Registry Live 2026

Supported AI Models

Compare capabilities of the latest generic and reasoning models powering your Bizzbly agents.

				Notes
Claude Haiku 4.0 `claude-haiku-4.0`	opencodezen	100k	Jun 2026	Fast model
GPT-5.2 `gpt-5.2`	openai	200k	May 2026	Flagship OpenAI model
GPT-5.2 `gpt-5.2`	opencodezen	200k	May 2026	Flagship OpenAI model via Zen
GPT-5.2 `openai/gpt-5.2`	openrouter	200k	May 2026	via OpenRouter
Claude Sonnet 4.5 `claude-sonnet-4.5`	anthropic	200k	Apr 2026	Balanced Anthropic model
Claude Sonnet 4.5 `claude-sonnet-4.5`	opencodezen	200k	Apr 2026	Balanced Anthropic model via Zen
Claude Sonnet 4.5 `anthropic/claude-sonnet-4.5`	openrouter	200k	Apr 2026	via OpenRouter
Claude 4.6 Opus `claude-4-6-opus`	anthropic	1M	Feb 2026	Ultimate context & reasoning
Claude Opus 4.6 `claude-opus-4.6`	opencodezen	500k	Feb 2026	High intelligence Anthropic model via Zen
GPT-5.1 Codex `gpt-5.1-codex`	opencodezen	128k	Feb 2026	Specialized coding model from OpenAI
Claude `claude`	opencodezen	200k	Feb 2026	Generic Claude alias
Gemini 3 Pro `gemini-3-pro`	opencodezen	2M	Feb 2026	Gemini 3 Pro alias
Gemini 3 Flash `gemini-3-flash`	gemini	2M	Jan 2026	Fast reasoning Google model
Gemini 3 Flash Preview `gemini-3-flash-preview`	gemini	1M	Jan 2026	Next-gen thinking model
Gemini 3 Flash `gemini-3-flash`	opencodezen	2M	Jan 2026	Fast reasoning Google model via Zen
Gemini 3 Flash `google/gemini-3-flash`	openrouter	2M	Jan 2026	via OpenRouter
Qwen 3 Coder `qwen3-coder`	opencodezen	200k	Jan 2026	Alibaba Top coding model
Gemini 3.0 Pro `gemini-3.0-pro`	gemini	4M	Jan 2026	Infinite Context Agent
Gemini 3.0 Pro `gemini-3.0-pro`	opencodezen	4M	Jan 2026	Infinite context Google model via Zen
GPT-5 Pro `gpt-5-pro`	openai	500k	Jan 2026	Next-gen reasoning
MiniMax M2.1 `minimax-m2.1`	opencodezen	256k	Nov 2025	High capability Chinese model via Zen
Gemma 3 27B `google/gemma-3-27b-it`	openrouter	96k	Oct 2025
Gemini 2.5 Flash `gemini-2.5-flash`	gemini	1M	Sep 2025	Incremental Speedup
Claude 4 Opus `claude-4-opus-20250522`	anthropic	500k	May 2025	High reasoning specialist
Gemini 2.0 Pro `gemini-2.0-pro`	gemini	2M	Feb 2025	High intelligence 2025
Gemini 2.0 Flash `gemini-2.0-flash`	gemini	1M	Jan 2025	Standard for 2025
Claude 3.5 Sonnet v2 `claude-3-5-sonnet-20241022`	anthropic	200k	Oct 2024	Upgraded balanced intelligence
Llama 3.2 `llama3.2`	ollama	128k	Sep 2024	Vision support for small models
Mistral Small 3.2 `mistralai/mistral-small-3.2-24b-instruct`	openrouter	128k	Sep 2024
GPT-4o Mini `gpt-4o-mini`	openai	128k	Jul 2024	Affordable compact
Claude 3.5 Sonnet `claude-3-5-sonnet-20240620`	anthropic	200k	Jun 2024	Balanced intelligence
Gemini 1.5 Flash `gemini-1.5-flash`	gemini	1M	May 2024	Fast multimodal
GPT-4o `gpt-4o`	openai	128k	May 2024	Fast omni model
GPT-4 Turbo `gpt-4-turbo`	openai	128k	Apr 2024	High intelligence
Claude 3 Opus `claude-3-opus-20240229`	anthropic	200k	Mar 2024	High intelligence
Gemini 1.5 Pro `gemini-1.5-pro`	gemini	2M	Feb 2024	Long context specialist

Data verified for 2026. Models marked "Deprecated" may still be available via API but are no longer recommended.

Capability Legend

VisionCan analyze images, screenshots, and visual inputs.
ToolsCan perform actions like web search and database queries.
JSONGuaranteed structured data output for integrations.

Note on Reasoning Models

Models like o3 and DeepSeek R1 are specialized for complex logic. They may have higher latency and are best used for "Assistant" personas rather than real-time "Sales" agents.

⚠️Reasoning models may take 10-30s to respond.