Grok 4.3 | xAI Multimodal LLM API Pricing

Name: Grok 4.3 API
Brand: x-ai
Price: 1.25 USD
Availability: InStock

Utilisation de l'API

Utilisez les exemples de code suivants pour intégrer notre API :

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="x-ai/grok-4.3",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

Introduction au modèle

xAI: Grok 4.3

Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

This model is imported from OpenRouter metadata and exposed through the WaveSpeed AI OpenAI-compatible API for chat completions and compatible application workflows.

Why It Looks Great

text+image->text architecture for Text, Image to Text workloads
1000000 context window for long prompts, document analysis, and multi-turn workflows
Competitive pricing at $1.25/$2.5 per million tokens
Vision input support for image understanding and multimodal tasks
Function calling and tool-use support for agentic application workflows
Structured output support for JSON responses and schema-constrained generation
Reasoning controls available through supported OpenRouter parameters

Key Features

Context Window: 1000000 tokens
Max Input: Not listed
Max Output: Not listed
Vision: Supported
Function Calling: Supported
Structured Outputs: Supported
Image Generation: Not listed
Audio Input: Not listed
Supported Parameters: frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p

Specifications

Specification	Value
Provider	xai
Model Type	Chat Completions model
Architecture	text+image->text
Context Window	1000000 tokens
Max Input	Not listed
Max Output	Not listed
Input	Text, Image
Output	Text
Vision	Supported
Function Calling	Supported
Structured Outputs	Supported
OpenRouter Created	April 30, 2026

How to Use

Write your prompt - describe the task, provide context, and specify the desired output format.
Submit - the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: x-ai/grok-4.3

API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="x-ai/grok-4.3",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "x-ai/grok-4.3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Grok 4.3 API

x-ai/grok-4.3

Grok 4.3 is xAI’s advanced reasoning model designed for agentic workflows, complex instruction-following, and high-accuracy knowledge tasks. It supports both text and image inputs, generating text outputs with configurable reasoning depth across none, low, medium, and high effort modes (default: low). The model features an industry-leading 1 million token context window with no fixed output token limit, enabling long-document analysis, deep research, multi-step reasoning, and large-scale autonomous agent applications. Pricing is usage-tiered, with higher rates applied to requests exceeding 200K total tokens.

Questions fréquentes sur Grok 4.3

Combien coûte l'API Grok 4.3 ?+

Tarification sur WaveSpeedAI : $1.25 par million de tokens d'entrée et $2.50 par million de tokens de sortie. Le prompt caching et le traitement par batch sont facturés séparément et réduisent le coût effectif sur les charges longues et répétitives.

Quelle est la fenêtre de contexte de Grok 4.3 ?+

Grok 4.3 prend en charge jusqu'à 1000K tokens de contexte et jusqu'à — tokens de sortie par requête.

Grok 4.3 est-il compatible avec OpenAI ?+

Oui. WaveSpeedAI expose Grok 4.3 via un endpoint compatible OpenAI à https://llm.wavespeed.ai/v1. Pointez le SDK officiel d'OpenAI vers cette base URL avec votre clé API WaveSpeedAI — aucune autre modification de code requise.

Comment démarrer avec Grok 4.3 ?+

Connectez-vous à WaveSpeedAI, créez une clé API dans Access Keys, puis envoyez une requête à https://llm.wavespeed.ai/v1/chat/completions avec l'id du modèle affiché ci-dessus. Les nouveaux comptes reçoivent des crédits gratuits pour évaluer Grok 4.3.

Tarification

Essayer le modèle