> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.vapi.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vapi.ai/_mcp/server.

# What's New: Week of October 5, 2026

1. **OpenAI GPT-6 Luna**: OpenAI's [GPT-6 Luna](/providers/model/openai) (`gpt-6-luna`) is now available for assistants in the API and dashboard, with model-specific pricing, reasoning support, and fast service tier.

2. **ElevenLabs v4 Turbo**: The [`eleven_v4_turbo`](/providers/voice/elevenlabs) voice model is now available in the dashboard voice picker and the API.

3. **Deepgram nova-3-pharma**: Deepgram's [`nova-3-pharma`](/providers/transcriber/deepgram) transcription model is now available for assistants.

4. **Soniox low-confidence filter**: You can now set a [confidence threshold](/providers/transcriber/soniox#low-confidence-filter) on the Soniox transcriber to discard low-confidence transcripts, from the transcriber Advanced settings and via the API.

5. **Simulation latency expectations**: Simulations can now [set latency limits](/observability/simulations-advanced#set-latency-limits) for model, voice, and turn timing, fail runs that exceed them, and show measured latency results.

6. **Fixes and Improvements**:
   * **Visual prompt editor**: The visual prompt editor no longer alters nested or multi-line Liquid tags or section headings when switching modes or saving.
   * **Chat handoff variables**: Chat squad handoffs now extract variables from the chat conversation instead of overwriting valid handoff values.