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 Betagrok-4.20-multi-agent-beta | Gemini 3.5 Transcribegemini-3.5-transcribe | Transcribe 1 Protranscribe-1-pro |
|---|---|---|---|
| Pricing | |||
| Input | $2.00 / 1M | — Not priced per input token | — Not priced per input token |
| Output | $6.00 / 1M | — Not priced per output token | — Not priced per output token |
| Cache Write (5m) | $2.00 / 1M | Not applicable | Not applicable |
| Cache Write (1h) | $2.00 / 1M | Not applicable | Not applicable |
| Cache Read | $2.00 / 1M | Not applicable | Not applicable |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 2M | 98.3K | N/A |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | Yes | Yes | No |
| Function Calling | Yes | Yes | No |
| JSON Mode | Yes | No | No |
| Streaming | Yes | No | No |
| Catalogue | |||
| Provider | xAI | Fish Audio | |
| Category | chat | voice | voice |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | 2026-09-25 | 2026-09-24 |
| Description | |||
| Summary | Grok 4.20 Multi-Agent Beta is a specialized variant of xAI'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. | Google Gemini 3.5 Transcribe speech-to-text. Billed per input and output token. | Fish Audio Transcribe 1 Pro speech-to-text with speaker labels; transcripts include speaker tags such as <|speaker:0|>. Billed per second of audio. |