Saturday, September 12, 2026 · No. 412Prices synced 6 hours ago
All·AI·Model

The AI Model Price Index

Llama 4 Maverick 17B Instruct

by Charm Hyper · family llama · listed Apr 2026TW

Open multimodal Llama for strong reasoning with efficient everyday serving

Current rates USD per 1M tokens

Input$0.255
Output$0.837
Cache read$0.128
Cache write—

Against the market

Input price vs. maker flagships ($/1M tokens)
DeepSeek V4 Flash Vision ExpDeepSeek V4 Flash Vision Exp: $0.15 per 1M tokens$0.15Qwen3.8 FlashQwen3.8 Flash: $0.15 per 1M tokens$0.15Llama 4 Maverick 17B InstructLlama 4 Maverick 17B Instruct: $0.255 per 1M tokens$0.255Gemini 3.8 FlashGemini 3.8 Flash: $0.75 per 1M tokens$0.75GLM-5.2GLM-5.2: $1.40 per 1M tokens$1.40Grok 4.6Grok 4.6: $2.00 per 1M tokens$2.00Claude Fable 5.1Claude Fable 5.1: $10.00 per 1M tokens$10.00GPT-6 AstraGPT-6 Astra: $10.00 per 1M tokens$10.00
Output price vs. maker flagships ($/1M tokens)
Qwen3.8 FlashQwen3.8 Flash: $0.47 per 1M tokens$0.47DeepSeek V4 Flash Vision ExpDeepSeek V4 Flash Vision Exp: $0.60 per 1M tokens$0.60Llama 4 Maverick 17B InstructLlama 4 Maverick 17B Instruct: $0.837 per 1M tokens$0.837Gemini 3.8 FlashGemini 3.8 Flash: $3.75 per 1M tokens$3.75GLM-5.2GLM-5.2: $4.40 per 1M tokens$4.40Grok 4.6Grok 4.6: $6.00 per 1M tokens$6.00Claude Fable 5.1Claude Fable 5.1: $50.00 per 1M tokens$50.00GPT-6 AstraGPT-6 Astra: $50.00 per 1M tokens$50.00

On the record

Model id
llama-4-maverick-17b-128e-instruct-fp8
Context window
430K tokens
Max output
43K tokens
Input modalities
text
Output modalities
text
Reasoning
no
Tool calls
yes
Open weights
yes
Knowledge cutoff
Aug 2024
Released
2026-04-30
Last updated
2026-07-22
Provider docs
hyper.charm.land

Back of the envelope

≈

Also listed at

← All Charm Hyper listings