gpt-5.3-codex-spark
gpt-5.3-codex-spark (OpenAI) — 128K context, Coding tier. Input price: $1.47/M · Output price: $11.76/M · Avg latency 24ms. Routed via Routara OpenAI-compatible endpoint with multi-region failover and metered billing.
Input price: $1.47/M · Output price: $11.76/M · TTFT: 24ms
Specifications
- Developer: OpenAI
- Category: Coding
- Context window: 128K
- Input price: $1.47 / 1M
- Output price: $11.76 / 1M
- Avg latency: 24 ms
- SLA grade: A
Typical use cases
- Code generation, review, and test synthesis
- RAG pipelines with tool calling
- Multi-step reasoning and agent workflows
FAQ
- How is gpt-5.3-codex-spark priced on Routara? — Input tokens are billed at $1.47/M and output at $11.76/M. Charges are metered per request with no separate platform fee.
- Is gpt-5.3-codex-spark OpenAI-compatible? — Yes. Point any OpenAI SDK to https://api.routara.ai/v1 and set model to the Routara slug shown below.
- Does gpt-5.3-codex-spark support streaming? — Streaming is supported when the upstream route is live. Use stream: true in chat.completions.
Related models
- qwen-coder-plus (/detail/qwen-coder-plus)
- qwen-coder-plus-1106 (/detail/qwen-coder-plus-1106)
- qwen-coder-plus-latest (/detail/qwen-coder-plus-latest)
Quick integration
- curl https://api.routara.ai/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"gpt-5.3-codex-spark","messages":[{"role":"user","content":"Hello"}],"stream":true}'