GPT-6 Sol
−30% vs OpenAI
AzureOpenAIThe middle of the GPT-6 line: the same million-token window as Astra, at a fifth of the price. Reasoning, tools and pictures, for work that does not need the dearest model in the family.
The real OpenAI model
Same weights, same API, same answers. We change only how you pay for it: one key for every maker, one bill, no separate account to open. Every figure on this page comes from OpenAI’s own page — check it.
Maker's own pagePrice
input / output · per 1M tokensThe same model and the same answers through both. The daily discount applies to eligible requests within the displayed token limit.
Azure
−30%Only on FlintBeam−30% on requests up to 250,000 tokens
Direct on Azure: $2.00 / $10.00
Daily discount. Today's price can change.
OpenAI
Official price
More pricing details: speeds and very long prompts
| Speed | AzureUp to 250,000 tokens | OpenAIAbove 250,000 tokens |
|---|---|---|
| Flex · slower | $1.00 / $5.00 | |
| Priority · faster | — | $4.00 / $20.00 |
Above 272,000 input tokens through OpenAI, the whole request costs here: $4.00 / $15.00 (Standard); $2.00 / $7.50 (Flex · slower); $8.00 / $30.00 (Priority · faster)
Context
1,050,000
up to 128,000 out
128,000 by default here
Modalities
Released
—
Knows up to Apr 20, 2026
What it would cost you
1000 tokens is roughly 750 English words.
How it is served
Requests are retried automatically if a provider is unavailable.
Similar models
Models built for the same kind of work, at a similar price.
Eligible models may have a daily discount below the maker's price. Daily discounts apply to eligible models and can change from day to day.
Use it from your code
from openai import OpenAI
# Works with the official openai package (pip install openai)
client = OpenAI(
base_url="https://api.flintbeam.com/v1",
api_key="sk-live-your-api-key"
)
response = client.chat.completions.create(
model="openai/gpt-6-sol",
messages=[
{"role": "system", "content": "You are an experienced software engineer."},
{"role": "user", "content": "Describe the architecture of a distributed cache."}
],
temperature=0.7,
max_tokens=1500
)
print(response.choices[0].message.content)