Home → Guides → GPT-6.1 Sol API pricing and what a call costs

GPT-6.1 Sol API pricing and what a call costs

GPT-6.1 Sol costs the same per token as GPT-6 Sol. Moving to it is a one-word change in your code, and the bill per token stays where it was.

Price per million tokens

ModelList inputList outputHere: inputHere: outputShare of list
gpt-6.1-sol$2.00$10.00$0.400$2.0020%
gpt-6-sol$2.00$10.00$0.400$2.0020%
gpt-6-astra$10.00$50.00$2.00$10.0020%

The figures on this platform are filled in from live billing data each hour, so they always match what you are charged. GPT-6 Astra is listed for comparison: it costs five times as much per token.

What a call costs

A coding-agent turn of 100,000 input tokens and 2,000 output tokens:

At these volumes input is about 90% of the bill, so keep stable content — system prompt, tool definitions, files — at the start of the prompt where it can be cached.

Response times we measured

RequestTimeDate
Short text reply (“OK”)2.7 s total2 Nov 2026
First token, text request, streaming2.6 s12 Oct 2026
Question about an attached image24–25 s12 Oct 2026

It reads images correctly but slowly. For screenshot-heavy work, gpt-6-astra answered the same image question in 6.6 seconds. It called tools with the correct argument names in every run of our Cline tool-call test.

Switching from gpt-6-sol

Both models are in the same group, so an existing key keeps working. Change the model name and nothing else:

- "model": "gpt-6-sol"
+ "model": "gpt-6.1-sol"

Calling gpt-6.1-sol here

The endpoint is OpenAI-compatible. Base URL https://apiclan.us/v1:

curl https://apiclan.us/v1/chat/completions \
  -H "Authorization: Bearer sk-your-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-6.1-sol","stream":true,"messages":[{"role":"user","content":"hi"}]}'

With the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI(base_url="https://apiclan.us/v1", api_key="sk-your-key", timeout=120)
r = client.chat.completions.create(
    model="gpt-6.1-sol",
    messages=[{"role": "user", "content": "hi"}],
)
print(r.choices[0].message.content)

Create the API key under the GPT group in the console. To use it in Codex, see Codex with a custom API. For long generations, use https://api.apiclan.us/v1, which avoids the 100-second proxy limit.

Comparing models? GPT-6.1 Sol vs Claude Opus 5.5. Top-ups are in USDT, at 1 USDT for 2 credits of balance, with no monthly fee.

Start using it

No subscription, no monthly minimum, no sales call. Top up with USDT and spend what you use — 1 USDT gives you 2 credits of API balance.

Read the 30-second quickstart

Language: English · 简体中文

Prices on this page are filled in automatically from live billing data. Third-party terms are quoted from that party's own documentation.