AI TOOLS RADAR
Submit
All models / X-AI
x-ai logo
x-ai

SpaceXAI: Grok 4.20 Multi-Agent

Source description (English)

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...

View source on OpenRouter
Overview

Model specifications

Context
2,000,000 tokens
Maximum output
1,800,000 tokens
Architecture
text+image+file->text
Tokenizer
Grok
Knowledge cutoff
2025-09-01
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$1.25
per 1M tokens
  • ≤200K$1.25
  • >200K$2.5
Output
$2.5
per 1M tokens
  • ≤200K$2.5
  • >200K$5
Cache read
$0.2
per 1M tokens
  • ≤200K$0.2
  • >200K$0.4
Web search
$5
per 1,000 calls
API

Model configuration

Reasoning

Reasoning required
Yes
Default parameters
medium
Capabilities
xhigh, high, medium, low
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"x-ai/grok-4.20-multi-agent","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimagefile
Output
text
Reasoning

Yes · xhigh · high · medium · low

API

Supported API parameters

include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetop_logprobstop_p
Available providers

4 providers

Checked: September 7, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

xAI

Not provided
Context
2M
Maximum output
1.8M
Input
$1.25
Output
$2.5
Cache read
$0.2
Cache write
Not provided

xAI

Not provided
Context
2M
Maximum output
1.8M
Input
$1.25
Output
$2.5
Cache read
$0.2
Cache write
Not provided

xAI

Not provided
Context
2M
Maximum output
1.8M
Input
$2.5
Output
$5
Cache read
$0.4
Cache write
Not provided

xAI

Not provided
Context
2M
Maximum output
1.8M
Input
$2.5
Output
$5
Cache read
$0.4
Cache write
Not provided
x-ai

4 models

All models
x-ai logox-ai

SpaceXAI: Grok 4.7

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...

Context
500K
Input
text · image · file
Output
text
Input: $1.6Output: $4.8per 1M tokens
View model details →
x-ai logox-ai

SpaceXAI: Grok 4.6

Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.

Context
500K
Input
text · image · file
Output
text
Input: $2Output: $6per 1M tokens
View model details →
x-ai logox-ai

xAI: Grok Imagine Image 2.0

Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and...

Context
66K
Input
text · image
Output
image
Image input: $0.01 per imageImage output: $0.04 per image
View model details →
x-ai logox-ai

SpaceXAI: Grok STT 1.0

Grok STT is SpaceXAI's speech-to-text model, available via the REST /v1/stt endpoint. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.

Context
Not provided
Input
audio
Output
transcription
Audio seconds: $0.000028 per second
View model details →