Grok 4.20 Multi-Agent
xAIdocs.x.ai/developers/models/grok-4.20-multi-agen
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...
Updated 4 h ago · first seen 11 Sept 2026
model_01M294WW227TBTN9Q3PY5N8PCX
- Context
- 1M tokens
- T1 · 4 h ago
- Released
- 31 Mar 2026
- T2 · 6 h ago
- Knowledge cutoff
- Sept 2025
- T2 · 6 h ago
Specification
- Family
- Grok
Source:xAI — docsT1observed 4 h agohigh
- Release date
- 31 Mar 2026
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Context window
- 1M tokens
Source:xAI — docsT1observed 4 h agohigh
- Max output
- 1.8M tokens
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Knowledge cutoff
- Sept 2025
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Input modalities
- text, image
Source:xAI — docsT1observed 4 h agohigh
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Tokenizer
- Grok
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- API model id
- grok-4.20-multi-agent-0309
Source:xAI — docsT1observed 4 h agohigh
- Official page
Source:xAI — docsT1observed 4 h agohigh
- Batch api
- Yes
Source:xAI — docsT1observed 4 h agohigh
- File input
- Yes
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Openrouter id
- x-ai/grok-4.20-multi-agent
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Regions
- us-east-1, us-west-2
Source:xAI — docsT1observed 4 h agohigh
- Supported parameters
- include_reasoning, logprobs, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, temperature, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
21
Source tiers
T1T28 / 13
Freshest observation
4 h ago
Conflicts
6 flagged
Modalities
- Modalities
- imagetext
- Input
- textimage
- Output
- text
Capabilities
Tool calling
Yes
xAI — docs · T1
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 1M tokens
Source:xAI — docsT1observed 4 h agohigh
- Max output
- 1.8M tokens
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Knowledge cutoff
- Sept 2025
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Tokenizer
- Grok
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| xAI APIgrok-4.20-multi-agent-0309 | $1.25 | $2.5 | $0.20 | $1 / $2 | 1M | 2 h ago | docs.x.aiT1 |
| xAI APIx-ai/grok-4.20-multi-agent | $1.25 | $2.5 | $0.20 | — | 2M | 2 h ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- xAI API
No hardware estimate available
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Tool calling
Tool callingtool_calling4conflicting claims
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| No | → current | conflicting | OpenRouter public model & pricing listingT2 | medium | deterministic |
| No | → current | conflicting | OpenRouter public model & pricing listingT2 | medium | deterministic |
| Yes | → current | current | xAI — docsT1 | conflicted | deterministic |
| No | → | superseded | OpenRouter public model & pricing listingT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
xAI API lists Grok 4.20 Multi-Agent at $1.25 in / $2.5 out per 1M tokens
xaiGrok 4.20 Multi-Agent: tool calling changed from false to true
Tool callingNo→YesxaiGrok 4.20 Multi-Agent: context length changed from 2000000 to 1000000
Context window2M tokens→1M tokensxaiGrok 4.20 Multi-Agent: modalities input changed from ["image", "text"] to ["text", "image"]
Input modalitiesimage, text→text, imagexaixAI API lists Grok 4.20 Multi-Agent at $1.25 in / $2.5 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| xAI — docs | docs.x.ai/developers/models/grok-4.20-multi-agent-0309.md | model_page | T1· Official | 2 h ago | 1 |
| xAI — docs | docs.x.ai/developers/models | model_docs | T1· Official | 2 h ago | 3 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 2 h ago | 4 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.