OpenAI: GPT-6.1 Sol

GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, with a 1.05M-token context window and configurable reasoning.

Compare models

gpt-6.1-sol

AvailableOpenAIChatCached input 95% lessNew

Input / Output-70%: $2.00 / $10.00$0.60 / $3.00
Context: 1.05M
Released: Sep 29, 2026
Max output: 128K
Modalities: Chat
Capabilities: Tool usePrompt CacheReasoning

About GPT-6.1 Sol

GPT-6.1 Sol is OpenAI's update to GPT-6 Sol, offering near-Astra intelligence for complex coding, computer use, and professional work at a fraction of Astra's cost. It is the model OpenAI recommends for new projects over GPT-6 Sol. It is a text model with tool calling and configurable reasoning from low to max.

Where it works well

OpenAI reports it matches GPT-6 Astra on the DeepSWE v1.1 software engineering evaluation at much lower cost.
On OSWorld 2.0's offline set it beats GPT-6 Sol by seven points at maximum reasoning effort, per OpenAI.
More than doubles GPT-6 Sol's Terminal-Bench Science 0.1 score at maximum effort, according to OpenAI.
Reasoning effort spans low, medium, high, xhigh, and max, with medium as the default.

When to choose another model

It accepts text only and has no schema-constrained JSON output, so image and strict-schema jobs need another model.
Reasoning cannot be set to none, which makes it heavier than GPT-6 Luna for trivial calls.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.
02
Send your first request
Copy the example for your language and run it against the endpoint.
Text to textResponses API
POST/v1/responses
API format:
curl https://api.tokenlab.sh/v1/responses \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-xxx" \ -d '{ "model": "gpt-6.1-sol", "input": "Hello!" }'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Input tokens <= 272K

per 1M tokens

Official price: Input $2.00 / Output $10.00 / Cache read $0.10 / Cache write $2.50
Verified price: Input $0.60 / Output $3.00 / Cache read $0.03 / Cache write $0.75
Discount: -70%

Input tokens 272K-1.05M

per 1M tokens

Official price: Input $4.00 / Output $15.00 / Cache read $0.20 / Cache write $5.00
Verified price: Input $1.20 / Output $4.50 / Cache read $0.06 / Cache write $1.50
Discount: -70%

Prompt cache pricing

Cache read

Official price: $0.10
Verified price: $0.03
Discount: -70%

Cache write

Official price: $2.50
Verified price: $0.75
Discount: -70%

Tool fees

Charged per call, only when the model uses the tool.

Web search

Official price: $0.01/search
Verified price: $0.003/search
Discount: -70%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Input tokens <= 272K	Input $2.00 / Output $10.00 / Cache read $0.10 / Cache write $2.50	Input $0.60 / Output $3.00 / Cache read $0.03 / Cache write $0.75	-70%
Input tokens 272K-1.05M	Input $4.00 / Output $15.00 / Cache read $0.20 / Cache write $5.00	Input $1.20 / Output $4.50 / Cache read $0.06 / Cache write $1.50	-70%
Prompt cache pricing
Cache read	$0.10	$0.03	-70%
Cache write	$2.50	$0.75	-70%
Tool feesCharged per call, only when the model uses the tool.
Web search	$0.01/search	$0.003/search	-70%

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 16, 2026, 11:23 AM UTC

30-day success rate: 97.2%
7-day median latency: 18.6sn=12,905
7-day P95 latency: 98.6sn=12,905
30-day requests: 10K+
Last active: 21 minutes ago

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open GPT-6.1 Sol in Console with a prompt ready to edit or send.

Help me try gpt-6.1-sol with a short message at /v1/responses. Show the reply, latency, and cost.

Use cases

Best for

Code
Reasoning

Repository-scale coding
Hand it a ticket and a codebase, let it plan, edit, and test, and review the pull request it produces.
Desktop and browser automation
Run workflows that need on-screen operation, comparing results against a human-written checklist.
Scientific computing tasks
Run terminal-driven analyses, fix environment errors, and report findings from the output.
Cheaper Astra substitute
Replace Astra on coding workloads once your own evaluations show the same pass rate.

Prompt examples

Implement the feature described in this issue, add tests, run them with the terminal tool, and report what changed.

Set up the analysis environment from this README, rerun the notebook script, and explain any numbers that differ from the paper.

Review this migration for data-loss risks and propose a safer ordering of steps.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is GPT-6.1 Sol?

GPT-6.1 Sol is OpenAI's cost-efficient step beneath GPT-6 Astra, aimed at complex coding, computer use, and professional work. OpenAI recommends it over GPT-6 Sol for new projects.

How close is GPT-6.1 Sol to Astra?

OpenAI says it matches Astra on DeepSWE v1.1 and comes within 2.1 points on OSWorld 2.0's offline set at maximum effort. Treat those as the maker's figures and test on your own tasks.

How do I call GPT-6.1 Sol?

Call it like any other chat model, with standard OpenAI-style messages and function definitions. Tool calling is supported, and reasoning effort is set per request from low up to max.

Does GPT-6.1 Sol support image input?

No. It takes text input only. For screenshots, scanned pages, or other pictures, use GPT-6 Sol, GPT-6 Astra, or another model that accepts image input.

Can I disable reasoning on GPT-6.1 Sol?

No. OpenAI lists low, medium, high, xhigh, and max, with medium by default and no none setting. For no-reasoning calls, choose GPT-6 Luna or GPT-6 Sol.

How much does GPT-6.1 Sol cost?

On TokenLab, GPT-6.1 Sol costs Input $0.60 / Output $3.00 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of GPT-6.1 Sol?

GPT-6.1 Sol accepts up to 1,050,000 tokens of context and returns up to 128,000 tokens in one response.

Which endpoint should GPT-6.1 Sol use?

Use https://api.tokenlab.sh/v1/responses for GPT-6.1 Sol. The request example below shows the matching code shape.

Which operations does GPT-6.1 Sol support?

GPT-6.1 Sol supports Text to text. Select an operation above to see its endpoint and request example.