ModelBench
Meta logo
Models/Meta

Llama 4 Maverick 17B Instruct

Open multimodal Llama for strong reasoning with efficient everyday serving

Source-linked llama Open weights Released 2025-04-05
API data Report
Input modalitiesT
Output modalitiesT
Input price$0.124/1M tokens
Output price$0.603/1M tokens
Context window1M
Max output16.384K
Overview

Capabilities and specifications

× Reasoning No
× Tool calling No
× Structured output No
✓ Attachments Yes
✓ Vision input Yes
✓ Open weights Yes
Creator
Meta
Model family
llama
Knowledge cutoff
2024-08
License
Not documented
Release date
2025-04-05
Model ID
meta/llama-4-maverick-17b-instruct
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering Llama 4 Maverick 17B Instruct
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
Cortecs llama-4-maverick 1M $0.124 $0.603 $0.03 Tools Docs
Abacus meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 1.04858M $0.14 $0.59 - Tools Docs
Amazon Bedrock meta.llama4-maverick-17b-instruct-v1:0 1M $0.24 $0.97 - Tools Docs
LLM Gateway llama-4-maverick-17b-instruct 1.04858M $0.27 $0.85 - Not listed Docs
Charm Hyper llama-4-maverick-17b-128e-instruct-fp8 430K $0.284 $0.934 - Tools Docs
Neon llama-4-maverick 1M $0.5 $1.5 - Tools Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
Aider Polyglot - Unversioned - percent correctTop 8 reported models
GPT-5
88.0
o3-pro
84.9
Gemini 2.5 Pro
83.1
o3
81.3
DeepSeek Reasoner
74.2
Claude Opus 4
72.0
Claude Opus 4 (latest)
72.0
Llama 4 Maverick 17B Instruct
15.6
SWE-Bench Pro - Unversioned - resolve rateTop 8 reported models
Claude Fable 5
80.3
Claude Opus 4.8
69.2
Grok 4.5
64.7
GPT-5.6 Sol
64.6
Claude Opus 4.7
64.3
GPT-5.6 Terra
63.4
Claude Sonnet 5
63.2
Llama 4 Maverick 17B Instruct
5.2
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
No recent changes detected

This record has not changed in the retained import history.

Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/meta/llama-4-maverick-17b-instruct
curl
curl "https://www.modelbench.lol/api/v1/models/meta/llama-4-maverick-17b-instruct"