Grok 4.20 Non-Reasoning (Batch)

spacexai/grok-4.20-non-reasoning-batch

A chat model with a 2M-token context window, at $1.05 per million input tokens and $2.10 per million output tokens.

Details

Maker: spacexai
Kind: Chat
Context window: 2,000,000 tokens
Max output: 2,000,000 tokens
Input: $1.05 per million tokens
Cached input: $0.168 per million tokens, 84% off
Cache write: Same as input
Output: $2.10 per million tokens
Capabilities: Tool use, vision, file input
Takes: Text, image, pdf
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-03-10

Description

Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "spacexai/grok-4.20-non-reasoning-batch",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model