GPT-6 Astra vs GPT-6.1 Sol
| Benchmark | GPT-6 Astra | GPT-6.1 Sol |
|---|---|---|
| AutomationBench-AA | 64.6 | 62.6 |
| GDPval-AA (work tasks) 2.1 | 49.3 | 47.5 |
| AA Analyst Agent | 51.3 · max | 50 · max |
| Terminal-Bench 4.0 | 49.5 | 48 |
| Terminal-Bench Science 0.1 | 63.3 · max | 58.1 · max |
| AA-Briefcase 1.1 · Elo | 1,460.9 | 1,361.2 |
| AA-LCR (long context) 1.1 | 79.7 | 83.3 |
| DeepSWE 1.1 | 72.8 | 72.3 · max |
| FrontierCode 1.1 | 47 · max | 49.1 · max |
| Harvey LAB-AA 1.1 | 8.6 · max | 6.9 · max |
| SWE-bench Pro (v2 full) | 96.9 · high | 96.1 · xhigh |
| EBR Bench | 76.2 · max | 54.3 · max |
| Furniture Assembly | 80 · max | 80 · max |
| SpireClimb | 25.7 · max | 24.7 · max |
| SpireClimb StS1 A20 Heart | 16.7 · max | 20 · max |
| SpireClimb StS2 A10 | 34.7 · max | 29.3 · max |
| AutomationBench · Zapier run | 34.1 | — |
| τ³-Banking · AA | 35.5 | — |
| ITBench SRE | 48.6 · max | — |
| SWE-bench Pro (v2 hard) | 90.2 · high | — |
Specs
| Spec | GPT-6 Astra | GPT-6.1 Sol |
|---|---|---|
| Input, per 1M | $10 | $2 |
| Output, per 1M | $50 | $10 |
| Cost per task? | $1.54 | $0.21 |
| Speed, tok/s | 59 | 45 |
| Context | 1.05M | 1.05M |
| Weights | Closed | Closed |
| Released | Sep 2026 | Sep 2026 |
| See images | ✓ | ✓ |
| Read PDFs | Partial | Partial |
| Hear audio | — | — |
| Watch video | — | — |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | Partial |
| Return strict JSON | ✓ | ✓ |
| Search the web | ✓ | ✓ |
| Run code | ✓ | ✓ |
| Use a computer | ✓ | ✓ |
What breaks when you switch
Remove unsupported parameters›
With reasoning enabled, remove temperature, top_p and top_logprobs, plus Chat Completions logprobs or Responses message.output_text.logprobs includes.
Responses API for tool calling · Chat Completions›
Use Responses for tools; Chat Completions supports this model without tool calling.
No none or minimal reasoning›
The none and minimal reasoning efforts are unsupported; choose low, medium, high, xhigh or max.
More than 272K input tokens›
Prompts above 272K input tokens charge 2× input and cache rates and 1.5× output rates for the entire request.
Cache writes billed at 1.25x›
Cache writes cost 1.25× the uncached input token rate.
Ultrafast prices 6x Standard›
Ultrafast mode costs 6× Standard token prices.
Monitoring can return HTTP 403›
Misalignment monitoring can return HTTP 403 before streaming or errors after output; match misalignment_policy_violation and handle stream errors.
No none reasoning effort›
The none reasoning effort is unsupported on GPT-6 Astra and GPT-6.1 Sol; use low instead.
Remove unsupported sampling parameters›
When reasoning effort is not none, remove temperature, top_p and top_logprobs, plus Chat Completions logprobs or Responses output logprobs inclusion.