v0.5.35

QwenAudio/SenseVoicev0.5.35Jul 16, 2026by decolua

AI Summary

Feature additions including Grok Imagine video generation, Claude route improvements, and internationalization support.

Key Highlights

Added Grok Imagine video generation (/v1/videos) with CLI support
Enabled Claude models to route through Copilot native /v1/messages
Added GPT-5.6 model family support
Added Thai (th) and Persian (fa) translations
Improved direct session cache reuse for Kiro

New Features

Grok Imagine video generation
Claude route through Copilot
GPT-5.6 model family
Internationalization (Thai and Persian)
X-9Router-Token-Saver header for token savers bypass

Full Release Notes

Features:
- xAI: Grok Imagine video generation (/v1/videos) + CLI
- CLI tools: Grok Build setup — writes [model.9router] to ~/.grok/config.toml
- GitHub Copilot: route Claude models through Copilot native /v1/messages
- Kiro: add GPT-5.6 model family (#2596)
- RTK: X-9Router-Token-Saver header to bypass token savers per request
- Providers: quota visibility settings
- Translator: drop temperature for all Claude models
- i18n: Thai (th) + Persian (fa) translations / README

Fixes:
- Providers: bulk-add API keys no longer overwrite existing keys (gap-fill Key N)
- Anthropic: lowercase anthropic-version header to prevent duplication on /v1/messages
- Alicode-intl: use DashScope compatible-mode endpoint so standard keys work
- Grok CLI: align Grok Build with current subscription protocol (#2590)
- Grok CLI: surface expiresAt so proactive token refresh fires (#2546)
- Kiro: improve direct session cache reuse
- Models: populate capabilities for live-catalog LLM models
- Models: list compatible provider models in /v1/models
- Thinking: send explicit thinking:{type:adaptive} alongside output_config.effort
- Translator: strip client_metadata when converting openai-responses to openai

Improvements:
- Perf: skip inactive background services on startup

Docs:
- README: Persian YouTube tutorial