xAIApr 18, 2026
Grok 4.3
Grok 4.3 is a reasoning model from xAI with function calling, structured outputs, and a 1M-token context window. Suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy.
$1.42/$2.83
per 1M in / out
1M
context window
32K
max output
Time to first token—
Output speed—
Uptime—
Last 24 hours of Venice traffic.How it’s measured
Capabilities
What the model takes in, returns and supports through the API.
InTextImage
OutText
Streaming
Function callingstream: truetoolsStructured outputsresponse_formatReasoningreasoning_effort none · low · medium · highVisionUp to 10 imagesWeb search
enable_web_searchX search
Prompt cachingReads at $0.23enable_x_searchNot supportedvideo input, audio input and log probabilities
Benchmarks
GPQA Diamond
84.8%69th of 139 · 20 score higher for less, including Pareto, DeepSeek v4.1 Flash (1017) and MiniMax M2.5
Specs
- Model ID
grok-4-3- Endpoint
POST /api/v1/chat/completions- Context window
- 1,000,000 tokens
- Max output
- 32,000 tokens
- Reasoning
none · low · medium · high· default low- Precision
- Not disclosed
- Privacy
- Private
- Weights
- Closed
- Added
- Apr 18, 2026
Compare
| Model | Input | Output |
|---|---|---|
| Grok 4.3 | $1.42 | $2.83 |
| GPT-5.4 Mini | $0.75 | $4.50 |
| GLM 5 Turbo | $1.20 | $4.00 |
| Qwen 3.5 397B | $0.75 | $4.50 |
| DeepSeek V4 Pro | $1.65 | $3.30 |
Pricing
Billed per token in USD. Reasoning tokens bill as output.
Input$1.42per 1M tokens
Cached input$0.2384% off input
Output$2.83per 1M tokens
Estimate a workload
$0.0043per request
$42.55for 10,000 requests
Blended price against similar models
Quickstart
OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-4-3",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "low"
}'Base URL
https://api.venice.ai/api/v1Parameters
| Parameter | Values |
|---|---|
model | grok-4-3 |
messages | text · image_url |
max_completion_tokens | Up to 32,000 |
reasoning_effort | none | low | medium | high |
tools | Function definitions |
response_format | { type: |
stream | true | false |
venice_parameters.enable_web_search | auto | on | off |
venice_parameters.enable_x_search | true | false |