GPT-6.1 Sol

GPT-6.1 Sol is OpenAI's September 29, 2026 coding and agent model in the API and eligible ChatGPT Work and Codex plans; ordinary Chat access is planned later.

GPT-6.1 Sol
Read the release, access boundaries, evidence, and evaluation context for GPT-6.1 Sol.
AI Model API
Compare provider IDs, inputs, outputs, prices, and access boundaries before selecting an integration.
GPT-6.1 Terra
A separate model and price/effort contract for visual and computer work.

Browse Language Models models to compare other options for this task.

Platform: OpenAI

Language ModelCoding AssistantAgent WorkflowsLong ContextTool UseOpenAI

OpenAI API / eligible ChatGPT Work / Codex; Chat later

$2/1M input, $0.10 cached input, $2.50 cache write, $10 output; above 272K input: $4/$0.20/$5/$15 for full request; Ultrafast API 6x Standard: short $12/$0.60/$15/$60; long $24/$1.20/$30/$90

Commercial

🚀Function Overview

GPT-6.1 Sol is the updated Sol model for coding and agents; API and eligible Work/Codex access are live, Chat support is later.

Key Features

Official API ID gpt-6.1-sol
1,050,000-token context and 128,000 maximum output
Text and image input, text output
Reasoning effort low, medium (default), high, xhigh, max; none/minimal unsupported
Responses API supports tool calling; Chat Completions tool calling is unavailable
Standard $2 input, $0.10 cached input, $2.50 cache write, $10 output per million tokens
Above 272K input tokens, entire request uses $4 input, $0.20 cached input, $5 cache write, $15 output per million
Fast 2x applicable rates; Batch and Flex separate 50% discounts
Available through API and eligible paid ChatGPT Work/Codex plans; not yet ordinary Chat
October 8 Responses API Ultrafast: same model ID plus service_tier ultrafast, six times Standard API rates and separate Work/Codex plan eligibility.
Google Cloud Model Garden private preview for selected enterprise customers (October 21); separate provider billing, eligibility and API contract, not general availability.
Codex / ChatGPT Work default context 500K; subscription usage has no long-context surcharge. API limits and surcharges are separate.

Use Cases

•Verified coding changes
•Agent workflows on Responses API
•Long-context analysis with cost measurement
•Migration trials from GPT-6 Sol

⚙️Input Parameters

model

string

Use gpt-6.1-sol.

input

object

Text or supported image input for the Responses API.

reasoning.effort

string

Choose low, medium, high, xhigh, or max; medium is default.

tools

array

Optional built-in or custom tools supported by the active endpoint.

💡Usage Examples

Example 1

Input Parameters

{
  "model": "gpt-6.1-sol",
  "input": "Inspect this repository, implement the smallest safe fix, and verify the affected workflow.",
  "reasoning": {
    "effort": "high"
  }
}

Output Results

GPT-6.1 Sol returns a tool-using response. Verify task quality, account access, long-context rates, latency, and cache behavior before changing production routing.

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: OpenAI API / eligible ChatGPT Work / Codex; Chat later
Commercial Use: Supported
Pricing: $2/1M input, $0.10 cached input, $2.50 cache write, $10 output; above 272K input: $4/$0.20/$5/$15 for full request; Ultrafast API 6x Standard: short $12/$0.60/$15/$60; long $24/$1.20/$30/$90
Platform: OpenAI

Sources

Google Cloud exact preview model list