Llama 4 Maverick 17B
As a general purpose LLM, Llama 4 Maverick contains 17 billion active parameters, 128 experts, and 400 billion total parameters, offering high quality at a lower price compared to Llama 3.3 70B.
text + image → text · made by Meta
Sold by 24 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | batch | $0.12per Mtok in$0.48per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| Google Vertex AI 0 ways | $0.17per Mtok in$0.57per Mtok out | |
| Google Vertex AI cloudnot on the seller's list today | batch | $0.17per Mtok in$0.57per Mtok outcloud.google.com · read 2026-08-24 |
| AWS Bedrock cloud | standard | $0.24per Mtok in$0.97per Mtok outmodels.dev · read 2026-11-01 |
| Snowflake Cortex cloud | standard | $0.24per Mtok in$0.97per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| DigitalOcean cloud | standard | $0.25per Mtok in$0.87per Mtok out$0.05per Mtok cachedmodels.dev · read 2026-11-01 |
| Microsoft Azure AI cloud | standard | $0.25per Mtok in$1per Mtok outmodels.dev · read 2026-11-01 |
| Google Vertex AI 0 ways | $0.35per Mtok in$1.15per Mtok out | |
| Google Vertex AI cloudnot on the seller's list today | standard | $0.35per Mtok in$1.15per Mtok outcloud.google.com · read 2026-08-24 |
| IBM watsonx cloud | standard | $0.37per Mtok in$1.48per Mtok outmodels.dev · read 2026-11-01 |
| IBM watsonx.ai cloud | standard | $0.37per Mtok in$1.48per Mtok outibm.com · read 2026-08-25 |
| Databricks cloud | standard | $0.5per Mtok in$1.5per Mtok out$0.5per Mtok cached$0.5per Mtok cache writeraw.githubusercontent.com · read 2026-11-01 |
| Oracle Cloud Infrastructure cloud | standard | $0.72per Mtok in$0.72per Mtok outmodels.dev · read 2026-11-01 |
| Lambda aggregator | standard | $0.05per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| Nous Research aggregator | standard | $0.19per Mtok in$0.65per Mtok out$0.05per Mtok cachedinference-api.nousresearch.com · read 2026-09-15 |
| OpenRouter 4 ways | $0.19per Mtok in$0.65per Mtok out$0.05per Mtok cached | |
| OpenRouter aggregator | standard | $0.19per Mtok in$0.65per Mtok out$0.05per Mtok cachedopenrouter.ai · read 2026-09-22 |
| OpenRouter aggregator | digitalocean | $0.19per Mtok in$0.65per Mtok out$0.05per Mtok cachedopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregatornot on the seller's list today | deepinfra/base | $0.2per Mtok in$0.8per Mtok outopenrouter.ai · read 2026-08-31 |
| OpenRouter aggregatornot on the seller's list today | novita/fp8 | $0.27per Mtok in$0.85per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | google-vertex/us-east5 | $0.35per Mtok in$1.15per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | parasail/fp8 | $0.35per Mtok in$1per Mtok out$0.17per Mtok cachedopenrouter.ai · read 2026-08-25 |
| DeepInfra aggregator | standard | $0.2per Mtok in$0.8per Mtok outapi.deepinfra.com · read 2026-09-02 |
| Vercel AI Gateway aggregator | standard | $0.24per Mtok in$0.97per Mtok outvercel.com · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | novita | $0.27per Mtok in$0.85per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Novita AI aggregator | standard | $0.27per Mtok in$0.85per Mtok outapi.novita.ai · read 2026-09-02 |
| Together AI 0 ways | $0.27per Mtok in$0.85per Mtok out | |
| Together AI aggregatornot on the seller's list today | standard | $0.27per Mtok in$0.85per Mtok outraw.githubusercontent.com · read 2026-09-22 |
Measured 10 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 41stof 111 | Vectara Hallucination Leaderboard | Hallucination Rate | 8.2 |
| 42ndof 108 | Math level 5 — Epoch AI | mean_score | 73.017 |
| 61stof 69 | Aider polyglot coding leaderboard | Percent correct | 15.6 |
| 93rdof 101 | FrontierMath (Tiers 1-3) | mean_score | 0.69 |
| 131stof 132 | Ale bench — Epoch AI | Performance | 172.97 |
| 143rdof 150 | Design Arena · 3d (models) | Elo | 898 |
| 152ndof 154 | Design Arena · dataviz (models) | Elo | 882 |
| 160thof 163 | Design Arena · codecategories (models) | Elo | 878 |
| 197thof 326 | GPQA Diamond | mean_score | 66.982 |
| 246thof 306 | OTIS Mock AIME 2024-2025 | mean_score | 20.556 |
About
Llama 4 Maverick 17B — a text model from Meta, sold by 15 companies from $0.05 in and $0.1 out per million tokens, placed 41st of 111 on Vectara Hallucination Leaderboard.
It takes text and images and returns text, with a context window of 128,000 tokens. It was published in January 2025, trained on material up to August 2024. Its sellers say it can call a tool. The catalogue files it under reasoning and code. Fifteen companies sell it. The cheapest is $0.05 in and $0.1 out per million tokens at Lambda. Beside the standard rate there are batch, separately routed and regional lanes. It has been measured on 10 boards, and stands best at 41st of 111 on Vectara Hallucination Leaderboard.
Every current figure
- Maker
- Meta
- Register
- model
- Takes
- text + image
- Returns
- text
- Context
- 128,000 tokens
- Longest answer
- 65,536 tokens
- Published
- January 2025
- Knowledge to
- August 2024
- Parameters
- 402 billion
- Licence
- not read
- Sellers
- 15
- Maker's own price
- not read
- Price
- $0.05 in and $0.1 out per million tokens — Lambda
- Boards
- 10
- Best place
- 41st of 111 — Vectara Hallucination Leaderboard
Known as 7 names
llama4-maverick-17b-instructmeta.llama4-maverick-17b-instruct-v1:0meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8llama-4-maverick-17b-128e-instruct-fp8meta-llama/llama-4-maverickmeta/llama-4-maverickLlama 4 Maverick