RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

SpaceXAI: Grok 4.20 API pricing

$1.25 per 1M input tokens and $2.50 per 1M output tokens on OpenRouter. Context window: 2,000,000 tokens.

$1.25input / 1M tokens
$2.50output / 1M tokens
$0.20cached input / 1M
1.9073486328125Mcontext
text+image+file->textmodality

What it costs in practice

WorkloadCost
Chatbot: 10,000 messages (1,500 in / 400 out tokens each)$28.75
RAG: 1,000 queries (8,000 in / 600 out each)$11.50
Summarize 100 long documents (50,000 in / 1,000 out each)$6.50

Cross-check against the provider's list price

LiteLLM's price map lists xai/grok-4.20 (xai) at $1.25 in / $2.50 out per 1M tokens. Matches OpenRouter

Price history

No price change recorded since we started tracking on Nov 17, 2026. We check every 6 hours and log every change.

Cheaper alternatives with similar context

Text models with at least 125K context and a lower blended price (75% input, 25% output). Price only, not a quality ranking.

ModelInput / 1MOutput / 1MContext
Z.ai: GLM 5$1.00$3.20200K
Google: Gemini 4 Hydrogen (batch)$0.75$3.751M
Google: Gemini 3.7 Flash$0.75$3.751M
Google: Gemini 3.6 Flash$0.75$3.751M
Mistral: Mistral Medium 3.5 (batch)$0.75$3.75256K
Relace: Relace Search$1.00$3.00250K
Nous: Hermes 4 405B$1.00$3.00128K
StepFun: Step 5 Preview$1.00$2.70977K

Source: OpenRouter listing via the public models API · LiteLLM price map (MIT). Prices checked Nov 17, 2026. Model ID x-ai/grok-4.20, listed Mar 31, 2026. Report an error.