Grok 4.20 Multi-Agent
Deep-research slug that fans out multiple agents in parallel inside one API call - same per-token price as 4.20 but total token burn per request is far higher and rate limits are ~4x tighter (9 RPS / 2.5M TPM at Tier 0), so budget for it as a research tool, not a chat backend.
Data checked 2026-09-06
xAI
beta
grok-4.20-multi-agent-0309
- Context window
- 1M tokens in
- Max output
- —
- Input
- $1.25 per 1M tokens
- Output
- $2.50 per 1M tokens
- Cached input
- $0.20 per 1M tokens
- Blended
- $1.56 3:1 in:out
- Released
- 2026-03-10
- Licence
- proprietary
A What it is for
Long context (>=200K) bills $2.50/$0.40/$5.00.
At a three-to-one input-to-output ratio, Grok 4.20 Multi-Agent costs $1.56 per million tokens blended. A workload of one million input and 330,000 output tokens per day would run about $62.25 per month at list price, before caching or batch discounts.
B Capabilities
| Input modalities | text, image |
|---|---|
| Output modalities | text |
| Batch discount | 20% off asynchronous requests |
C Others from xAI
| Model | Context | Max out | In $/M | Out $/M | Blended | Status |
|---|---|---|---|---|---|---|
Grok 4.6
grok-4.6
|
500K | — | $2.00 | $6.00 | $3.00 | ga |
Grok 4.5
grok-4.5
|
500K | — | $2.00 | $6.00 | $3.00 | ga |
Grok 4.3
grok-4.3
|
1M | — | $1.25 | $2.50 | $1.56 | ga |
Grok Build 0.1
grok-build-0.1
|
256K | — | $1.00 | $2.00 | $1.25 | ga |
Grok 4.20 (Reasoning)
grok-4.20-0309-reasoning
|
1M | — | $1.25 | $2.50 | $1.56 | ga |
Grok 4.20 (Non-Reasoning)
grok-4.20-0309-non-reasoning
|
1M | — | $1.25 | $2.50 | $1.56 | ga |
Grok Imagine Image 2.0
grok-imagine-image-2.0
|
— | — | — | — | — | ga |
Grok Imagine Image
grok-imagine-image
|
— | — | — | — | — | ga |
Grok Imagine Image Quality
grok-imagine-image-quality
|
— | — | — | — | — | deprecated |
Grok Imagine Video 1.5
grok-imagine-video-1.5
|
— | — | — | — | — | ga |
Grok Imagine Video
grok-imagine-video
|
— | — | — | — | — | ga |
Grok Voice Think Fast 2.0
grok-voice-think-fast-2.0
|
— | — | — | — | — | ga |
D Verify before you commit
Model pricing changes without notice and this page is a snapshot. Confirm against the vendor's own page before you build a budget on it.
Source: docs.x.ai · checked 2026-09-06 · xAI pricing · API docs