SpaceXAI: Grok 4.20 Multi-Agent
x-ai/grok-4-20-multi-agentGrok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows.
Modalities
In / out per 1M$1.25 / $2.50
Context1.9M
ReleasedMar 31, 2026
Providers
4 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $1.25 | $2.50 | $0.20 | 8.56s | 454 tps | 100% | |
| $1.25 | $2.50 | $0.20 | 2.42s | 429 tps | 75.86% | |
| $2.50 | $5.00 | $0.40 | — | — | — | |
| $2.50 | $5.00 | $0.40 | — | — | — |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Grok 4.20 Multi-Agent in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Grok 4.20 Multi-Agent costs pay-as-you-go elsewhere, not what you pay here.
Input
$1.25
per 1M tokens
Output
$2.50
per 1M tokens
Cache read
$0.20
per 1M cached tokens
Included in every pass
Grok 4.20 Multi-Agent is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s10.0s20.0s30.0s40.0s
Oct 29, 3 AMOct 29, 8 AMOct 29, 11 AMOct 29, 3 PMOct 30, 3 PMOct 30, 5 PMOct 30, 8 PMNov 1, 1 PM
SpaceXAI SpaceXAI
0 tok/s200 tok/s400 tok/s600 tok/s800 tok/s
Oct 29, 3 AMOct 29, 8 AMOct 29, 11 AMOct 29, 3 PMOct 30, 3 PMOct 30, 5 PMOct 30, 8 PMNov 1, 1 PM
SpaceXAI SpaceXAI
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.96%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 100%
100% 98% 97% 95%
Oct 31, 6:10 PMNow
Apps
Tools that most often run Grok 4.20 Multi-Agent, by tokens this week.
Activity
5.1B tokens processed market-wide in the last month.
0200.0M400.0M600.0M800.0M
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens
FAQ
Which model id do I use for Grok 4.20 Multi-Agent?
x-ai/grok-4.20-multi-agent. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does Grok 4.20 Multi-Agent hold?
2,000,000 tokens per request, of which up to 1,800,000 can be the response.
What can it accept and return?
Input: text, image, file. Output: text.
What does Grok 4.20 Multi-Agent cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $1.25 per 1M input tokens and $2.50 per 1M output tokens.
How current is its knowledge?
Training data runs to Sep 2025. Anything later has to come from your prompt or a tool call.
Who built Grok 4.20 Multi-Agent?
SpaceXAI, in the Grok family.
Explore
Other models your pass can call.
