2025-10-17 CometAPI Model Update Announcement

[tensornull]

We've added three powerful AI models, all supporting chat format calls to accelerate your AI application development!
New Models
Claude Haiku 4.5
Model ID: claude-haiku-4-5-20251001 / cometapi-haiku-4-5-20251001
Low Latency & High Throughput: Optimized for real-time, high-concurrency scenarios
Configurable Reasoning Depth: Supports "extended thinking" mode
Massive Context: Up to 200K input tokens, 8K output tokens
Strong Code Capabilities: Code generation, debugging, tool calling
Cost Advantage: ~1/3 the cost of Sonnet 4
Format Support: Claude native message format + chat format
GLM-4.6
Zhipu AI's latest flagship model with 355B total params, 32B active
Coding Excellence: Aligns with Claude Sonnet 4, best in China
Extended Context: Expanded from 128K to 200K tokens
Enhanced Reasoning: Supports tool calling during inference
Search Optimization: Improved tool calling and agent performance
Better Writing: Enhanced style, readability, and role-playing alignment
Multilingual: Boosted cross-language translation capabilities
Format Support: Chat format
Veo3.1 & Veo3.1-Pro
Google's latest AI video generation models for high-quality video creation
High Resolution: 1080p video generation
Synchronized Audio: Dialogue, ambient sounds, effects with native lip-sync
Video Length: Generate seamless clips up to 8 seconds
Creative Control: Reference image support, first/last frame setting, cinematic presets
Dual Variants: Veo3.1 (standard quality) + Veo3.1-Pro (maximum quality)
Format Support: Async calls + chat format
Quick Start
Get started now: https://www.cometapi.com/?utm_source=github&utm_medium=referral&utm_campaign=community_daily
Join our community: https://discord.com/invite/HMpuV6FCrG
All models support chat format calls, with Claude models additionally supporting native message format for maximum integration flexibility!