Llama 4 Scout Instruct
meta-llama/llama-4-scout-17b-16e-instruct
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.
Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.
Funktionen
Serverless API
Dokumentation
meta-llama/llama-4-scout-17b-16e-instruct is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.
Verfügbare Serverless
Abfragen sofort ausführen, nur für die Nutzung bezahlen
Eingabe$0.18 / M Tokens
Ausgabe$0.59 / M Tokens
Verwenden Sie die folgenden Codebeispiele, um unsere API zu integrieren:
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="<Your API Key>",
5 base_url="https://api.novita.ai/openai"
6)
7
8response = client.chat.completions.create(
9 model="meta-llama/llama-4-scout-17b-16e-instruct",
10 messages=[
11 {"role": "system", "content": "You are a helpful assistant."},
12 {"role": "user", "content": "Hello, how are you?"}
13 ],
14 max_tokens=131072,
15 temperature=0.7
16)
17
18print(response.choices[0].message.content)Info
Anbieter
Llama
Quantisierung
bf16
Unterstützte Funktionalität
Kontextlänge
131072
Maximale Ausgabe
131072
Serverless
Unterstützt
Eingabefähigkeiten
text, image
Ausgabefähigkeiten
text
Alles, was Sie brauchen, um produktionsreife AI zu entwickeln.
Über 200 Modelle, GPUs auf Abruf und sichere Agent-Runtimes — vereint unter einer API. Kostenlos zum Einstieg, skaliert mit Ihrem Wachstum.