The model docs now list openai/gpt-6-astra at $10.00 per million input tokens and $50.00 per million output tokens up to 272k input tokens, with flex and priority tiers.
The model docs list perplexity/deepseek-v4-pro-0813 at $1.32 per million input tokens, $0.044 per cached input token million, and $3.96 per million output tokens. It is also available through the Orchestrator API.
The xhigh level stays on Claude Opus 5.5 with GPT-6.1 Sol as fallback. Context compaction starts at 150,000 tokens, and it no longer sends a system prompt.
