Tuesday, July 7, 2026 · No. 345Prices synced 1 hour ago
All·AI·Model

The AI Model Price Index

Llama 4 Maverick 17B FP8

by Deep Infra · family llama · listed Apr 2025VW

Open multimodal Llama model for strong reasoning and fast responses

Current rates USD per 1M tokens

Input$0.15
Output$0.60
Cache read—
Cache write—

Against the market

Input price vs. maker flagships ($/1M tokens)
DeepSeek V4 FlashDeepSeek V4 Flash: $0.14 per 1M tokens$0.14Llama 4 Maverick 17B FP8Llama 4 Maverick 17B FP8: $0.15 per 1M tokens$0.15Qwen3.7 PlusQwen3.7 Plus: $0.50 per 1M tokens$0.50Grok 4.3Grok 4.3: $1.25 per 1M tokens$1.25Gemini 3.5 FlashGemini 3.5 Flash: $1.50 per 1M tokens$1.50Mistral Medium (latest)Mistral Medium (latest): $1.50 per 1M tokens$1.50Claude Sonnet 5Claude Sonnet 5: $2.00 per 1M tokens$2.00GPT-5.5 ProGPT-5.5 Pro: $30.00 per 1M tokens$30.00
Output price vs. maker flagships ($/1M tokens)
DeepSeek V4 FlashDeepSeek V4 Flash: $0.28 per 1M tokens$0.28Llama 4 Maverick 17B FP8Llama 4 Maverick 17B FP8: $0.60 per 1M tokens$0.60Grok 4.3Grok 4.3: $2.50 per 1M tokens$2.50Qwen3.7 PlusQwen3.7 Plus: $3.00 per 1M tokens$3.00Mistral Medium (latest)Mistral Medium (latest): $7.50 per 1M tokens$7.50Gemini 3.5 FlashGemini 3.5 Flash: $9.00 per 1M tokens$9.00Claude Sonnet 5Claude Sonnet 5: $10.00 per 1M tokens$10.00GPT-5.5 ProGPT-5.5 Pro: $180 per 1M tokens$180

On the record

Model id
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Context window
1.0M tokens
Max output
16K tokens
Input modalities
text, image
Output modalities
text
Reasoning
no
Tool calls
no
Open weights
yes
Knowledge cutoff
—
Released
2025-04-05
Last updated
2025-04-05
Provider docs
deepinfra.com/models

Back of the envelope

≈

Also listed at

← All Deep Infra listings