tokenstat
tokenstat

Llama 4 Maverick 17B 128E Instruct FP8

azure-cognitive-services/llama-4-maverick-17b-128e-instruct-fp8 · rates as of · Benchmarks · Plans · Calculator

Open multimodal Llama model for strong reasoning and fast responses

Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
1M
tokens
Offers
6
2 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Showing free/$0 offers. Hide them.

SourceProviderInputOutputCache readContext
models.devcheapestllama-4-maverick-17b-128e-instruct-fp8Llama$0$0$0128K
LiteLLMllama-4-maverick-17b-128e-instruct-fp8$0.05$0.1$0.005
models.devllama-4-maverick-17b-128e-instruct-fp8Azure$0.25$1$01M
models.devllama-4-maverick-17b-128e-instruct-fp8Azure$0.25$1$01M
models.devllama-4-maverick-17b-128e-instruct-fp8Charm Hyper$0.284$0.934$0430K
LiteLLMLlama-4-Maverick-17B-128E-Instruct-FP8$1.41$0.35$0.141

Capabilities

  • Tool calling
  • Attachments
  • Open weights
  • In: text
  • In: image
  • Out: text
Knowledge cutoff: 2024-08Released: 2025-04-05Family: llama

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash