Llama 4 Maverick 17B 128E Instruct FP8

DeepinfraText

Llama 4 Maverick 17B 128E Instruct FP8 is a text model from Deepinfra with a context window of 1.0M tokens and max output of 1.0M tokens. Pricing starts at $0.15 per million input tokens and $0.60 per million output tokens (cheapest at Deepinfra).

Specifications

Model Keydeepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
ProviderDeepinfra
LiteLLM Providerdeepinfra
ModeText
Canonical Namellama-maverick-4-17b-128e
Context Window1.0M tokens
Max Output1.0M tokens

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens$0.000150$0.150
Output Tokens$0.000600$0.600

Price Comparison by Provider

Compare prices for Llama 4 Maverick 17B 128E Instruct FP8 across different providers. The same model may be available through multiple providers at different price points.

Provider
Model Key
Input Price
Output Price
Groqgroq/meta-llama/llama-4-maverick-17b-128e-instruct$0.200$0.600
Deepinfradeepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8$0.150$0.600
Together AItogether_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8$0.270$0.850
Google Vertex AIvertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas$0.350$1.15

Similar Models

Models with similar capabilities and context window size.

Model
Provider
Mode
Input Price
Output Price
Context
Max Output
Vision
Functions
Gemini 1.5 Flash-8bGoogle GeminiTextN/AN/A1.0M8Kyesyes
Gemini 1.5 Flash-8b-exp-0924Google GeminiTextN/AN/A1.0M8Kyesyes
Gemini 1.5 Flash-exp-0827Google GeminiTextN/AN/A1.0M8Kyesyes
Gemini 2.0 Flash-expGoogle GeminiTextN/AN/A1.0M8Kyesyes
Gemini 2.0 Flash-thinking-expGoogle Vertex AITextN/AN/A1.0M8Kyesyes
Gemini 2.0 Flash-thinking-expGoogle GeminiTextN/AN/A1.0M66Kyesyes
Gemini 2.0 Flash-thinking-exp-01-21Google Vertex AITextN/AN/A1.0M66Kyesno
Gemini 2.0 Flash-thinking-exp-01-21Google GeminiTextN/AN/A1.0M66Kyesyes
Gemini 2.5 Pro-exp-03-25Google GeminiTextN/AN/A1.0M66Kyesyes
Gemini Experimental 1114Google GeminiTextN/AN/A1.0M8Kyesyes