Sunday, August 9, 2026 · No. 378Prices synced 4 hours ago
All·AI·Model

The AI Model Price Index

Llama 4 Maverick 17B 128E Instruct FP8

by watsonx.ai · family llama · listed Apr 2025TVW

Open multimodal Llama for strong reasoning with efficient everyday serving

Current rates USD per 1M tokens

Input$0.371
Output$1.48
Cache read—
Cache write—

Against the market

Input price vs. maker flagships ($/1M tokens)
DeepSeek V4 FlashDeepSeek V4 Flash: $0.14 per 1M tokens$0.14Gemini 3.5 Flash LiteGemini 3.5 Flash Lite: $0.30 per 1M tokens$0.30Llama 4 Maverick 17B 128E Instruct FP8Llama 4 Maverick 17B 128E Instruct FP8: $0.371 per 1M tokens$0.371Mistral Medium (latest)Mistral Medium (latest): $1.50 per 1M tokens$1.50Grok 4.5Grok 4.5: $2.00 per 1M tokens$2.00Qwen3.8 MaxQwen3.8 Max: $2.00 per 1M tokens$2.00Claude Opus 5Claude Opus 5: $5.00 per 1M tokens$5.00GPT-5.6 SolGPT-5.6 Sol: $5.00 per 1M tokens$5.00
Output price vs. maker flagships ($/1M tokens)
DeepSeek V4 FlashDeepSeek V4 Flash: $0.28 per 1M tokens$0.28Llama 4 Maverick 17B 128E Instruct FP8Llama 4 Maverick 17B 128E Instruct FP8: $1.48 per 1M tokens$1.48Gemini 3.5 Flash LiteGemini 3.5 Flash Lite: $2.50 per 1M tokens$2.50Grok 4.5Grok 4.5: $6.00 per 1M tokens$6.00Qwen3.8 MaxQwen3.8 Max: $6.00 per 1M tokens$6.00Mistral Medium (latest)Mistral Medium (latest): $7.50 per 1M tokens$7.50Claude Opus 5Claude Opus 5: $25.00 per 1M tokens$25.00GPT-5.6 SolGPT-5.6 Sol: $30.00 per 1M tokens$30.00

On the record

Model id
meta-llama/llama-4-maverick-17b-128e-instruct-fp8
Context window
131K tokens
Max output
8K tokens
Input modalities
text, image
Output modalities
text
Reasoning
no
Tool calls
yes
Open weights
yes
Knowledge cutoff
Aug 2024
Released
2025-04-05
Last updated
2025-04-05
Provider docs
www.ibm.com/docs/en/watsonx/saas?topic=solutions-supported-foundation-models

Back of the envelope

≈

Also listed at

← All watsonx.ai listings