An OpenAI long-context reasoning model for complex analysis, coding, and agent workflows.
Use openai/gpt-6-astra through the sjolt LLM API.
openai/gpt-6-astraToken rates
openai/gpt-6-astraSimilar Models
A fast DeepSeek model for text generation and reasoning tasks.
A DeepSeek model for text generation and reasoning tasks that need more capability.
Google’s fast reasoning model for agentic coding and complex knowledge workflows.
Model overview
Use a long-context reasoning model for complex analysis, coding, and agent workflows.
Use up to 1,050,000 tokens of context for large repositories, documents, and multi-step work.
Select low, medium, high, xhigh, or max reasoning effort to match the task.
Connect through OpenAI-compatible Chat Completions and Responses.
Model characteristics
Complex analysis, coding, and long-context agent workflows.
Up to 1,050,000 context tokens.
Up to 128,000 tokens.
Reasoning stays enabled with low, medium, high, xhigh, and max effort levels; the Playground defaults to medium.
FAQ
It is suited to complex analysis, coding, and long-context agent workflows.
No. Select low, medium, high, xhigh, or max effort instead.
The API supports up to 1,050,000 context tokens and up to 128,000 output tokens.
No. The SJProxyAPI route removes caller-selected output limits before forwarding the request.
sjolt exposes GPT-6 Astra through OpenAI-compatible Chat Completions and Responses.