meta-llama/llama-4-maverick-17b-128e-instruct-fp8
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 (meta-llama) — 128K context, Lightweight tier. Input-Preis: $0.5940000000000001/M · Output-Preis: $1.8700000000000003/M · Latenz 18ms. Routed via Routara OpenAI-compatible endpoint with multi-region failover and metered billing.
Input-Preis: $0.5940000000000001/M · Output-Preis: $1.8700000000000003/M · TTFT: 18ms
Specifications
- Entwickler: meta-llama
- Kategorie: Lightweight
- Kontextfenster: 128K
- Input-Preis: $0.5940000000000001 / 1M
- Output-Preis: $1.8700000000000003 / 1M
- Latenz: 18 ms
- SLA: S
Typical use cases
- High-QPS-Klassifikation
- Mehrsprachige Chatbots
- RAG und Tool-Aufrufe
FAQ
- Wie wird meta-llama/llama-4-maverick-17b-128e-instruct-fp8 auf Routara abgerechnet? — Input $0.5940000000000001/M, Output $1.8700000000000003/M — nutzungsbasiert ohne Plattformgebühr.
- Ist meta-llama/llama-4-maverick-17b-128e-instruct-fp8 OpenAI-kompatibel? — Ja. base_url: https://api.routara.ai/v1
- Unterstützt meta-llama/llama-4-maverick-17b-128e-instruct-fp8 Streaming? — Ja, wenn die Route live ist (stream: true).
Related models
- z-image-turbo (/detail/z-image-turbo)
- qwen-7b-chat (/detail/qwen-7b-chat)
- qwen-flash-character (/detail/qwen-flash-character)
Quick integration
- curl https://api.routara.ai/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","messages":[{"role":"user","content":"Hello"}],"stream":true}'