Tokenless
G
OpenAI

GPT-6 Sol API at half of list price

The GPT-6 workhorse: the frontier reasoning of the GPT-6 line at mid-tier cost, built for agentic workflows and complex coding across a 1M-token context. Reach for Sol when you want GPT-6 quality without the flagship price.

ReasoningAgentic codingVision1M contextTool use

GPT-6 Sol API pricing

Every rate is 50% of the provider's official list price. USD per million tokens.

Token typeList priceTokenless
Input$2.00$1.00
Output$10.00$5.00
Cache write$2.50$1.25
Cache read$0.20$0.10
Prompts over 272K tokens
Input$4.00$2.00
Output$15.00$7.50
Cache write$5.00$2.50
Cache read$0.40$0.20

A request whose prompt, including cached tokens, is over the threshold is billed entirely at the long-prompt rates, as the provider bills it.

Call GPT-6 Sol in one request

Tokenless speaks the OpenAI Chat Completions format. Point your client at the base URL, set model to gpt-6-sol, and you are done.

request.sh
curl https://api.tokenless.store/api/v1/chat/completions \
  -H "Authorization: Bearer $TOKENLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-sol",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

GPT-6 Sol API questions

How much does the GPT-6 Sol API cost?

On Tokenless, GPT-6 Sol costs $1.00 per million input tokens and $5.00 per million output tokens, half of OpenAI's list price of $2.00 and $10.00. Prompts over 272K tokens bill at $2.00 input and $7.50 output per million.

Is it the genuine GPT-6 Sol?

Yes. Tokenless routes a request for gpt-6-sol to the genuine GPT-6 Sol and returns its response unchanged. No cheaper model is substituted.

How do I call the GPT-6 Sol API?

Point any OpenAI-compatible SDK at https://api.tokenless.store/api/v1, use your Tokenless API key, and set the model to gpt-6-sol. You pay per token from a prepaid balance, and your first $1 is free.

What is the GPT-6 Sol context window?

GPT-6 Sol accepts up to 1,000,000 tokens of context and returns up to 128,000 output tokens per request.

More GPT models