Impulse
Models/Llama-4-Maverick-17B-128E-Instruct-FP8
Compare

Llama-4-Maverick-17B-128E-Instruct-FP8Active · Cloud

DeepInfra · Released · Llama Community License

Deepinfra chat model.

Context
1.0M
Max output
1.0M
Input
$0.15
Output
$0.60
Cached in
-
Latency
-

Capabilities

Core
Streaming
Function calling
JSON mode
Structured outputs
Multimodal
Vision
Image input
Audio
Image generation
Video
Advanced
Reasoning
Tool calling
MCP
Prompt caching
Batch API
Embeddings

Details

ProviderDeepInfra
Released
LicenseLlama Community License
InputText
OutputText
Throughput-
Availability-

Related models

DeepSeek-V3.1-TerminusDeepInfra164K$0.27Qwen3-Next-80B-A3B-InstructDeepInfra262K$0.14Qwen3-Next-80B-A3B-ThinkingDeepInfra262K$0.14