Meta

Llama-4-Maverick-17B-128E-Instruct-FP8

Generally availableOpen weights128K context

Summary

Llama-4-Maverick-17B-128E-Instruct-FP8 is an open-weight language model from Meta, released on 5 Apr 2025. It accepts text and images and generates text, with a 128K-token context window and up to 8K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.27 per million input tokens and $0.85 per million output tokens (Novita AI), across 3 providers we track.

Open multimodal Llama model for strong reasoning and fast responses

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperMeta
Release date5 Apr 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [models.dev]
Context window128K (128,000 tokens) [models.dev]
Max output8K tokens [models.dev]
Knowledge cutoffAug 2024 [models.dev]
InputText and images [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facemeta-llama/Llama-4-Maverick-17B-128E-Instruct

Llama-4-Maverick-17B-128E-Instruct-FP8 API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Vercel AI Gateway
meta/llama-4-maverick
$0.24$0.97–128Kmodels.dev, 18 Nov 2026
Novita AI
meta-llama/llama-4-maverick-17b-128e-instruct-fp8
$0.27$0.85–1Mmodels.dev, 18 Nov 2026
OpenRouter
meta-llama/llama-4-maverick
$0.35$1$0.17524KOpenRouter, 18 Nov 2026

Frequently asked questions

What is the context window of Llama-4-Maverick-17B-128E-Instruct-FP8?

Llama-4-Maverick-17B-128E-Instruct-FP8 has a context window of 128,000 tokens (128K) and can generate up to 8,192 tokens in a single response, according to models.dev.

How much does the Llama-4-Maverick-17B-128E-Instruct-FP8 API cost?

Llama-4-Maverick-17B-128E-Instruct-FP8 is listed from $0.27 per million input tokens and $0.85 per million output tokens (Novita AI). Prices last verified 18 Nov 2026.

Is Llama-4-Maverick-17B-128E-Instruct-FP8 open source?

Llama-4-Maverick-17B-128E-Instruct-FP8 is an open-weight model: its weights are published on Hugging Face as meta-llama/Llama-4-Maverick-17B-128E-Instruct. Check the license terms before commercial use.

When was Llama-4-Maverick-17B-128E-Instruct-FP8 released?

Meta released Llama-4-Maverick-17B-128E-Instruct-FP8 on 5 Apr 2025, according to models.dev.

Which providers offer Llama-4-Maverick-17B-128E-Instruct-FP8?

We track Llama-4-Maverick-17B-128E-Instruct-FP8 on 3 providers: Vercel AI Gateway, Novita AI, OpenRouter.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Qwen3-VL 30B-A3BAlibaba (Qwen)Apr 2025131K$0.20$0.80Open
DeepSeek V3 0324DeepSeek24 Mar 2025164K$0.25$1Open
UncensoredCognitivecomputations9 Jul 2025128K$0.20$0.90Open
GLM-4.5-AirZhipu AI (Z.ai)28 Jul 2025131K$0.13$0.85Open
Qwen2.5-VL 72B InstructAlibaba (Qwen)26 Jan 2025128K$0.80$1Open
Mistral Small 3.1 24BMistral AI17 Mar 2025128K$0.10$0.30Open

Change history

  • Name changed from Llama 4 Maverick 17B Instruct to Llama-4-Maverick-17B-128E-Instruct-FP8
  • Context window changed from 1M to 128K
  • Tool calling changed from no to yes
  • Context window changed from 128K to 1M
  • Tool calling changed from yes to no
  • Name changed from Llama-4-Maverick-17B-128E-Instruct-FP8 to Llama 4 Maverick 17B Instruct
  • Context window changed from 524K to 128K
  • Name changed from Llama 4 Maverick to Llama-4-Maverick-17B-128E-Instruct-FP8
  • Max output changed from 33K to 8K
  • Name changed from Llama-4-Maverick-17B-128E-Instruct-FP8 to Llama 4 Maverick
  • Context window changed from 128K to 524K
  • Max output changed from 8K to 33K
  • Name changed from Llama 4 Maverick 17B Instruct to Llama-4-Maverick-17B-128E-Instruct-FP8
  • Context window changed from 1M to 128K
  • Tool calling changed from no to yes
  • Tool calling changed from yes to no
  • Name changed from Llama-4-Maverick-17B-128E-Instruct-FP8 to Llama 4 Maverick 17B Instruct
  • Context window changed from 128K to 1M
  • Name changed from Llama 4 Maverick to Llama-4-Maverick-17B-128E-Instruct-FP8
  • Context window changed from 524K to 128K
  • Max output changed from 33K to 8K
  • OpenRouter price changed: input $0.19 → $0.35, output $0.65 → $1 per 1M tokens
  • Context window changed from 128K to 524K
  • Max output changed from 8K to 33K
  • Name changed from Llama-4-Maverick-17B-128E-Instruct-FP8 to Llama 4 Maverick

Sources