GPT-6.1 / GPT-6 API — Access via an AI API Gateway
Call OpenAI’s GPT-6.1 / GPT-6 through byesu — an AI API gateway with pay-as-you-go billing and no subscription. Both the Responses and Chat Completions APIs work, and Codex connects directly.
Model specs below are quoted from OpenAI’s official documentation, checked on 2026-10-16.
What It Is
GPT-6 is OpenAI’s current model generation, in three tiers. OpenAI calls Astra its “most capable model for the most demanding work” and Luna its “most efficient model for focused, high-volume tasks”. The later GPT-6.1 Sol offers “near-Astra performance for complex work at a lower cost”.
| Item | Value |
|---|---|
| Model ID on byesu | gpt-6.1-sol · gpt-6-astra · gpt-6-sol · gpt-6-luna |
Context window (gpt-6.1-sol) | 1,050,000 tokens |
Max output (gpt-6.1-sol) | 128,000 tokens |
Knowledge cutoff (gpt-6.1-sol) | Apr 30, 2026 |
Models available on byesu
| Model ID | Notes |
|---|---|
gpt-6.1-sol | Official: near-Astra performance at a lower cost; 1.05M context, list price $2 / $10 |
gpt-6-astra | Official: most capable, for the most demanding work; 1.05M context, list price $10 / $50 |
gpt-6-sol | The Sol tier of the GPT-6 generation |
gpt-6-luna | Official: most efficient, for focused high-volume tasks; 1.05M context, list price $0.1 / $0.5 |
How Pricing Works
byesu bills per token with no monthly fee. The actual price of every model is shown live in the model list after you sign in, and the console records the charge for each request.
For reference, OpenAI’s official list price is $2 / $10 per million input / output tokens.
TIP
A token in the default auto group can call gpt-6.1-sol — no need to pick a group. A wrong group returns “no available channel”; see Choosing a Group.
How to Call It
The base URL depends on the API format:
- OpenAI-compatible (
/v1/chat/completions,/v1/responses) →https://byesu.com/v1
Authenticate with Authorization: Bearer sk-YOUR_TOKEN.
Option 1: Responses /v1/responses (recommended)
from openai import OpenAI
client = OpenAI(api_key="sk-YOUR_TOKEN", base_url="https://byesu.com/v1")
resp = client.responses.create(
model="gpt-6.1-sol",
reasoning={"effort": "medium"},
input="Explain what an API gateway is in one sentence",
)
print(resp.output_text)Option 2: Chat Completions /v1/chat/completions
resp = client.chat.completions.create(
model="gpt-6.1-sol",
messages=[{"role": "user", "content": "Explain what an API gateway is in one sentence"}],
)
print(resp.choices[0].message.content)Per OpenAI’s documentation, tool calling for gpt-6.1-sol is only available on the Responses API; Chat Completions works but without tool calling. Reasoning effort: low, medium (default), high, xhigh, max.
Use It in Codex
Codex uses the Responses API. Put this in ~/.codex/config.toml:
model = "gpt-6.1-sol"
model_provider = "byesu"
model_reasoning_effort = "high"
disable_response_storage = true
[model_providers.byesu]
name = "byesu"
base_url = "https://byesu.com/v1"
wire_api = "responses"Full steps: Codex CLI.
FAQ
How do I get GPT-6.1 / GPT-6 API access?
Sign up at byesu, create a token (the default auto group works), and call gpt-6.1-sol through the OpenAI-compatible endpoint https://byesu.com/v1 (Responses or Chat Completions). You can pay with USDT or Alipay.
How much does the GPT-6.1 / GPT-6 API cost on byesu?
byesu bills per token with no subscription; the live price is shown in the model list after you sign in. For reference, OpenAI’s official list price is $2 / $10 per million input / output tokens.
How long is the GPT-6.1 / GPT-6 context window?
According to OpenAI’s documentation, the context window is 1.05M tokens with up to 128K output tokens per request.
Can I call GPT-6.1 / GPT-6 with the OpenAI SDK?
Yes. Set the SDK base_url to https://byesu.com/v1, use your byesu token as the api_key, and set model to gpt-6.1-sol.
What does “no available channel” mean when calling gpt-6.1-sol?
Usually the token is in a group that does not include this model. Use the default auto group (or a group that lists the model) and check the model ID matches the console exactly.