Quick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click the Qoder tile
Sign in with the provider's free flow (AWS Builder ID / Google / GitHub)
Pick the model you want to expose to your IDE
Use in your IDE
Point any OpenAI-compatible client at kRouter using your local API key.
# Endpoint
http://localhost:20128/v1
# API key (from Dashboard → API Keys)
sk-krouter-XXXX
# Model
qd/qoder-defaultHow Qoder billing works with kRouter
Qoder has a genuinely free tier — no card, no per-token cost. Rate limits apply, and kRouter rotates across accounts when you add more than one. kRouter authenticates it via oauth. 12 models are routable as qd/<model>.
Through kRouter, Qoder serves chat and code completion. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from Qoder is a one-line model change in your client rather than a rewrite.
Qoder models & pricing
Prices are USD per 1M tokens, cheapest first. You are not billed per token on this provider — the figures show what the same model costs elsewhere, which is what routing here saves you.
| Model | Route as | Input /1M | Output /1M |
|---|---|---|---|
| Qoder Auto | qd/auto | $2.00 | $8.00 |
| Qoder Ultimate | qd/ultimate | — | — |
| Qoder Performance | qd/performance | — | — |
| Qoder Efficient | qd/efficient | — | — |
| Qoder Lite | qd/lite | — | — |
| Qwen 3.6 Plus (Qoder) | qd/qmodel | — | — |
| Qoder Qwen 3.7 Max | qd/qmodel_latest | — | — |
| DeepSeek V4 Pro (Qoder) | qd/dmodel | — | — |
| DeepSeek V4 Flash (Qoder) | qd/dfmodel | — | — |
| GLM 5.1 (Qoder) | qd/gm51model | — | — |
| Kimi K2.6 (Qoder) | qd/kmodel | — | — |
| MiniMax M2.7 (Qoder) | qd/mmodel | — | — |
Qoder links
Qoder FAQ
Is Qoder free through kRouter?
Qoder does not bill per token here — kRouter uses your existing free tier, so the only cost is whatever you already pay Qoder directly. kRouter itself is MIT-licensed and free.
How do I use Qoder with Claude Code or Cursor?
Connect Qoder in the kRouter dashboard, then point your tool at kRouter's local endpoint (http://localhost:20128/v1) with a kRouter API key. Any OpenAI-compatible client works, and models are addressed as qd/<model>.
Which Qoder models can kRouter route to?
12 models, including Qoder Auto, Qoder Ultimate, Qoder Performance. Every one is addressed as qd/<model> from any client.
What happens when Qoder is rate limited?
kRouter detects the limit, parks that account until its real reset time, and fails over to your next connected account or provider — so the request still completes instead of erroring.