All models · x-ai

SpaceXAI: Grok 4.6 pricing and limits

id x-ai/grok-4.6 · listed 2026-08-12

Input (per 1M tokens)$2.000
Output (per 1M tokens)$6.000
Cached input read (per 1M)$0.500
Context window500,000 tokens
Max output450,000 tokens
Modalitiestext+image+file → text
Reasoningyes

What 1,000 calls cost at 1,000 input and 300 output tokens each: $3.80.

Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).

Cheaper on both input and output, with at least half the context

ModelIn / 1MOut / 1MContext
Auto Router (Beta)$-1000000.000$-1000000.0002,000,000
Pareto Code Router$-1000000.000$-1000000.0002,000,000
SpaceXAI: Grok 4.20 Multi-Agent$1.250$2.5002,000,000
SpaceXAI: Grok 4.20$1.250$2.5002,000,000
Auto Router$-1000000.000$-1000000.0002,000,000
Meta: Llama 4 Scout$0.100$0.3001,310,720

Other x-ai models

SpaceXAI: Grok Build 0.1 ($1.000 / $2.000) · SpaceXAI: Grok 4.3 (batch) ($1.000 / $2.000) · SpaceXAI: Grok 4.3 ($1.250 / $2.500) · SpaceXAI: Grok 4.20 Multi-Agent ($1.250 / $2.500) · SpaceXAI: Grok 4.20 ($1.250 / $2.500) · SpaceXAI: Grok 4.7 ($2.000 / $6.000) · SpaceXAI: Grok 4.5 ($2.000 / $6.000)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=x-ai/grok-4.6 (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=x-ai. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with x-ai. Agent Exchange