Skip to content
Metatext Hub — one governed catalog for your company’s AI toolsGet early access
Metatext
Sign Up

Llama 4 Maverick 17B 128E Instruct FP8

watsonx.aiOpen weights

Llama 4 Maverick 17B 128E Instruct FP8 by watsonx.ai costs $0.37 per 1M input tokens and $1.48 per 1M output tokens, with a 131K-token context window.

Pricing

Input (per 1M tokens)
$0.37
Output (per 1M tokens)
$1.48
Cached input (per 1M)
—

Specifications

Provider
watsonx.ai
Context window
131K tokens
Parameters
—
Released
Apr 2025
Open weights
Yes
Frontier model
No

Compare Llama 4 Maverick 17B 128E Instruct FP8 with…

Llama 4 Maverick 17B 128E Instruct FP8 vs Llama-3.3-70B-Instruct$0.75/1MLlama 4 Maverick 17B 128E Instruct FP8 vs Granite-4.0-H-Small$0.27/1MLlama 4 Maverick 17B 128E Instruct FP8 vs Mistral Small 3.1 24B$0.32/1MLlama 4 Maverick 17B 128E Instruct FP8 vs GPT OSS 120B$0.64/1M

FAQ

Pricing is per 1M tokens (USD); confirm with the provider before production use.