Grok 4.20 Multi-Agent
xAI · released Mar 31, 2026
- Type
- Proprietary
- Input
- $1.25
- Output
- $2.50
- Cached
- $0.20
List price · per 1M tokens · xAI at 2M context · source ↗
Our take
Written Aug 3, 2026Grok 4.20 Multi-Agent is xAI's proprietary flagship that handles text, images and files with a two-million-token request limit. It leads its own coding benchmark suite and is built for multi-agent workflows, though it comes at a premium price and its weights cannot be downloaded.
Pick this for frontier-class coding or long-document analysis at two million tokens, and for multi-agent orchestration. Skip it if your budget cannot absorb premium output rates, if you need strong creative writing scores, or if you require downloadable weights.
The case for it
- Two-million-token request limit, among the largest for frontier-class models.
- Highest coding score in its own benchmark suite at 1508.99 Elo, 38 points above its general text score.
- Day-to-day leaderboard consistency within a tenth of a point on both text and coding.
- Direct provider throughput of 563 tokens per second on the cheapest tracked tier.
The case against it
- Premium pricing with a wide spread across tiers, creating cost uncertainty.
- Creative writing and instruction following lag well behind its coding performance, by over 60 points each.
- Proprietary weights with no disclosed licence; cannot be self-hosted or redistributed.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)17th of 143 · 1470.9
CodingWriting and fixing code on its own
Arena Coding24th of 143 · 1509
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Grok 4.20 Multi-Agent for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Grok 4.20 Multi-Agent placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Or rent it from someone else
Why this differs from the header. The strip above quotes xAI's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $1.25 in / $2.50 out
- Context served
- 2M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $1.25 / $2.50 | 2M | not measured | Unknown | Unknown | Unknown |
| xAI | $1.25 / $2.50 | 2M | 572 tok/s | No | Yes30 days | Confirmed |
| xAIpriority tier | $2.50 / $5.00 | 2M | not measured | No | Yes30 days | Unknown |
| xAI | $2.00 / $6.00 | 2M2M out | not measured | Unknown | Unknown | Unknown |
xAIAcross the 4 listings we hold: 2 say they do not train on prompts, 0 say they do and 2 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✓ |
| xAI | ✗ | ✓ | ✓ |
| xAIpriority | ✗ | ✓ | ✓ |
| xAI |
Tool calling: 0 of 4 listings say yes, 3 say no, 1 publishes no parameter list. JSON output: 3 of 4 listings say yes, 1 publishes no parameter list. Strict schema: 3 of 4 listings say yes, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- 1 of 4 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 4 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image+file->text
- Catalogue slug
- x-ai-grok-4-20-multi-agent