OpenAI

GPT-6 Sol Fast

GPT-6 Sol with priority processing. Same model, twice the price.

gpt-6-sol, priority processingtext + image inputtext output

Replaces GPT 5.6 Sol (Fast): input $8.4 → $4.2 per 1M (-50%), output $42 → $21 per 1M (-50%), same context window.

Run this model

openai/gpt-6-sol-fast

Use an endpoint supported by this model.

Get a key for this setup →
const response = await fetch('https://api.minirouter.sh/v1/chat/completions', {  method: 'POST',  headers: {    Authorization: `Bearer ${process.env.MINIROUTER_KEY}`,    'Content-Type': 'application/json',  },  body: JSON.stringify({    model: 'openai/gpt-6-sol-fast',    messages: [{ role: 'user', content: 'Why is the sky blue?' }],    max_tokens: 1024,  }),}) const data = await response.json()console.log(data.choices[0].message.content)
Read docs →

Model overview

Input / 1M
$4.2
All-in MiniRouter rate
Output / 1M
$21
All-in MiniRouter rate
Context
1.1M
1,050,000 tokens
Max output
128K
tokens
Model
GPT-6 Sol
same model and scores
Price
2x Sol
$4 in, $20 out per 1M
Announced
22 Sept 2026
publisher release

Publisher-reported, plotted by MiniRouter

Sol's scores, served faster.

Fast serves the same model, so these are GPT-6 Sol's results.

OpenAI-reported

AutomationBench 1.0.6

Business workflows across 47 tools. Fable 5.1 fell back to Opus 5 on about 40% of tasks.

Score by effort

0 to 100%

  • Sol · xhigh33.2%
  • Fable 5.1 · max31.4%
  • Astra · low30.3%
  • Opus 5 · max26.9%
Source: OpenAI announcement ↗, September 22, 2026. Publisher results; MiniRouter did not run these evaluations.
View chart data
AutomationBench 1.0.6 values
ModelEffortScore
GPT-6 Solxhigh33.2%
Claude Fable 5.1max31.4%
GPT-6 Astralow30.3%
Claude Opus 5max26.9%

OpenAI-reported

DeepSWE 1.1

Long-horizon software engineering in real codebases.

Score by effort

0 to 100%

  • Fable 5 · xhigh69.9%
  • Sol · max68.8%
  • Luna · max66.6%
Source: OpenAI announcement ↗, September 22, 2026. Publisher results; MiniRouter did not run these evaluations.
View chart data
DeepSWE 1.1 values
ModelEffortScore
Claude Fable 5xhigh69.9%
GPT-6 Solmax68.8%
GPT-6 Lunamax66.6%

OpenAI-reported

OSWorld 2.0 · offline

Long computer-use workflows, partial reward.

Score by effort

0 to 100%

  • Sol · xhigh60.5%
  • Opus 5 · med60.3%
Source: OpenAI announcement ↗, September 22, 2026. Publisher results; MiniRouter did not run these evaluations.
View chart data
OSWorld 2.0 · offline values
ModelEffortScore
GPT-6 Solxhigh60.5%
Claude Opus 5medium60.3%

When it pays off

Pay for speed only where you wait.

Route interactive turns here and background work to GPT-6 Sol.

GPT-6 Sol

OpenAI list, per 1M tokens

Input
$4.00$2.00 standard
Output
$20.00$10.00 standard
Source: OpenAI announcement ↗ for list prices; Vercel AI Gateway ↗ for fast rates.
View chart data
Rates per 1M tokens
ModelInputOutput
GPT-6 Sol$2.00$10.00
GPT-6 Sol Fast$4.00$20.00
GPT-6 Luna$0.10$0.50
GPT-6 Luna Fast$0.20$1.00

One route, standard clients.

Authenticate with a MiniRouter bearer key. Caller-provided upstream credentials are not used on this route.

Read model setup docs →
Base URLhttps://api.minirouter.sh/v1
Model IDopenai/gpt-6-sol-fast
Endpoints
/v1/chat/completions/v1/messages/v1/responses
Parameters

max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs

Structured output

JSON Schema and JSON mode enforced on verified providers.

Configured provider

Priority follows the live catalog order.

Input: text, image · Output: text

ProviderPriorityInput / 1MOutput / 1MParametersAccess
vercel
1$4.2$21max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputsMiniRouter balance