News and updates
Incidents and planned maintenance, new models and gateway capabilities, pricing changes — everything worth knowing before your project notices it.
- ReleaseSeptember 18, 2026
Long streamed answers now arrive in full
A stream is no longer capped by total response time: it stays alive as long as the model keeps sending and is cut only after a pause longer than 4 minutes. Long answers from reasoning models and agents arrive complete. Dropped streams now show up on the status page.
Read → - NewsSeptember 17, 2026
Long streamed answers now arrive in full
A stream is no longer capped by total response time: it stays alive as long as the model keeps sending and is cut only after a pause longer than 4 minutes. Long answers from reasoning models and agents arrive complete. Dropped streams now show up on the status page.
ReleaseSeptember 15, 2026
GPT-6 Astra on ApiMira - pricing, context limit and working streaming code
GPT-6 Astra is live in the ApiMira catalog at $0.50 per million input tokens and $2.25 per million output. Where it beats Claude Fable 5.1, what to strip from your request before you switch, and why it breaks your timeouts without streaming.