gpt-6.1-sol API — per-token pricing and code examples

Checking statusPrice version 5 · in effect since Nov 19, 2026

Price per 1M tokens

InputOfficial price $2.00$0.58
Cache readOfficial price $0.10$0.029
Cache writeOfficial price $2.50$0.725
OutputOfficial price $10.00$2.90

Minimum per request$0.00002

Cache rates apply when the provider reports cache tokens.

71% off

About this model

gpt-6.1-sol is served through OpenAI Chat Completions, OpenAI Responses, Anthropic Messages. You pay $0.58 per 1M input tokens and $2.90 per 1M output tokens. That is 71% below the official price of $2.00 and $10.00. Cache reads cost $0.029 per 1M tokens when the provider reports cached tokens. It is included in budget packs from $9.99 up.

Where GPT-6.1 Sol fits

OpenAI positions GPT-6.1 Sol as near-Astra performance for complex work at a lower cost, and recommends it for complex coding, computer use and professional work. It was released on September 29, 2026, a week after GPT-6 Sol, with a knowledge cutoff of April 30, 2026. If you want most of what GPT-6 Astra offers for day-to-day engineering and document work, this is the GPT-6 model OpenAI suggests looking at first.

The API limits match the rest of the family: a context window of 1,050,000 tokens, up to 922,000 of them as input, and up to 128,000 output tokens. OpenAI mentions a 500K default context inside Codex and ChatGPT Work, but that applies to those products, not to API calls. GPT-6.1 Sol takes text and images as input and replies in text. Audio and video input are not supported, and neither are fine-tuning or predicted outputs.

Always reasoning, tools only on Responses

GPT-6.1 Sol always reasons. OpenAI's latest-model guide states that it does not support the none effort, and the reasoning guide says a request that sends none to a model without it returns HTTP 400. The levels on the model page are low, medium, high, xhigh and max, with medium as the default. If your code used none with an earlier model, OpenAI's migration advice is to switch it to low.

Two more gotchas come from the same fact. Because effort is never none, temperature, top_p, top_logprobs and logprobs have to go. And OpenAI states that its Chat Completions API does not support function calling with GPT-6.1 Sol; OpenAI documents tool calling for GPT-6.1 Sol on its Responses API. On Cent AI, the /v1/responses format is available for this model.

{
  "model": "gpt-6.1-sol",
  "reasoning": { "effort": "low" },
  "tools": [{ "type": "function", "name": "run_tests", "parameters": { "type": "object", "properties": {} } }],
  "input": "Run the tests and tell me which ones fail"
}

This body is in the /v1/responses format. On /v1/chat/completions you can still set reasoning_effort, but without function tools.

What it costs on Cent AI

You are charged per token from your prepaid USD balance, using the four rates in the price box on this page. Since GPT-6.1 Sol reasons on every request, part of the output you pay for is always thinking, reported by OpenAI in usage.output_tokens_details.reasoning_tokens. To keep that share small, start at low and raise the effort only when the answers fall short.

OpenAI's prompt caching guide names GPT-6.1 Sol explicitly, and OpenAI reports cached tokens in the usage of each response. On Cent AI, cache read and cache write are billed only from the cached token counts OpenAI reports in that usage, never from an estimate.

Using it from your tools

GPT-6.1 Sol is served on /v1/chat/completions, /v1/responses and /v1/messages. Cent AI does not change your parameters silently, so reasoning_effort: "none" comes back as an upstream_error with the model's status code, for example HTTP 400, instead of being fixed for you, and a leftover temperature is not removed on your behalf either. Because every GPT-6.1 Sol answer includes reasoning, set the output limit with that in mind: OpenAI suggests reserving around 25,000 tokens for reasoning and the visible reply, and a Responses call that runs out ends as incomplete with the reason max_output_tokens.

Specification

Context window
—
Input and output
Text
Endpoints
/v1/chat/completions, /v1/responses, /v1/messages
Smallest pack
$9.99

Latency and error rate per model are on the status page. status.cent-ai.dev

What a request costs

Open the full calculator

Cost per request

90% is an assumption you can change, not a promise. Cache is billed only from cache tokens the model provider reports.

See how many such requests it covers.

Estimate

gpt-6.1-sol
Fresh input99,000 tok
Cache read891,000 tok
Output10,000 tok

Per request$0.1122
At official pricesAt official prices $0.3871

Total$0.1122

An estimate at price version 5. Your bill comes from the usage the provider reports for each request.

Save $0.2748

Code

curl https://api.cent-ai.dev/v1/chat/completions \
  -H "Authorization: Bearer $CENT_AI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-6.1-sol", "messages": [{"role": "user", "content": "Hello"}]}'

Set CENT_AI_KEY to a key from the dashboard. OpenAI SDKs use https://api.cent-ai.dev/v1; Anthropic SDKs use https://api.cent-ai.dev.

Price history

Version 5, in effect since Nov 19, 2026.

  1. Effective

    per 1M tokens

    Inputold $0.20 new $0.58
    Cache readold $0.02 new $0.029
    Cache writeold $0.20 new $0.725
    Outputold $1.00 new $2.90
  2. Effective

    per 1M tokens

    Inputold $0.10 new $0.20
    Cache readold $0.01 new $0.02
    Cache writeold $0.10 new $0.20
    Outputold $0.50 new $1.00
  3. Effective

    per 1M tokens

    Inputold $0.10 new $0.10
    Cache readold $0.01 new $0.01
    Cache writeold $0.125 new $0.10
    Outputold $0.50 new $0.50
  4. Effective

    per 1M tokens

    Inputold $0.10 new $0.10
    Cache readold $0.005 new $0.01
    Cache writeold $0.125 new $0.125
    Outputold $0.50 new $0.50

Compare with

All models against official prices

Questions

How much does gpt-6.1-sol cost on Cent AI?

$0.58 per 1M input tokens and $2.90 per 1M output tokens. Cache reads cost $0.029 and cache writes $0.725 per 1M tokens. Each request is rounded up once.

Is there a minimum charge?

A successful request costs at least $0.00002. A request that ends early, because the client left or the output was cut off, pays only for its tokens.

How do I pay?

Top up a prepaid USD balance with QRIS or USDT/USDC, or buy a budget pack once. Nothing renews automatically.

What if the provider does not report usage?

The request is billed from an estimate and marked estimated on the Requests page. An estimate never contains cache tokens.

Which endpoint do I call?

/v1/chat/completions, /v1/responses, /v1/messages. The OpenAI base URL is https://api.cent-ai.dev/v1.

Try gpt-6.1-sol with one key

One prepaid balance for every model. Pay with QRIS or USDT/USDC.

Start free