Grok 4.20 Multi Agent Experimental beta latest

xAI responses

Grok 4.20 Multi Agent Experimental beta latest is a xAI responses-API model.It supports a 1,000,000-token context windowwith up to 1,000,000 output tokens.Input is priced at $1.25/M tokens and output at $2.50/M tokens. Capabilities include vision, reasoning, prompt caching. Route Grok 4.20 Multi Agent Experimental beta latest via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.

Pricing source: litellm Last verified: Oct 22, 2026 View source ↗
Cost calculator

Estimate Grok 4.20 Multi Agent Experimental beta latest spend

Pick a workload, fine-tune the sliders, and see the monthly bill.

~3K in / ~400 out · 5K req/day
3,000
01,000,000
400
0200,000
5,000
01,000,000
cached @ $0.2000/M
Per request
$0.004750
in $0.003750 · out $0.001000
Per day
$23.75
5,000 requests
Per month
$723
152,188 requests

Estimate uses $1.25/M input · $2.50/M output. Provider pricing changes. Production costs vary with retries, streaming overhead, and tool-call rounds.
Want this for free? Cache + route via Agent Command Center — first 100K requests and 100K cache hits free every month.

Pricing

Per-token rates, expressed in USD per 1M tokens. Verified Oct 22, 2026.

Input $1.25/M
Output $2.50/M
Blended (3:1 in:out) $1.56/M
Cross-model comparable price
Cached input $0.200/M

Context & limits

Context window
1,000,000 tokens
Max input
1,000,000 tokens
Max output
1,000,000 tokens
Modalities
vision, text

Capabilities

  • Function calling — not advertised
  • Parallel tool calls — not advertised
  • Vision input ✓ supported
  • Audio input — not advertised
  • Audio output — not advertised
  • PDF input — not advertised
  • Streaming ✓ supported
  • Structured output ✓ supported
  • Prompt caching ✓ supported
  • Reasoning ✓ supported

Strengths & caveats — when to pick Grok 4.20 Multi Agent Experimental beta latest

Data-driven from Grok 4.20 Multi Agent Experimental beta latest's percentile within responses peers.

Where it's strong

  • +long-context tasks — context window in the top 8% of peers
  • +long-form generation — 1,000,000-token max output, top-0% of peers

Watch out for

  • No major caveats flagged from public spec.

Benchmarks pending

We haven't logged public benchmark scores for Grok 4.20 Multi Agent Experimental beta latest yet. Have one to contribute? Submit a source — citations help us prioritise.

Try it

Call Grok 4.20 Multi Agent Experimental beta latest via Agent Command Center

One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.

SDK
Native Future AGI client (agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.
# Grok 4.20 Multi Agent Experimental beta latest via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC

client = AgentCC(
    api_key=os.environ["AGENTCC_API_KEY"],   # from app.futureagi.com → Settings → API Keys
    base_url="https://gateway.futureagi.com/v1",
)

resp = client.chat.completions.create(
    model="xai/grok-4-20-multi-agent-experimental-beta-latest",
    messages=[{"role": "user", "content": "Hello, Grok 4.20 Multi Agent Experimental beta latest!"}],
)

print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")

# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
    model="xai/grok-4-20-multi-agent-experimental-beta-latest",
    messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost:   ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache:  ", raw.headers.get("x-agentcc-cache"))
Set AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗

Explore similar models

Grok 4.20 Multi Agent Experimental beta latest doesn't have a public Arena ELO score yet, so we group by provider only — quality-tier comparisons need a benchmark. Side-by-side links appear where a comparison page exists; otherwise, open the model profile.

FAQ

How much does Grok 4.20 Multi Agent Experimental beta latest cost?

Input is priced at $1.25 per 1M tokens and output at $2.50 per 1M tokens (xAI, last verified Oct 22, 2026).

What is the context window of Grok 4.20 Multi Agent Experimental beta latest?

Grok 4.20 Multi Agent Experimental beta latest supports a 1,000,000-token context window with up to 1,000,000 output tokens.

Does Grok 4.20 Multi Agent Experimental beta latest support function calling?

Grok 4.20 Multi Agent Experimental beta latest does not currently advertise function-calling support. For agentic workloads, prefer a tool-calling-capable model and route via Agent Command Center for fallback.

Is Grok 4.20 Multi Agent Experimental beta latest good for production?

Grok 4.20 Multi Agent Experimental beta latest is well-suited for long-context tasks — context window in the top 8% of peers and long-form generation — 1,000,000-token max output, top-0% of peers.

How can I route to Grok 4.20 Multi Agent Experimental beta latest with fallback?

Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.

Useful links for Grok 4.20 Multi Agent Experimental beta latest

Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.