Older models removed from the model docs; GPT-6 Astra and DeepSeek V4 Pro added
By Steven Van ·
Perplexity's Agent API docs drop old Claude, Gemini and Grok models, and list GPT-6 Astra at $10 per million input tokens and DeepSeek V4 Pro at $1.32.
Perplexity has removed 16 older models from the Perplexity Agent API model docs, pricing calculator and examples, and added two: OpenAI's GPT-6 Astra and DeepSeek V4 Pro.
Models no longer listed
- Anthropic: anthropic/claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-opus-4-5, claude-sonnet-4-6, claude-sonnet-4-5 and claude-haiku-4-5
- Google: google/gemini-3-flash-preview, gemini-3.1-pro-preview, gemini-3.1-flash-lite, gemini-3.5-flash and gemini-3.5-flash-lite
- xAI: xai/grok-4.3, grok-4.20-reasoning, grok-4.20-non-reasoning and grok-4.20-multi-agent
For new integrations, the model docs point to anthropic/claude-opus-5-5, anthropic/claude-sonnet-5-5, anthropic/claude-haiku-5-5, google/gemini-4-argon, google/gemini-3.8-flash or xai/grok-4.7.
New in the model docs
openai/gpt-6-astra costs $10.00 per million input tokens and $50.00 per million output tokens up to 272k input tokens. It supports the flex and priority service tiers.
perplexity/deepseek-v4-pro-0813 costs $1.32 per million input tokens, $0.044 per million cached input tokens and $3.96 per million output tokens. It is also available through the Orchestrator API.