grok-4.20-0309-reasoning
grok-4.20-0309-reasoning (xAI) — 128K context, Reasoning tier. Input price: $1.3125/M · Output price: $2.625/M · Avg latency 48ms. Routed via Routara OpenAI-compatible endpoint with multi-region failover and metered billing.
Input price: $1.3125/M · Output price: $2.625/M · TTFT: 48ms
Specifications
- Developer: xAI
- Category: Reasoning
- Context window: 128K
- Input price: $1.3125 / 1M
- Output price: $2.625 / 1M
- Avg latency: 48 ms
- SLA grade: A
Typical use cases
- Multi-step reasoning and agent workflows
- RAG pipelines with tool calling
- Code generation, review, and test synthesis
FAQ
- How is grok-4.20-0309-reasoning priced on Routara? — Input tokens are billed at $1.3125/M and output at $2.625/M. Charges are metered per request with no separate platform fee.
- Is grok-4.20-0309-reasoning OpenAI-compatible? — Yes. Point any OpenAI SDK to https://api.routara.ai/v1 and set model to the Routara slug shown below.
- Does grok-4.20-0309-reasoning support streaming? — Streaming is supported when the upstream route is live. Use stream: true in chat.completions.
Related models
- audio1.0 (/detail/audio1-0)
- grok-imagine-image (/detail/grok-imagine-image)
- grok-imagine-image-pro (/detail/grok-imagine-image-pro)
Quick integration
- curl https://api.routara.ai/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"grok-4.20-0309-reasoning","messages":[{"role":"user","content":"Hello"}],"stream":true}'