Updated venice models

[jooray]

• I have read CONTRIBUTING.md.
• I have created a discussion that was approved by a maintainer (for new features).

[Copilot]

Pull request overview

This PR updates the Venice AI provider configuration by modifying existing model specifications and adding 8 new models. The changes include reduced pricing for existing models, standardized default_max_tokens values, and expanded context windows for some models.

• Updated pricing and token limits for 5 existing Venice models
• Added 8 new models including Qwen variants, Gemma, OpenAI GPT OSS, GLM, and DeepSeek R1
• Standardized default_max_tokens to 16384 across all models

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[kujtimiihoxha]

@jooray thanks for the PR, will see if can get #137 in, this will keep the models always up to date.