usage. For tools, validate arguments and score the result after execution. For images, preserve resolution and preprocessing. A valid response format alone does not establish a correct answer.
Compare cost per accepted result
Calculate input cost plus all billed output, including reasoning where the provider counts it. Add retries and discarded answers. Divide the total by the number of results that pass your quality criteria. Keep API usage cost separate from deployment and engineering cost.
Latest recorded measurements aligned by exact artifact, benchmark version, source and methodology. These are source results, not tests of Flonno's deployment.
Artificial Analysis observations are refreshed by the integrated Radar. Differences in artifact, benchmark version or method prevent a score comparison. Read the evidence methodology →
YOUR WORKLOAD
Compare cost per accepted task.
Enter results from your own evaluation. A task should count once it meets your written quality criteria. Include failed attempts and retries in total spend. These inputs stay in this browser and are not a Flonno benchmark.
GPT-6 Sol
Enter all four values. Attempted tasks must be at least one; accepted tasks cannot exceed attempted tasks.
GPT-6 Luna
Enter all four values. Attempted tasks must be at least one; accepted tasks cannot exceed attempted tasks.
Turn evidence into a deployment decision
A source benchmark can inform your shortlist, while your evaluation shows whether a model finishes the work at an acceptable cost. Keep the chosen endpoint, processing terms and output limits in the decision record. Inclusion in the Radar does not mean the model is served by Flonno.
