Grok 4.20 Beta Non-Reasoning (0309) API

Model details

Context window

2M tokens

Max output

30K tokens

Input

Text, images

Output

Text

Capabilities

Vision, Tool calling, Streaming, JSON output

Interfaces

OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Why teams pick it

• Grok 4.20 Beta Non-Reasoning (0309) for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call Grok 4.20 Beta Non-Reasoning (0309)

Grok 4.20 Beta Non-Reasoning (0309) answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "grok-4-20-beta-0309-non-reasoning",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "grok-4-20-beta-0309-non-reasoning",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "grok-4-20-beta-0309-non-reasoning",
  "input": "Hello"
}'

Use Grok 4.20 Beta Non-Reasoning (0309) in your tools

Every coding agent below has a setup guide. Set the model to grok-4-20-beta-0309-non-reasoning.

• Claude Code
• Codex
• opencode
• Cline
• Roo Code
• Aider
• Continue

More from xAI

Alternatives to Grok 4.20 Beta Non-Reasoning (0309)

• Qwen3.8 MaxAlibaba's flagship MoE, built for coding and long-horizon agents.Alibaba
• Fugu MaxFugu Max for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Sakana AI
• Mistral Medium 3.5Mistral Medium 3.5 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Mistral

Questions about this model

How much does the Grok 4.20 Beta Non-Reasoning (0309) API cost?

Grok 4.20 Beta Non-Reasoning (0309) costs $2 per 1M input tokens and $6 per 1M output tokens on Inferray, and cached input is $0.2 per 1M. That is the list price, with no gateway fee on top.

Is there a free tier for Grok 4.20 Beta Non-Reasoning (0309)?

No. You add credit and pay Grok 4.20 Beta Non-Reasoning (0309)'s list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.

Am I charged for failed requests?

No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.

Is Grok 4.20 Beta Non-Reasoning (0309) included in Token Plans?

No. Grok 4.20 Beta Non-Reasoning (0309) is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use Grok 4.20 Beta Non-Reasoning (0309) in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to grok-4-20-beta-0309-non-reasoning. The same key works in Codex, opencode, Cline, and other agents.

Does Grok 4.20 Beta Non-Reasoning (0309) support tool calling and vision?

Grok 4.20 Beta Non-Reasoning (0309) supports tool calling, image input, JSON output and streaming on Inferray.

Is it the real Grok 4.20 Beta Non-Reasoning (0309)?

Yes. A request for grok-4-20-beta-0309-non-reasoning is answered by Grok 4.20 Beta Non-Reasoning (0309) from xAI, billed at its published list price. Inferray never substitutes a different or smaller model.