multimodal-embedding-v1
multimodal-embedding-v1 (ali) — 128K context, General tier. Price per image: $0.00012 · Avg latency 32ms. Routed via Routara OpenAI-compatible endpoint with multi-region failover and metered billing.
Price per image: $0.00012 · TTFT: 32ms
Specifications
- Developer: ali
- Category: General
- Context window: 128K
- Price per image: $0.00012
- Avg latency: 32 ms
- SLA grade: A
Typical use cases
- Image and video generation pipelines
- Multilingual chatbots and customer support
- RAG pipelines with tool calling
FAQ
- How is multimodal-embedding-v1 priced on Routara? — $0.00012 per generated image, metered per request with no separate platform fee.
- Is multimodal-embedding-v1 OpenAI-compatible? — Yes. Point any OpenAI SDK to https://api.routara.ai/v1 and set model to the Routara slug shown below.
- Does multimodal-embedding-v1 support streaming? — Streaming is supported when the upstream route is live. Use stream: true in chat.completions.
Related models
- ai_infer_test_1 (/detail/ai-infer-test-1)
- ai_infer_test_2 (/detail/ai-infer-test-2)
- ai_infer_test_3 (/detail/ai-infer-test-3)
Quick integration
- curl https://api.routara.ai/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"multimodal-embedding-v1","messages":[{"role":"user","content":"Hello"}],"stream":true}'