GPT-6 API access
Use OpenAI's GPT-6 and GPT-5.6 models through 7API with the Responses API (the format Codex uses) or Chat Completions. You don't need an OpenAI account. Point the SDK or tool at https://7api.st/v1 and use your 7API key.
| Model | ID | Context | Max output | Input / 1M | Output / 1M | Cached / 1M |
|---|---|---|---|---|---|---|
| GPT-6 Astra | gpt-6-astra | 1.05M | 128K | $0.65 | $0.65 | $0.06 |
| GPT-6.2 Astra | gpt-6.2-astra | 1.05M | 128K | $0.65 | $0.65 | $0.06 |
| GPT-6.1 Sol | gpt-6.1-sol | 1.05M | 128K | $0.15 | $0.15 | $0.04 |
| GPT-6.2 Sol | gpt-6.2-sol | 1.05M | 128K | $0.15 | $0.15 | $0.04 |
| GPT-6 Sol | gpt-6-sol | 1.05M | 128K | $0.15 | $0.15 | $0.04 |
| GPT-6 Luna | gpt-6-luna | 1.05M | 128K | $0.05 | $0.05 | $0.01 |
| GPT-5.6 Sol | gpt-5.6-sol | 1M | 128K | $0.45 | $0.45 | $0.04 |
| GPT-5.6 Terra | gpt-5.6-terra | 1M | 128K | $0.45 | $0.45 | $0.04 |
| GPT-5.6 Luna | gpt-5.6-luna | 1M | 128K | $0.45 | $0.45 | $0.04 |
| GPT-5.5 | gpt-5.5 | 1M | 128K | $0.45 | $0.45 | $0.04 |
Rates are in USD per million tokens. Last checked 2026-11-20.
What to know
- The GPT-6 models have a 1,050,000-token context window and 128K output.
- GPT-6 models accept image input.
- Reasoning effort ranges from
nonetomax. Ongpt-6.1-sol,maxbecomesxhigh. - Codex CLI works with a five-line provider block. See the Codex guide.
Quick start
curl https://7api.st/v1/chat/completions \
-H "Authorization: Bearer $SEVENAPI_API_KEY" -H "Content-Type: application/json" \
-d '{"model": "gpt-6-astra", "messages": [{"role": "user", "content": "Hello"}]}'Set the base URL to https://7api.st/v1 for OpenAI-format clients, or https://7api.st for Anthropic-format clients. See the quickstart for SDK examples.
Independent benchmarks
Scores published by third parties, not by 7API. See all benchmarks for sources and method.
| Model | Artificial Analysis Intelligence Index | Effort |
|---|---|---|
gpt-6-astra | 53 | max |
gpt-6.1-sol | 52 | max |
gpt-6-luna | 38 | max |
gpt-5.6-terra | 42 | max |
Is this the official OpenAI API?
No. 7API is an independent gateway that serves GPT models through OpenAI-compatible endpoints. You use a 7API key and pay from a 7API balance.
Which GPT model is cheapest?
Check the table above: the build lists the current rates. GPT-6 Luna is the lowest-cost GPT-6 model.
Does previous_response_id work?
Yes, on GPT models. It accepts IDs returned to your own account for the same model.
