Grok 4.3 (Non-reasoning)
Intelligence
31
#154/521
Coding
25.1
#168/427
Math
—
Speed
64 tok/s
TTFT: 0.66s
Pricing
$1.25 / $2.50
per 1M tokens (in/out)
Grok 4.3 is xAI’s newest flagship general-purpose model. xAI describes it as the most intelligent and fastest model it has built, with a 1 million token context window, reasoning support, function calling, structured outputs, prompt caching, and industry-leading non-hallucination, agentic tool calling, and instruction-following capabilities.
Grok 4.3 (Non-reasoning) is xAI’s model designed for various AI applications. It processes at 64.363 tokens per second and is priced at $1.25 per million input tokens, targeting professional users.
When to Use Grok 4.3 (Non-reasoning)
✓ Best For
- Text generation tasks.
- Basic coding assistance.
- Data processing applications.
✗ Not Ideal For
- Complex reasoning tasks.
- High-level mathematical computations.
How Grok 4.3 (Non-reasoning) Compares
Intelligence Index · Higher is better
GoogleAnthropicxAIKimi
Benchmark Profile
Coding Index
OpenAIxAIGoogle
Output Speed · tok/s
MistralDeepSeekxAIAlibabaZ AI
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (9)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 31 | |
| Coding Index | 25.1 | |
| GPQA | 658% | |
| HLE | 65% | |
| SciCode | 37.4% | |
| IFBench | 47.6% | |
| LCR | 24.7% | |
| TerminalBench Hard | 18.9% | |
| Tau2 | 65.8% |
Data: Artificial Analysis · Updated: May 8, 2026
Frequently Asked Questions (15)
When was Grok 4.3 (Non-reasoning) released?
Grok 4.3 (Non-reasoning) was released on April 30, 2026.
Who created Grok 4.3 (Non-reasoning)?
Grok 4.3 (Non-reasoning) was created by xAI.
How intelligent is Grok 4.3 (Non-reasoning)?
Grok 4.3 (Non-reasoning) scores 31 on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 24).
How fast is Grok 4.3 (Non-reasoning)?
Grok 4.3 (Non-reasoning) generates output at 68.6 tokens per second (based on xAI's API), which is above average compared to other non-reasoning models in a similar price tier (median: 54.3 t/s).
What is the latency of Grok 4.3 (Non-reasoning)?
Grok 4.3 (Non-reasoning) has a time to first token (TTFT) of 0.75s (based on xAI's API), which is very competitive compared to other non-reasoning models in a similar price tier (median: 1.69s).
How much does Grok 4.3 (Non-reasoning) cost?
Grok 4.3 (Non-reasoning) costs $1.25 per 1M input tokens (better than average, median: $2.00) and $2.50 per 1M output tokens (very competitive, median: $8.00), based on xAI's API.
What is Grok 4.3 (Non-reasoning) API pricing?
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 (3:1 input to output ratio), this is $1.56 per 1M tokens. Pricing may vary by provider.
How verbose is Grok 4.3 (Non-reasoning)?
When evaluated on the Intelligence Index, Grok 4.3 (Non-reasoning) generated 7.8M output tokens, which is better than average compared to other non-reasoning models in a similar price tier (median: 7.8M).
Is Grok 4.3 (Non-reasoning) a reasoning model?
No, Grok 4.3 (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Grok 4.3 (Non-reasoning) support?
Grok 4.3 (Non-reasoning) supports text and image input.
What output modalities does Grok 4.3 (Non-reasoning) support?
Grok 4.3 (Non-reasoning) supports text output.
Can Grok 4.3 (Non-reasoning) process images?
Yes, Grok 4.3 (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.
Is Grok 4.3 (Non-reasoning) multimodal?
Yes, Grok 4.3 (Non-reasoning) is multimodal. It can process text and image input and generate text output.
What is the context window of Grok 4.3 (Non-reasoning)?
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.
Is Grok 4.3 (Non-reasoning) open source?
No, Grok 4.3 (Non-reasoning) is proprietary. The model weights are not publicly available.
