GPT-6.1 Sol API

openai/gpt-6.1-sol
GPT-6.1 model from OpenAI with near-Astra performance at a lower cost for complex coding, computer use and professional work: text and image input over a 1.05M-token context, with reasoning, and tool calling and server tools via the Responses API.
Context
1.1M tokens
Input
$2.6 / 1M tokens
Output
$13 / 1M tokens
Released
Sep 29, 2026

How to use GPT-6.1 Sol API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to openai/gpt-6.1-sol.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "openai/gpt-6.1-sol",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "openai/gpt-6.1-sol",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-6.1-sol","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

GPT-6.1 Sol API Pricing

TypePrice
Input
$2.6 / 1M tokens
Output
$13 / 1M tokens
Cached input
$0.13 / 1M tokens

GPT-6.1 Sol vs other models

ModelInputOutputContextBest for
GPT-6.1 Sol
This page
$2.6 / 1M tokens
$13 / 1M tokens
1.1M tokens
Complex coding and agentic work
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Everyday coding and agents
$13 / 1M tokens
$65 / 1M tokens
1M tokens
Agentic workflows and computer use
$0.13 / 1M tokens
$0.65 / 1M tokens
1M tokens
Fast, high-volume tasks

Frequently asked questions

Yes. OpenAI announced the model on 29 September 2026 and it went live on AI/ML API the same day. Call it as openai/gpt-6.1-sol on the standard chat completions endpoint.

$2.60 per 1M input tokens, $13.00 per 1M output tokens and $0.13 per 1M cached input tokens. Prompt caching is billed separately from standard input.

1,050,000 tokens, with up to 128,000 tokens of output. OpenAI gives the knowledge cutoff as 30 April 2026.

It takes text and image input and returns text. OpenAI lists streaming, structured outputs, function calling, file search, web search and prompt caching, plus reasoning with effort levels from low through max.

OpenAI presents it as an upgrade that approaches GPT-6 Astra's results on agentic coding, computer use and professional work at roughly a fifth of Astra's token price. Both models share the same 1.05M-token context and the same $2.60 / $13.00 pricing here, so the difference is in quality rather than cost.

Start building with GPT-6.1 Sol

Get API Key
1000+ models, one API.