GPT-6 Astra vs GPT-6.1 Sol

$1.54 / task
Wins 4 of 5 benchmarks
$0.21 / task
Wins 1 of 5 benchmarks
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models
GPT-6 Astra52.7
GPT-6.1 Sol49.9
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
GPT-6 Astra49.5
GPT-6.1 Sol48
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation
GPT-6 Astra64.6
GPT-6.1 Sol62.6
Arena Text · creative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool
GPT-6 Astra · max1,450
GPT-6.1 Sol · max1,458
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos
GPT-6 Astra85.1
GPT-6.1 Sol83.9

Specs

SpecGPT-6 AstraGPT-6.1 Sol
Input, per 1M$10$2
Output, per 1M$50$10
Cost per task?$1.54$0.21
Speed, tok/s5945
Context1.05M1.05M
WeightsClosedClosed
ReleasedSep 2026Sep 2026
See images✓✓
Read PDFsPartialPartial
Hear audio——
Watch video——
Call tools✓✓
Force a tool callPartialPartial
Return strict JSON✓✓
Search the web✓✓
Run code✓✓
Use a computer✓✓

What breaks when you switch

GPT-6 Astra → GPT-6.1 Sol
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.

GPT-6.1 Sol → GPT-6 Astra
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.