What is Grok 4.20 Non-Reasoning?

Grok 4.20 Non-Reasoning is a model from xAI, released on Mar 10, 2026. Grok 4 20 0309 Non is an xAI Grok model for reasoning, coding, vision, and general conversational tasks.

How much does Grok 4.20 Non-Reasoning cost?

On the Respan gateway, input starts at $1.25 per 1M tokens on every provider, and output starts at $2.50 per 1M tokens on every provider, after gateway discounts.

Which providers serve Grok 4.20 Non-Reasoning on Respan?

11 providers serve Grok 4.20 Non-Reasoning: Perplexity, Google Vertex AI, and xAI. Perplexity and Google Vertex AI require your own provider API key (BYOK).

What is Grok 4.20 Non-Reasoning's context window?

Grok 4.20 Non-Reasoning accepts up to 1M tokens of context on its largest provider route.

How do I use Grok 4.20 Non-Reasoning with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "xai/grok-4.20-non-reasoning-latest". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is Grok 4.20 Non-Reasoning?

Over the last 30 days of requests through the Respan gateway, the fastest provider was xAI at 17 tokens per second, and the lowest response latency was 0.5 seconds on xAI. Speed varies with request size and provider.

Grok 4.20 Non-Reasoning

Grok 4 20 0309 Non is an xAI Grok model for reasoning, coding, vision, and general conversational tasks.

Tool Use

# Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://respan.ai/docs/agent-setup.md. Use model "xai/grok-4.20-non-reasoning-latest".

Context window: 1M tokens
Input from: $1.25/M
Output from: $2.50/M
Providers: 11
Released: Mar 10, 2026

Providers

11 providers serve this model through the Respan gateway, cheapest first. Copy a model ID to call that route directly.

Provider	Context	Input	Output
PerplexityBYOK only`perplexity/xai/grok-4.20-non-reasoning`	1M	$1.25/M	$2.50/M
Google Vertex AIBYOK only`vertex_ai/xai/grok-4.20-non-reasoning`	1M	$1.25/M	$2.50/M
xAI`xai/grok-4.20-0309-non-reasoning`	1M	$1.25/M	$2.50/M
xAI`xai/grok-4.20-beta-0309-non-reasoning`	1M	$1.25/M	$2.50/M
xAI`xai/grok-4.20-beta-latest-non-reasoning`	1M	$1.25/M	$2.50/M
xAI`xai/grok-4.20-beta-non-reasoning`	1M	$1.25/M	$2.50/M
xAI`xai/grok-4.20-experimental-beta-0304-non-reasoning`	1M	$1.25/M	$2.50/M
xAI`xai/grok-4.20-experimental-beta-non-reasoning-latest`	1M	$1.25/M	$2.50/M
xAI`xai/grok-4.20-non-reasoning`	1M	$1.25/M	$2.50/M
xAI`xai/grok-4.20-non-reasoning-gv2`	1M	$1.25/M	$2.50/M
xAI`xai/grok-4.20-non-reasoning-latest`	1M	$1.25/M	$2.50/M

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

Grok 4.20 Non-Reasoning

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps