Skip to content

Meta · Chat

Llama 4 Maverick

Meta 🇺🇸ChatLlama familyOpen weights. One of its sources says the weights are publicly available.The maker lists this model as deprecated (19 Nov 2026).

Llama 4 Maverick, a 17 billion active parameter model with 128 experts.

llminfo IQ
111.8
Market median price
$0.4225 blended / 1M
Max context
1M
Listings
54

Evidence and sources

🤗 meta-llama/Llama-4-Maverick-17B-128E-Instruct400B paramsllminfo IQ 111.8, ranked among chat models. From 350 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 78.1, 95% interval 69–87. From 13 benchmark families across 10 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (42.1). Costs more per task than its benchmark results predict. From 25 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTerse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 1,406 output tokens per task at default effort.How the Yap score worksReleased 5 Apr 2025Maker HQ: US (according to Meta's own website)
All rankings: #188 on OpenRouter today #206 on OpenRouter this month #212 on OpenRouter this weekSources: LMArena data, IBM watsonx.ai Foundation Models data docs, LiteLLM data, Models.dev data, llminfo researchPrimary data from LMArena from IBM watsonx.ai Foundation Models: parameter count, description from LiteLLM: deprecation date from Models.dev: weights availability from llminfo research: release date
Tags from its sources:multimodalmultilingual

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 2 of the 7 peers that say either way have open weights.

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (19 Nov 2026).

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 8 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionFunction callingStructured outputPrompt cachingBatch API

Listings

 OpenRoutermeta-llama/llama-4-maverick:free · freeSource: Helicone Costs dataNot published by the provider$0.00$0.00
 Lambda AIlambda_ai/llama-4-maverick-17b-128e-instruct-fp8 · fp8Source: LiteLLM data131K$0.05$0.10
 Abacusmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · fp8Source: Models.dev data1M$0.14$0.59
 Flowdotmeta-llama/llama-4-maverickSource: FlowDot data1M$0.15$0.60
 302aimeta-llama/llama-4-maverick-17b-128e-instruct-fp8 · fp8Source: 302.ai data1M$0.20$0.90
 Aihubmixllama-4-maverickSource: AIHubMix data docs1M$0.20$0.20
 RequestyInference by Novita AInovita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8 · fp8Source: Requesty data1M$0.20$0.85
 DeepInfradeepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · fp8Sources: LiteLLM data, Models.dev data1M$0.20$0.80
 Groqmeta-llama/llama-4-maverick-17b-128e-instructSource: GenAI Prices data131K$0.20$0.60
 Vercel AI Gatewayvercel_ai_gateway/meta/llama-4-maverickSource: LiteLLM data131K$0.20$0.60

7 listings without a price are hidden.

These providers advertise this model. Researchers have found some resellers serving a different, cheaper model, so see how to check whether a provider meets your needs.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Safety

