xAI · Released Mar 31, 2026
Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent is a variant of SpaceXAI’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...
- Released
- Mar 31 2026
- Context window
- 2M 1.8M out
- Input / 1M tokens
- $1.25
- Output / 1M tokens
- $2.50
Where to run it
6 providers compared
Cheapest: xAI, NanoGPT, Kilo Gateway +1 more at $1.25 / $2.50 per 1M input / output tokens — 50% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| xAIzdr · no tool calling | $1.25 | $2.50 | $0.20 | 2M | 1.8M | 100%24h | Cheapest |
| xAIno tool calling | $1.25 | $2.50 | $0.20 | 2M | 1.8M | 72.7%24h | Cheapest |
| NanoGPT | $1.25 | $2.50 | $0.20 | 2M | 131K | — | Cheapest |
| Kilo Gatewayno tool calling | $1.25 | $2.50 | $0.20 | 2M | 1.8M | — | Cheapest |
| Vercel AI Gateway | $1.25 | $2.50 | $0.20 | 2M | 2M | — | Cheapest |
| Poe | $1.26 | $2.52 | $0.20 | 128K | — | — | +1% |
| Venice AIno tool calling | $1.42 | $2.83 | $0.23 | 2M | 128K | — | +13% |
| xAIzdr/priority · no tool calling | $2.50 | $5.00 | $0.40 | 2M | 1.8M | — | +100% |
| xAIpriority · no tool calling | $2.50 | $5.00 | $0.40 | 2M | 1.8M | — | +100% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Grok 4.20 Multi-Agent. Scores appear here automatically once it does.
Specs
Details
- Model ID
x-ai/grok-4.20-multi-agent- Developer
- xAI
- Release date
- Mar 31, 2026 ·
- Context window
- 2,000,000 tokens
- Max output
- 1,800,000 tokens
- API price
- $1.25 / $2.50 per 1M input / output tokens
- Providers
- 6
- Input types
- text, image, file
- Reasoning
- Yes
- Tool calling
- No
- Open weights
- No
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.