spacexaiCertifiedReleased 08/12/2026

Grok 4.6

Grok 4.6 builds on Grok 4.5 with a particular focus on long-running agents and more ambitious interactive and visual work. It stays with complex tasks across many steps, whether researching a topic, analyzing information, working across a codebase, or turning an idea into a polished application or work artifact.

View API reference ↓
Input / output priceFrom$2.00 / $6.00per 1M
24h uptime—
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "spacexai/grok-4.6",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
Amazon Bedrock500K500K——$2.00$6.00Read $0.50Write —5 featuresYesYesUSListed
xAI500K500K——$2.00$6.00Read $0.50Write —5 featuresYesYesUSCertified

Uptime

24 hours

Request success rate per provider.

Amazon Bedrock—
xAI—

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "spacexai/grok-4.6",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. spacexai/grok-4.6. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. Grok 4.6 supports up to 500,000 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 500K-token context window
ImageURL, base64Sent as image_url content parts; counts as input tokens

More models by spacexai

ModelContextInputOutputCacheRelease
spacexai/grok-4.7500K$2.00$6.00Read $0.50Write —09/21/2026
spacexai/grok-4.5500K$2.00$6.00Read $0.30Write —07/08/2026
spacexai/grok-build-0.1256K$1.00$2.00Read $0.20Write —05/20/2026
spacexai/grok-4.31M$1.25$2.50Read $0.20Write —04/30/2026
spacexai/grok-4.3-batch1M$1.00$2.00Read $0.16Write —04/30/2026
spacexai/grok-4.20-multi-agent-beta2M$1.25$2.50Read $0.20Write —03/11/2026
spacexai/grok-4.20-non-reasoning-beta2M$1.25$2.50Read $0.20Write —03/11/2026
spacexai/grok-4.20-reasoning-beta2M$1.25$2.50Read $0.20Write —03/11/2026
spacexai/grok-4.20-multi-agent2M$1.25$2.50Read $0.20Write —03/10/2026
spacexai/grok-4.20-multi-agent-batch2M$1.00$2.00Read $0.16Write —03/10/2026