Llama 4 Scout 17B
Llama 4 Scout is the best multimodal model in the world in its class and is more powerful than our Llama 3 models, while fitting in a single H100 GPU.
text + image → text · made by Meta
Sold by 26 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | batch | $0.085per Mtok in$0.33per Mtok outaws.amazon.com · read 2026-08-24 |
| Google Vertex AI 0 ways | $0.12per Mtok in$0.35per Mtok out | |
| Google Vertex AI cloudnot on the seller's list today | batch | $0.12per Mtok in$0.35per Mtok outcloud.google.com · read 2026-08-24 |
| AWS Bedrock cloud | standard | $0.17per Mtok in$0.66per Mtok outaws.amazon.com · read 2026-08-24 |
| Microsoft Azure AI 0 ways | $0.2per Mtok in$0.78per Mtok out | |
| Microsoft Azure AI cloudnot on the seller's list today | standard | $0.2per Mtok in$0.78per Mtok outmodels.dev · read 2026-08-27 |
| Google Vertex AI 0 ways | $0.25per Mtok in$0.7per Mtok out | |
| Google Vertex AI cloudnot on the seller's list today | standard | $0.25per Mtok in$0.7per Mtok outcloud.google.com · read 2026-08-24 |
| Oracle Cloud Infrastructure 0 ways | $0.72per Mtok in$0.72per Mtok out | |
| Oracle Cloud Infrastructure cloudnot on the seller's list today | standard | $0.72per Mtok in$0.72per Mtok outraw.githubusercontent.com · read 2026-08-27 |
| Lambda 0 ways | $0.05per Mtok in$0.1per Mtok out | |
| Lambda aggregatornot on the seller's list today | standard | $0.05per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-08-27 |
| Hugging Face Inference Providers 3 ways | $0.09per Mtok in$0.29per Mtok out | |
| Hugging Face Inference Providers aggregator | nscale | $0.09per Mtok in$0.29per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | deepinfra | $0.1per Mtok in$0.3per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | novita | $0.18per Mtok in$0.59per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Nscale 0 ways | $0.09per Mtok in$0.29per Mtok out | |
| Nscale aggregatornot on the seller's list today | standard | $0.09per Mtok in$0.29per Mtok outraw.githubusercontent.com · read 2026-08-27 |
| DeepInfra aggregator | standard | $0.1per Mtok in$0.3per Mtok outapi.deepinfra.com · read 2026-09-02 |
| ElectronHub 0 ways | $0.1per Mtok in$0.5per Mtok out | |
| ElectronHub aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.5per Mtok outapi.electronhub.ai · read 2026-08-27 |
| Nous Research aggregator | standard | $0.1per Mtok in$0.3per Mtok out$0.044per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 4 ways | $0.1per Mtok in$0.3per Mtok out$0.055per Mtok cached | |
| OpenRouter aggregator | standard | $0.1per Mtok in$0.3per Mtok out$0.055per Mtok cachedopenrouter.ai · read 2026-09-01 |
| OpenRouter aggregator | deepinfra/fp8 | $0.1per Mtok in$0.3per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregatornot on the seller's list today | groq | $0.11per Mtok in$0.34per Mtok out$0.055per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | novita/bf16 | $0.18per Mtok in$0.59per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | google-vertex/us-east5 | $0.25per Mtok in$0.7per Mtok outopenrouter.ai · read 2026-08-25 |
| Groq 0 ways | $0.11per Mtok in$0.34per Mtok out | |
| Groq aggregatornot on the seller's list today | standard | $0.11per Mtok in$0.34per Mtok outraw.githubusercontent.com · read 2026-08-27 |
| Vercel AI Gateway aggregator | standard | $0.17per Mtok in$0.66per Mtok outai-gateway.vercel.sh · read 2026-08-25 |
| Novita AI aggregator | standard | $0.18per Mtok in$0.59per Mtok outapi.novita.ai · read 2026-09-02 |
| Together AI 0 ways | $0.18per Mtok in$0.59per Mtok out | |
| Together AI aggregatornot on the seller's list today | standard | $0.18per Mtok in$0.59per Mtok outraw.githubusercontent.com · read 2026-08-27 |
| Cloudflare 0 ways | $0.27per Mtok in$0.85per Mtok out | |
| Cloudflare aggregatornot on the seller's list today | standard | $0.27per Mtok in$0.85per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| Cloudflare aggregatornot on the seller's list today | sandbox | $0.27per Mtok in$0.85per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| SambaNova Cloud 0 ways | $0.4per Mtok in$0.7per Mtok out | |
| SambaNova Cloud aggregatornot on the seller's list today | standard | $0.4per Mtok in$0.7per Mtok outraw.githubusercontent.com · read 2026-08-27 |
Measured 8 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 141stof 143 | Artificial Analysis · Agentic Index | Index | 0.5 |
| 147thof 152 | Design Arena · dataviz (models) | Elo | 909 |
| 150thof 150 | Design Arena · uicomponent (models) | Elo | 783 |
| 155thof 155 | Design Arena · gamedev (models) | Elo | 796 |
| 156thof 156 | Design Arena · codecategories (models) | Elo | 805 |
| 162ndof 162 | Design Arena · website (models) | Elo | 763 |
| 180thof 184 | Artificial Analysis · Coding Index | Index | 8.2 |
| 254thof 302 | Artificial Analysis · Intelligence Index | Artificial Analysis Intelligence Index | 6 |
About
Llama 4 Scout 17B — a text model from Meta, sold by 7 companies from $0.1 in and $0.3 out per million tokens, placed 254th of 302 on Artificial Analysis · Intelligence Index.
It takes text and images and returns text, with a context window of 128,000 tokens. It was published in April 2025, trained on material up to August 2024. Its sellers say it can call a tool. The catalogue files it under chat. Seven companies sell it. The cheapest is $0.1 in and $0.3 out per million tokens at DeepInfra. Beside the standard rate there are batch, separately routed and regional lanes. It has been measured on 8 boards, and stands best at 254th of 302 on Artificial Analysis · Intelligence Index.
Every current figure
- Maker
- Meta
- Register
- model
- Takes
- text + image
- Returns
- text
- Context
- 128,000 tokens
- Longest answer
- 65,536 tokens
- Published
- April 2025
- Knowledge to
- August 2024
- Parameters
- 109 billion
- Licence
- not read
- Sellers
- 7
- Maker's own price
- not read
- Price
- $0.1 in and $0.3 out per million tokens — DeepInfra
- Boards
- 8
- Best place
- 254th of 302 — Artificial Analysis · Intelligence Index
Known as 6 names
meta.llama4-scout-17b-instruct-v1:0@cf/meta/llama-4-scout-17b-16e-instructmeta-llama/Llama-4-Scout-17B-16E-Instructmeta-llama/llama-4-scoutmeta/llama-4-scoutLlama 4 Scout