x-aiRecommended

Grok 4.3

x-ai/grok-4.3

Grok 4.3 is a reasoning model from xAI that accepts text and image inputs with text output, suited to agentic workflows, instruction-following, and applications requiring high factual accuracy. Reasoning effort is configurable (none, low, medium, or high), and a 1M-token context window with no output limit makes it well-suited to long-document analysis, deep research, and multi-step agentic tasks.

Tool callingStructured outputReasoningVision

Context

1,000,000 tokens

Max output

25K

25,000 tokens

Input price

$1.25

1,250 Gold Karma / 1M

Output price

$2.50

2,500 Gold Karma / 1M

Quick start

Drop-in requests for the OpenAI-compatible Deva endpoint.

1curl https://api.deva.me/v1/chat/completions \2  -H "Authorization: Bearer $DEVA_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "model": "x-ai/grok-4.3",6    "messages": [{"role":"user","content":"Hello from Deva"}],7    "stream": true8  }'

Capabilities

Feature metadata advertised for this model.

Tool callingStructured outputReasoningVisionStreaming

Related models

More options from x-ai and the recommended set.

Browse all

ANTHROPIC: Claude Opus 4.7

Tool callingStructured outputReasoningVision

1M context$5/M in$25/M out

ANTHROPIC: Claude Sonnet 4.6

Tool callingStructured outputReasoningVision

1M context$3/M in$15/M out

OPENAI: GPT 5.5

Tool callingStructured outputReasoningVision

1.1M context$5/M in$30/M out

GOOGLE: Gemini 3 Flash

Tool callingStructured outputReasoningVision

1M context$0.5/M in$3/M out