# Llama 3.1 8B Instruct fp8

> Llama 3.1 8B Instruct fp8 is an open-weight language model from Meta, released on 23 Jul 2024. It accepts text and generates text, with a 32K-token context window and up to 32K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.02 per million input tokens and $0.05 per million output tokens (Novita AI), across 5 providers we track.

Source page: https://www.aimodel.directory/models/llama-3-1-8b-instruct
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Meta
- **Release date:** 23 Jul 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-3.1-8b-instruct-fp8.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-3.1-8b-instruct-fp8.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
- **License:** llama3.1 (source: Hugging Face, https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
- **Parameters:** 8B (source: Hugging Face, https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
- **Context window:** 32K (32,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-3.1-8b-instruct-fp8.toml)
- **Max output:** 32K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-3.1-8b-instruct-fp8.toml)
- **Knowledge cutoff:** Dec 2023 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-3.1-8b-instruct-fp8.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-3.1-8b-instruct-fp8.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-3.1-8b-instruct-fp8.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-3.1-8b-instruct-fp8.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-3.1-8b-instruct-fp8.toml)
- **Structured output:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/meta/llama-3.1-8b-instruct-fp8.toml)
- **Hugging Face:** meta-llama/Meta-Llama-3.1-8B-Instruct (source: Hugging Face, https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Novita AI | $0.02 | $0.05 | – | 16K |
| OpenRouter | $0.05 | $0.08 | $0.03 | 131K |
| Hugging Face Inference Providers | $0.06 | $0.06 | – | 131K |
| Cloudflare Workers AI | $0.15 | $0.29 | – | 32K |
| Amazon Bedrock | $0.22 | $0.22 | – | 128K |
| Amazon Bedrock | $0.22 | $0.22 | – | 128K |

## FAQ

### What is the context window of Llama 3.1 8B Instruct fp8?

Llama 3.1 8B Instruct fp8 has a context window of 32,000 tokens (32K) and can generate up to 32,000 tokens in a single response, according to models.dev.

### How much does the Llama 3.1 8B Instruct fp8 API cost?

Llama 3.1 8B Instruct fp8 is listed from $0.02 per million input tokens and $0.05 per million output tokens (Novita AI). Prices last verified 4 Oct 2026.

### Is Llama 3.1 8B Instruct fp8 open source?

Llama 3.1 8B Instruct fp8 is an open-weight model: its weights are published on Hugging Face as meta-llama/Meta-Llama-3.1-8B-Instruct under the llama3.1 license. Check the license terms before commercial use.

### When was Llama 3.1 8B Instruct fp8 released?

Meta released Llama 3.1 8B Instruct fp8 on 23 Jul 2024, according to models.dev.

### Which providers offer Llama 3.1 8B Instruct fp8?

We track Llama 3.1 8B Instruct fp8 on 5 providers: Novita AI, OpenRouter, Hugging Face Inference Providers, Cloudflare Workers AI, Amazon Bedrock.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Llama 3.1 8B Instruct fp8", https://www.aimodel.directory/models/llama-3-1-8b-instruct