import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "x-ai/grok-3-beta", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "x-ai/grok-3-beta", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"x-ai/grok-3-beta","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| MMMU | 76.0% | College-level multimodal understanding + reasoning | Source | July 12, 2026 |
| AIME 2025 | 77.3% | Competition mathematics (AIME), 2025 | Source | July 12, 2026 |
| GPQA Diamond | 80.2% | Google-proof graduate science questions (hardest subset) | Source | July 12, 2026 |
| Intelligence | 10.4 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Grok 3 Beta This page | Coding + agents | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Grok 3 Beta has a 131,000 tokens context window and can return up to 130,000 tokens.
Grok 3 Beta takes text as input and returns text.
Use x-ai/grok-3-beta as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Grok 3 Beta is priced at input $1.625 / 1M tokens, output $3.25 / 1M tokens, cached input $0.26 / 1M tokens.
Yes, Grok 3 Beta can stream responses as they are generated.
Grok 3 Beta was built by xAI .
Grok 3 Beta is available via the API endpoint https://api.aimlapi.com/v1/chat/completions.
It supports file input, parallel tool calls, streaming, structured output, and tool use.
Yes, it supports function calling, tool use, and parallel tool calls.