Grok 4.20 Beta

Grok 4.20 Beta is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses. Reasoning can be enabled/disabled using the reasoning enabled parameter in the API.

Grok 4.20 Multi-Agent Beta

Grok 4.20 Multi-Agent Beta is a variant of xAI's Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks. Reasoning effort controls agent count: low/medium uses 4 agents, high/xhigh uses 16 agents.

Grok Code Fast 1

Grok Code Fast 1 model integrated via automation on 2025-08-26

xAI: Grok 4

Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not exposed, reasoning cannot be disabled, and the reasoning effort cannot be specified.

Grok 3 Mini Beta

Grok 3 Mini is a lightweight, smaller thinking model ideal for reasoning-heavy tasks that don't demand extensive domain knowledge. It shines in math-specific and quantitative use cases. Transparent 'thinking' traces accessible.

Grok 3 Beta

Grok 3 Beta is xAI's flagship model excelling at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science. Outperforms Grok 3 Mini on high thinking tasks.

Grok 4.20 Beta

Grok 4.20 Beta is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses. Reasoning can be enabled/disabled using the reasoning enabled parameter in the API.

Grok 4.20 Multi-Agent Beta

Grok 4.20 Multi-Agent Beta is a variant of xAI's Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks. Reasoning effort controls agent count: low/medium uses 4 agents, high/xhigh uses 16 agents.

Grok Code Fast 1

Grok Code Fast 1 model integrated via automation on 2025-08-26

xAI: Grok 4

Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not exposed, reasoning cannot be disabled, and the reasoning effort cannot be specified.

Grok 3 Mini Beta

Grok 3 Mini is a lightweight, smaller thinking model ideal for reasoning-heavy tasks that don't demand extensive domain knowledge. It shines in math-specific and quantitative use cases. Transparent 'thinking' traces accessible.

Grok 3 Beta

Grok 3 Beta is xAI's flagship model excelling at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science. Outperforms Grok 3 Mini on high thinking tasks.