Skip to content

Model Library

xAIReleased April 30, 2026

Grok 4.3 (Non-reasoning)

xAI · Released April 30, 2026

Intelligence score

25

At a glance

Intelligence
25
Speed
133.1tokens/sec
Latency
730mstime to first token
Input price
$1.25per 1M tokens
Output price
$2.50per 1M tokens
Context window
4tokens
Parameters
—

Summary

Comparison summary

Grok 4.3 (Non-reasoning) scores 25 on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 17). Grok 4.3 (Non-reasoning) generates output at 133.1 tokens per second (based on xAI's API), which is well above average compared to other non-reasoning models in a similar price tier (median: 61.7 t/s). Grok 4.3 (Non-reasoning) costs $1.25 per 1M input tokens (better than average, median: $1.88) and $2.50 per 1M output tokens (very competitive, median: $7.75), based on xAI's API.

Specifications

Technical specifications

Model nameGrok 4.3 (Non-reasoning)
ProviderxAI
Release dateApril 30, 2026
Intelligence score25
Speed133.1 tokens/sec
Latency (TTFT)0.73s
Input price$1.25 / 1M tokens
Output price$2.50 / 1M tokens
Context window4 tokens
Parameters—
ReasoningNo
Input modalitiestext, image
Output modalities—
Open weightsNo
License—
API availability—
SourceModel Intelligence legacy profile: grok-4-3-non-reasoning

Pricing

Token prices

Price per 1M tokens

Grok 4.3 (Non-reasoning), as listed in the catalog record

Input $1.25 and output $2.50 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$1.25
  2. Output$2.50

Model Intelligence legacy profile: grok-4-3-non-reasoning

FAQ · 19

Frequently asked questions

Grok 4.3 (Non-reasoning) was released on April 30, 2026.

Grok 4.3 (Non-reasoning) was created by xAI.

Grok 4.3 (Non-reasoning) scores 25 on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 17).

Grok 4.3 (Non-reasoning) generates output at 133.1 tokens per second (based on xAI's API), which is well above average compared to other non-reasoning models in a similar price tier (median: 61.7 t/s).

Grok 4.3 (Non-reasoning) has a time to first token (TTFT) of 0.73s (based on xAI's API), which is very competitive compared to other non-reasoning models in a similar price tier (median: 1.57s).

Grok 4.3 (Non-reasoning) costs $1.25 per 1M input tokens (better than average, median: $1.88) and $2.50 per 1M output tokens (very competitive, median: $7.75), based on xAI's API.

Grok 4.3 (Non-reasoning) costs $1.25 per 1M input tokens and $2.50 per 1M output tokens (based on xAI's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.64 per 1M tokens. Pricing may vary by provider.

When evaluated on the Intelligence Index, Grok 4.3 (Non-reasoning) generated 9.0M output tokens, which is better than average compared to other non-reasoning models in a similar price tier (median: 7.2M).

No, Grok 4.3 (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Grok 4.3 (Non-reasoning) supports text and image input.

Grok 4.3 (Non-reasoning) supports text output.

Yes, Grok 4.3 (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.

Yes, Grok 4.3 (Non-reasoning) is multimodal. It can process text and image input and generate text output.

Grok 4.3 (Non-reasoning) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.

No, Grok 4.3 (Non-reasoning) is proprietary. The model weights are not publicly available.

Grok 4.3 (Non-reasoning) is a proprietary model and xAI has not disclosed the model size or parameter count.

Grok 4.3 (Non-reasoning) achieves a score of 25 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Grok 4.3 (Non-reasoning) is available via API through 2 providers.

Grok 4.3 (Non-reasoning) is available through 2 API providers.