LLM Reference

Llama 4 Maverick 17B

llama-4-maverick-17b

Researched 32d ago

Last refreshed 2026-05-11. Next refresh: weekly.

Open SourceMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use

Llama 4 Maverick 17B is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Decision context: Coding task fit, 1 tracked provider route, and research from 2026-04-19.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 128k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Workloads where another current model has stronger sourced task evidence

Cheapest output

$0.970

AWS Bedrock per 1M tokens

Provider routes

1

Tracked API hosts

Quality / dollar

Grade C

Ranked by benchmark score divided by cheapest output price

Freshness

2026-04-19

Researched 32d ago

aging

Top use-case fit

Coding

Q/$ C

3 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

ProviderInput / 1MOutput / 1MBatch in / outRoute
AWS Bedrock$0.240$0.970$0.120 / $0.485
Serverless

Benchmark peer barsfor Coding

Migration checks

No linked migration route is available for this model yet.

About

Multimodal Llama 4 with 128 experts, optimized for fast responses with minimal computational cost

Llama 4 Maverick 17B has a 128K-token context window.

Llama 4 Maverick 17B input tokens at $0.24/1M, output at $0.97/1M.

Capabilities

MultimodalStructured OutputsCode Execution

Benchmark Scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
HumanEval77.42025-04Meta AI
Aider Polyglot15.62026-04https://aider.chat/docs/leaderboards
BigCodeBench49.72025-04 (Instruct Pass@1)https://bigcode-bench.github.io/results.json
Google-Proof Q&A67.1diamondArtificial Analysis

Rankings

Specifications

FamilyLlama 4
Released2025-10-01
Parameters17
Context128k
Knowledge cutoff2024-08

Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website

Providers(1)