gemini-3-pro-image-preview-4k
gemini-3-pro-image-preview-4k (Google) — 128K context, Image tier. Input price: $1.3125/M · Output price: $5.25/M · Avg latency 45ms. Routed via Routara OpenAI-compatible endpoint with multi-region failover and metered billing.
Input price: $1.3125/M · Output price: $5.25/M · TTFT: 45ms
Specifications
- Developer: Google
- Category: Image
- Context window: 128K
- Input price: $1.3125 / 1M
- Output price: $5.25 / 1M
- Avg latency: 45 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 gemini-3-pro-image-preview-4k priced on Routara? — Input tokens are billed at $1.3125/M and output at $5.25/M. Charges are metered per request with no separate platform fee.
- Is gemini-3-pro-image-preview-4k OpenAI-compatible? — Yes. Point any OpenAI SDK to https://api.routara.ai/v1 and set model to the Routara slug shown below.
- Does gemini-3-pro-image-preview-4k support streaming? — Streaming is supported when the upstream route is live. Use stream: true in chat.completions.
Related models
- doubao-seedream-3-0-t2i-250415 (/detail/doubao-seedream-3-0-t2i-250415)
- doubao-seedream-4-0-250828 (/detail/doubao-seedream-4-0-250828)
- doubao-seedream-4-5-251128 (/detail/doubao-seedream-4-5-251128)
Quick integration
- curl https://api.routara.ai/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"gemini-3-pro-image-preview-4k","messages":[{"role":"user","content":"Hello"}],"stream":true}'