HELM66 related benchmarks · 66 results
Source: Stanford HELM specialized suites data docs
BenchmarkScore
Safety: BBQ - BBQ accuracy
AIR-Bench: AIRBench 2024 - #1: Confidentiality
AIR-Bench: AIRBench 2024 - #2: Integrity
AIR-Bench: AIRBench 2024 - #3: Availability
Show 62 more benchmarksHide 62 benchmarks
BenchmarkScore
AIR-Bench: AIRBench 2024 - #4: Automated Decision-Making
AIR-Bench: AIRBench 2024 - #5: Autonomous Unsafe Operation of Systems
AIR-Bench: AIRBench 2024 - #6: Advice in Heavily Regulated Industries
AIR-Bench: AIRBench 2024 - #7: Supporting Malicious Organized Groups
AIR-Bench: AIRBench 2024 - #8: Celebrating Suffering
AIR-Bench: AIRBench 2024 - #9: Violent acts
AIR-Bench: AIRBench 2024 - #10: Depicting Violence
AIR-Bench: AIRBench 2024 - #11: Weapon Usage & Development
AIR-Bench: AIRBench 2024 - #12: Military and Warfare
AIR-Bench: AIRBench 2024 - #13: Harassment
AIR-Bench: AIRBench 2024 - #15: Perpetuating Harmful Beliefs
AIR-Bench: AIRBench 2024 - #16: Offensive Language
AIR-Bench: AIRBench 2024 - #17: Adult content
AIR-Bench: AIRBench 2024 - #18: Erotic
AIR-Bench: AIRBench 2024 - #19: Non-Consensual Nudity
AIR-Bench: AIRBench 2024 - #20: Monetized
AIR-Bench: AIRBench 2024 - #21: Endangerment, Harm, or Abuse of Children
AIR-Bench: AIRBench 2024 - #22: Child Sexual Abuse
AIR-Bench: AIRBench 2024 - #23: Suicidal and non-suicidal self Injury
AIR-Bench: AIRBench 2024 - #24: Political Persuasion
AIR-Bench: AIRBench 2024 - #25: Influencing Politics
AIR-Bench: AIRBench 2024 - #26: Deterring Democratic Participation
AIR-Bench: AIRBench 2024 - #27: Disrupting Social Order (China-unique)
AIR-Bench: AIRBench 2024 - #28: High-Risk Financial Activities
AIR-Bench: AIRBench 2024 - #29: Unfair Market Practices
AIR-Bench: AIRBench 2024 - #30: Disempowering Workers
AIR-Bench: AIRBench 2024 - #31: Fraudulent Schemes
AIR-Bench: AIRBench 2024 - #32: Fraud
AIR-Bench: AIRBench 2024 - #33: Academic dishonesty
AIR-Bench: AIRBench 2024 - #34: Mis/disinformation
AIR-Bench: AIRBench 2024 - #35: Sowing Division
AIR-Bench: AIRBench 2024 - #36: Misrepresentation
AIR-Bench: AIRBench 2024 - #37: Types of Defamation
AIR-Bench: AIRBench 2024 - #38: Specific Types of Rights
AIR-Bench: AIRBench 2024 - #39-40: Discrimination/Protected Characteristics Combinations
AIR-Bench: AIRBench 2024 - #41-42: Privacy Violations/Sensitive Data Combinations
AIR-Bench: AIRBench 2024 - #43: Illegal/Regulated substances/goods
AIR-Bench: AIRBench 2024 - #44: Illegal services/exploitation
AIR-Bench: AIRBench 2024 - #45: Other Illegal/Unlawful/Criminal Activities
AIR-Bench: AIRBench 2024 - Child Harm
AIR-Bench: AIRBench 2024 - Criminal Activities
AIR-Bench: AIRBench 2024 - Deception
AIR-Bench: AIRBench 2024 - Defamation
AIR-Bench: AIRBench 2024 - Discrimination/Bias
AIR-Bench: AIRBench 2024 - Economic Harm
AIR-Bench: AIRBench 2024 - Fundamental Rights
AIR-Bench: AIRBench 2024 - Hate/Toxicity
AIR-Bench: AIRBench 2024 - Manipulation
AIR-Bench: AIRBench 2024 - Operational Misuses
AIR-Bench: AIRBench 2024 - Political Usage
AIR-Bench: AIRBench 2024 - Privacy
AIR-Bench: AIRBench 2024 - Refusal Rate
AIR-Bench: AIRBench 2024 - Security Risks
AIR-Bench: AIRBench 2024 - Self-harm
AIR-Bench: AIRBench 2024 - Sexual Content
AIR-Bench: AIRBench 2024 - Violence & Extremism
Safety: Anthropic Red Team - LM Evaluated Safety score
Safety: BBQ - BBQ (ambiguous)
Safety: BBQ - BBQ (unambiguous)
Safety: HarmBench - LM Evaluated Safety score
Safety: SimpleSafetyTests - LM Evaluated Safety score
Safety: XSTest - LM Evaluated Safety score
PhareSource: Phare

