Compare models
Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.
| Attribute | grok-4.20-multi-agent-beta |
|---|---|
| Pricing | |
| Input | $2.00 / 1M |
| Output | $6.00 / 1M |
| Cache Write (5m) | $2.00 / 1M Default rate |
| Cache Write (1h) | $2.00 / 1M Default rate |
| Cache Read | $2.00 / 1M Default rate |
| Web Search | No surcharge |
| Context | |
| Max context | 2M |
| Max output | Unknown |
| Capabilities | |
| Vision | Yes |
| Function Calling | Yes |
| JSON Mode | Yes |
| Streaming | Yes |
| Catalogue | |
| Provider | xAI |
| Category | chat |
| Charge type | Pay As You Go |
| Released | — |
| Description | |
| Summary | Grok 4.20 Multi-Agent Beta is a specialized variant of SpaceXAI's Grok 4.20 designed for collaborative, agent-based workflows. It enables multiple agents to operate in parallel, coordinating tool use and information synthesis to handle complex tasks. Optimized for deep research and multi-step problem solving, the model supports parallel reasoning, coordinated execution, and structured knowledge synthesis across large and complex workflows. |