Llama-4-Scout-17B-16E-Instruct-FP8
Summary
Llama-4-Scout-17B-16E-Instruct-FP8 is an open-weight language model from Meta, released on 5 Apr 2025. It accepts text and images and generates text, with a 128K-token context window and up to 8K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.10 per million input tokens and $0.30 per million output tokens (DeepInfra), across 6 providers we track.
Open multimodal Llama model for long-context analysis and efficient agents
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Meta |
|---|---|
| Release date | 5 Apr 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [models.dev] |
| Context window | 128K (128,000 tokens) [models.dev] |
| Max output | 8K tokens [models.dev] |
| Knowledge cutoff | Aug 2024 [models.dev] |
| Input | Text and images [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | meta-llama/Llama-4-Scout-17B-16E-Instruct |
Llama-4-Scout-17B-16E-Instruct-FP8 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepInfra meta-llama/Llama-4-Scout-17B-16E-Instruct | $0.10 | $0.30 | – | 328K | models.dev, 18 Nov 2026 |
| OpenRouter meta-llama/llama-4-scout | $0.10 | $0.30 | – | 328K | OpenRouter, 18 Nov 2026 |
| Vercel AI Gateway meta/llama-4-scout | $0.17 | $0.66 | – | 128K | models.dev, 18 Nov 2026 |
| Novita AI meta-llama/llama-4-scout-17b-16e-instruct | $0.18 | $0.59 | – | 131K | models.dev, 18 Nov 2026 |
| Google Vertex AI meta/llama-4-scout-17b-16e-instruct-maas | $0.25 | $0.70 | – | 1.3M | models.dev, 18 Nov 2026 |
| Cloudflare Workers AI @cf/meta/llama-4-scout-17b-16e-instruct | $0.27 | $0.85 | – | 131K | models.dev, 18 Nov 2026 |
Frequently asked questions
What is the context window of Llama-4-Scout-17B-16E-Instruct-FP8?
Llama-4-Scout-17B-16E-Instruct-FP8 has a context window of 128,000 tokens (128K) and can generate up to 8,192 tokens in a single response, according to models.dev.
How much does the Llama-4-Scout-17B-16E-Instruct-FP8 API cost?
Llama-4-Scout-17B-16E-Instruct-FP8 is listed from $0.10 per million input tokens and $0.30 per million output tokens (DeepInfra). Prices last verified 18 Nov 2026.
Is Llama-4-Scout-17B-16E-Instruct-FP8 open source?
Llama-4-Scout-17B-16E-Instruct-FP8 is an open-weight model: its weights are published on Hugging Face as meta-llama/Llama-4-Scout-17B-16E-Instruct. Check the license terms before commercial use.
When was Llama-4-Scout-17B-16E-Instruct-FP8 released?
Meta released Llama-4-Scout-17B-16E-Instruct-FP8 on 5 Apr 2025, according to models.dev.
Which providers offer Llama-4-Scout-17B-16E-Instruct-FP8?
We track Llama-4-Scout-17B-16E-Instruct-FP8 on 6 providers: DeepInfra, OpenRouter, Vercel AI Gateway, Novita AI, Google Vertex AI, Cloudflare Workers AI.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Mistral Small 3.1 24B | Mistral AI | 17 Mar 2025 | 128K | $0.10 | $0.30 | Open |
| Gemma 3 27B IT | Google DeepMind | 12 Mar 2025 | 131K | $0.08 | $0.16 | Open |
| ERNIE 4.5 21B A3B | Baidu | 30 Jun 2025 | 120K | $0.07 | $0.28 | Open |
| Phi-4-mini | Microsoft | 11 Dec 2024 | 128K | $0.07 | $0.30 | Open |
| Qwen3-VL 30B-A3B | Alibaba (Qwen) | Apr 2025 | 131K | $0.20 | $0.80 | Open |
| UI-TARS 7B | Bytedance | 22 Jul 2025 | 128K | $0.10 | $0.20 | Open |
Change history
- Name changed from Llama 4 Scout 17B Instruct to Llama-4-Scout-17B-16E-Instruct-FP8
- Context window changed from 1.3M to 128K
- Max output changed from 131K to 8K
- Tool calling changed from no to yes
- Structured output changed from no to yes
- Context window changed from 131K to 1.3M
- Context window changed from 131K to 131K
- Name changed from Llama 4 Scout 17B 16E Instruct to Llama 4 Scout 17B Instruct
- Tool calling changed from yes to no
- Max output changed from 16K to 131K
- Name changed from Llama 4 Scout 17B Instruct to Llama 4 Scout 17B 16E Instruct
- Context window changed from 1.3M to 131K
- Max output changed from 8K to 16K
- Structured output changed from yes to no
- Max output changed from 16K to 8K
- Context window changed from 328K to 1.3M
- Name changed from Llama 4 Scout 17B to Llama 4 Scout 17B Instruct
- Name changed from Llama 4 Scout 17B Instruct to Llama 4 Scout 17B
- Context window changed from 1.3M to 328K
- Max output changed from 8K to 16K
- Context window changed from 128K to 1.3M
- Name changed from Llama-4-Scout-17B-16E-Instruct-FP8 to Llama 4 Scout 17B Instruct
- Name changed from Llama 4 Scout 17B to Llama-4-Scout-17B-16E-Instruct-FP8
- Context window changed from 328K to 128K
- Max output changed from 16K to 8K
Sources
- https://openrouter.ai/meta-llama/llama-4-scout
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/meta/llama-4-scout.toml
- https://github.com/sst/models.dev/blob/dev/providers/google-vertex/models/meta/llama-4-scout-17b-16e-instruct-maas.toml
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/meta-llama/Llama-4-Scout-17B-16E-Instruct.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/meta-llama/llama-4-scout-17b-16e-instruct.toml
- https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-4-scout-17b-16e-instruct.toml