Human preference

Multilingual

SeaLLMs16 related benchmarks · 16 results
Show 10 more resultsHide 10 results

Agentic

Coding

SWE-rebenchSource: SWE-rebench

Science

ChemBench10 related benchmarks · 10 results
ChemBench
Source: ChemBench verified leaderboard data docs
groq_meta-llama/llama-4-maverick-17b-128e-instruct_e8a077d8
Analytical Chemistry
Source: ChemBench verified leaderboard data docs
groq_meta-llama/llama-4-maverick-17b-128e-instruct_e8a077d8
Chemical Preference
Source: ChemBench verified leaderboard data docs
groq_meta-llama/llama-4-maverick-17b-128e-instruct_e8a077d8
General Chemistry
Source: ChemBench verified leaderboard data docs
groq_meta-llama/llama-4-maverick-17b-128e-instruct_e8a077d8
Inorganic Chemistry
Source: ChemBench verified leaderboard data docs
groq_meta-llama/llama-4-maverick-17b-128e-instruct_e8a077d8
Materials Science
Source: ChemBench verified leaderboard data docs
groq_meta-llama/llama-4-maverick-17b-128e-instruct_e8a077d8
Show 4 more resultsHide 4 results
Organic Chemistry
Source: ChemBench verified leaderboard data docs
groq_meta-llama/llama-4-maverick-17b-128e-instruct_e8a077d8
Physical Chemistry
Source: ChemBench verified leaderboard data docs
groq_meta-llama/llama-4-maverick-17b-128e-instruct_e8a077d8
Technical Chemistry
Source: ChemBench verified leaderboard data docs
groq_meta-llama/llama-4-maverick-17b-128e-instruct_e8a077d8
Toxicity and Safety
Source: ChemBench verified leaderboard data docs
groq_meta-llama/llama-4-maverick-17b-128e-instruct_e8a077d8

Long context

General

Spatialviz BenchSource: Epoch AI Benchmarking Hub data

Reasoning

Math

Factuality

Instruction following

Knowledge

OCR

Speech

Vision

Other

Nejumi 428 related benchmarks · 28 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Show 22 more resultsHide 22 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_表現
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · SEA-HELM leaderboard, AI Singapore (AI Products team), National University of Singapore. Published aggregate scores; results licence not stated (SEA-HELM code is MIT). · LMArena, CC BY 4.0 (licence) · ChemBench leaderboard, Jablonka group / lamalab-org. Public verified numeric result summaries; results licence not separately stated. · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Phare (Giskard), CC BY 4.0 (licence) · SeaExam and SeaBench leaderboard, SeaLLMs (DAMO-NLP-SG). Published leaderboard scores; results licence not stated. · OpenEvals/leaderboard-data, MIT (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · Vectara Hallucination Leaderboard, Apache-2.0 (licence) · VideoGameBench, Alex L. Zhang, Thomas L. Griffiths, Karthik R. Narasimhan, Ofir Press. Public numeric scores; site licence not stated (code MIT not applied; games excluded).

Also known as: aws-bedrock/llama-4-maverick-17b-instruct, azure_ai/llama-4-maverick-17b-128e-instruct-fp8, cerebras-llama-4-maverick-17b-128e-instruct, databricks/databricks-llama-4-maverick, deepinfra-llama-4-maverick-17b-128e-instruct, deepinfra/meta-llama/llama-4-maverick-17b-128e-instruct-fp8, fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic, gmi/meta-llama/llama-4-maverick-17b-128e-instruct-fp8, groq-llama-4-maverick-17b-128e-instruct, lambda_ai/llama-4-maverick-17b-128e-instruct-fp8, llama-4-maverick, llama-4-maverick-17b, llama-4-maverick-17b-128e-instruct-fp8, llama-4-maverick-17b-16e-instruct, llama-4-maverick-17b-instruct, llama-4-maverick-instruct, llama4-maverick-instruct-basic, meta-llama/llama-4-maverick, meta-llama/llama-4-maverick-17b-128e-instruct, meta-llama/llama-4-maverick-17b-128e-instruct-fp4, meta-llama/llama-4-maverick-17b-128e-instruct-fp8, meta-llama/llama-4-maverick:free, meta.llama-4-maverick-17b-128e-instruct-fp8, meta.llama4-maverick-17b-instruct-v1:0, meta/llama-4-maverick, meta/llama-4-maverick-17b-128e-instruct-maas, meta_llama/llama-4-maverick-17b-128e-instruct-fp8, novita/llama-4-maverick-17b-instruct, novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8, oci/meta.llama-4-maverick-17b-128e-instruct-fp8, parasail-llama-4-maverick-instruct-fp8, replicate/meta/llama-4-maverick-instruct, sambanova/llama-4-maverick-17b-128e-instruct, snowflake/llama4-maverick, us.meta.llama4-maverick-17b-instruct-v1:0, vercel_ai_gateway/meta/llama-4-maverick, vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas, vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas, watsonx/meta-llama/llama-4-maverick-17b, watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works