Baltor Get started

Models

Llama-4-Scout-17B-16E-Instruct-FP8

By Llama. Unknown parameters, a context window of 128,000 tokens, licence Unknown.

Facts

Released
2025-04-05 the release date models.dev records models.dev, read
Licence
Unknown
Open weights
Yes models.dev records whether the weights are open models.dev, read
Parameters
Unknown
Active parameters
Unknown
Knowledge cutoff
2024-08 the knowledge cutoff models.dev records models.dev, read
Context window
  • 128,000 tokens the context limit models.dev records for the maker's own API models.dev, read
Longest output
  • 4,096 tokens the output limit models.dev records for the maker's own API models.dev, read
Tool calling
  • Yes models.dev records tool_call as true models.dev, read
Structured output
Unknown
Reasoning controls
  • No models.dev records reasoning as false models.dev, read
Inputs and outputs
text, image in, text out models.dev, read
Good for
  • Vision: models.dev lists images among its inputs models.dev, read

Prices

Prices in US dollars per million tokens, as each source lists them
ProviderInputOutputContextAs ofSource
Llama direct0 USD0 USD128,000 older than 30 days; check the providermodels.dev, read

Run it on your own hardware

No source lists weight files or a parameter count for this model, so its memory needs are Unknown.

Use it from your harness

Set up for Llama with the model llama-4-scout-17b-16e-instruct-fp8. Each endpoint page has the same setup for its own address.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "llama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Llama",
      "options": {
        "baseURL": "https://api.llama.com/compat/v1",
        "apiKey": "{env:LLAMA_API_KEY}"
      },
      "models": {
        "llama-4-scout-17b-16e-instruct-fp8": {
          "name": "Llama-4-Scout-17B-16E-Instruct-FP8",
          "limit": {
            "context": 128000,
            "output": 4096
          }
        }
      }
    }
  }
}
  • OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.

From OpenCode documentation, read .

Pi

Put this in ~/.pi/agent/models.json:

{
  "providers": {
    "llama": {
      "baseUrl": "https://api.llama.com/compat/v1",
      "api": "openai-completions",
      "apiKey": "$LLAMA_API_KEY",
      "models": [
        {
          "id": "llama-4-scout-17b-16e-instruct-fp8"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Llama documents no Responses address. A gateway that offers one can sit in between.

  • Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.

From Codex documentation, read .

Claude Code

Claude Code sends Anthropic Messages requests, and Llama documents no such address. A gateway that translates to that API can sit in between.

  • Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.

From Claude Code documentation, read .

Sources of this page