Llama 4 Scout 17B 16E Instruct
by GitHub Models · family llama · listed Jan 2025RTVW
Open multimodal Llama model for long-context analysis and efficient agents
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
On the record
- Model id
meta/llama-4-scout-17b-16e-instruct- Context window
- 128K tokens
- Max output
- 8K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Dec 2024
- Released
- 2025-01-31
- Last updated
- 2025-01-31
- Provider docs
- docs.github.com/en/github-models
Back of the envelope
≈
Also listed at
- Deep Infra$0.10 in · $0.30 out
- Groq$0.11 in · $0.34 out
- Weights & Biases$0.17 in · $0.66 out
- NovitaAI$0.18 in · $0.59 out
- Azure$0.20 in · $0.78 out
- Azure Cognitive Services$0.20 in · $0.78 out
- Cloudflare Workers AI$0.27 in · $0.85 out
- Cloudflare AI Gateway$0.27 in · $0.85 out