Grok 4.20 Multi Agent
Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows.
grok-4.20-multi-agentReleased 31 Mar 2026 (Mar 2026)Pricing
List prices at xAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.25 | $2.50 | |
| Cached input 84% off input | $0.20 | 84% off input | |
| Batch 20% off | $1.00 | $2.00 | 20% off |
| Prompts over 200K tokens | $2.50 | $5.00 |
What it costs a month
At xAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$468
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$438
- Coding agent1,000 requests a day, 40K in / 2K out, cached$768
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$2,880
Where to run it
4 hosts serve Grok 4.20 Multi Agent. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
xAILab API grok-4.20-multi-agent | $1.25 / $2.50 | grok-4.20-multi-agent | |
PerplexityGateway grok-4.20-multi-agent | $1.25 / $2.50 | grok-4.20-multi-agent | |
Kyma APICloud grok-4.20-multi-agent | $1.77 / $3.53 +41% vs headline | grok-4.20-multi-agent | |
Oracle OCICloud xai.grok-4.20-multi-agent | $3.00 / $15.00 +284% vs headline | xai.grok-4.20-multi-agent |
Show 2 more listings: regions, snapshots and variantsHide regional listings
| xAI | |||||||
| Alias grok-4.20-multi-agent-latest | $1.25 / $2.50 | grok-4.20-multi-agent-latest | |||||
| 0309 grok-4.20-multi-agent-0309 | $1.25 / $2.50 | grok-4.20-multi-agent-0309 | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Features
- Prompt cachingBuilt-in web search
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than xAI.
Smaller xAI models
- 20% less
- 20% less
Other frontier labs
- 4% less
- 70% less
- 87% less
- 46% less
Open-weight picks
- 56% less
- 59% less
- 66% less
- 69% less
Call it
Using xAI's API.
import os
from openai import OpenAI
client = OpenAI(base_url="https://api.x.ai/v1", api_key=os.environ["XAI_API_KEY"])
completion = client.chat.completions.create(
model="grok-4.20-multi-agent",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)from litellm import completion
response = completion(
model="xai/grok-4.20-multi-agent",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Grok 4.20 Multi Agent cost?
On xAI, Grok 4.20 Multi Agent costs $1.25 per million input tokens and $2.50 per million output tokens. Cached input costs $0.20 per million tokens.
Which APIs offer Grok 4.20 Multi Agent?
Grok 4.20 Multi Agent runs on 4 APIs: xAI, Perplexity, Kyma API and Oracle OCI.
What is Grok 4.20 Multi Agent's context window?
1M tokens, with up to 1M tokens in one reply.
Is Grok 4.20 Multi Agent being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Grok 4.20 Multi Agent?
Models that cost less and keep most of what it can do: Grok Build 0.1 on xAI (20% less), Gemini 3.8 Flash on Google AI Studio (4% less), GPT-5.4 Nano on OpenAI (70% less) and Kimi K2.7 Code on CLF AI Gateway (56% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Grok 4.20 Multi Agent released?
xAI released it on 31 Mar 2026.
What is Grok 4.20 Multi Agent's API model id?
Use grok-4.20-multi-agent with xAI. Other hosts use their own ids: xai.grok-4.20-multi-agent on Oracle OCI.
Sources
Raw catalog entry for grok-4.20-multi-agent on xAI
{
"cache_read_input_token_cost": 2e-7,
"cache_read_input_token_cost_batches": 1.6e-7,
"input_cost_per_token": 0.00000125,
"input_cost_per_token_batches": 0.000001,
"litellm_provider": "xai",
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"mode": "responses",
"output_cost_per_token": 0.0000025,
"output_cost_per_token_batches": 0.000002,
"source": "https://api.x.ai/v1/language-models",
"supported_endpoints": [
"/v1/responses"
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": false,
"supports_vision": true,
"supports_web_search": true,
"input_cost_per_token_above_200k_tokens": 0.0000025,
"input_cost_per_token_above_200k_tokens_batches": 0.000002,
"output_cost_per_token_above_200k_tokens": 0.000005,
"output_cost_per_token_above_200k_tokens_batches": 0.000004,
"cache_read_input_token_cost_above_200k_tokens": 4e-7,
"cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7,
"input_cost_per_image_token": 0.00000125,
"supports_response_schema": true
}