OpenAI-compatible gateway at https://api.kilo.ai/api/gateway (/chat/completions, SSE streaming, tool calling).
Anonymous free access: :free-suffixed models need no API key at all. Unauthenticated requests are IP-identified and rate limited to 200 requests/hour/IP. This is the only known free tier with zero account requirement.
Model catalog endpoint GET /api/gateway/models requires no authentication; returns pricing, context window, modalities → live discovery is possible and necessary.
Free pool (rotates; sample at research time): minimax/minimax-m2.1:free, z-ai/glm-5:free, stepfun/step-3.7-flash:free, poolside/laguna-s-2.1:free, poolside/laguna-xs-2.1:free, nvidia/nemotron-3-ultra-550b-a55b:free, tencent/hy3:free, plus virtual openrouter/free (best available free model) and kilo-auto/free (server-side routing over the free pool, per-session affinity).
Optional KILO_API_KEY (JWT from a Kilo account) raises limits beyond anonymous; paid credits only for non-free models.
Data caveat: kilo-auto/free may route to providers that log prompts/outputs for service improvement; free-pool providers vary.
Churn evidence
The old extension hardcoded Kilo IDs (inclusionai/ling-2.6-1t:free, tencent/hy3-preview:free, baidu/qianfan-ocr-fast:free, …) in April 2026 — none appear in the current pool.
Confirms the post-mortem: Kilo's failure mode was catalog rot, not auth. Discovery at load + tolerance for empty pools is mandatory.
Verdict
Kilo belongs in gratis v1 — as the keyless tier:
Only backend delivering the "zero config" goal literally: no env var, no account, visible out of the box.
Requires a spec amendment: current spec ties visibility to key resolution; Kilo is visible without a key (network permitting), KILO_API_KEY optional as enhancement.
Anonymity is IP-scoped → shared egress (office/VPN) shares the 200 req/h budget; keyed mode avoids that.
Unresolved questions
Whether a KILO_API_KEY actually raises the free-model rate limit above 200 req/h/IP (docs state anonymous limiting; keyed free-model limit unpublished).
openrouter/free and kilo-auto/free are virtual models whose underlying mapping changes server-side; their effective context window is unknown → catalog must treat virtual models conservatively.
---
id: PX-RESEARCH-KZ2M6WQ4
type: research
title: Kilo Gateway Free Access
---
## Kilo Gateway Free Access
Re-evaluation of Kilo as a gratis backend, requested after the [Free Extension Post-Mortem](../PX-RESEARCH-LXU8HWNJ-free-extension-post-mortem/index.md) flagged Kilo as unresolved.
Sources: [Authentication](https://kilo.ai/docs/gateway/authentication), [Models & Providers](https://kilo.ai/docs/gateway/models-and-providers), [Using Kilo for Free](https://kilo.ai/docs/getting-started/using-kilo-for-free), [Gateway overview](https://kilo.ai/docs/gateway).
### Facts
- OpenAI-compatible gateway at `https://api.kilo.ai/api/gateway` (`/chat/completions`, SSE streaming, tool calling).
- **Anonymous free access: `:free`-suffixed models need no API key at all.** Unauthenticated requests are IP-identified and rate limited to 200 requests/hour/IP. This is the only known free tier with zero account requirement.
- Model catalog endpoint `GET /api/gateway/models` requires no authentication; returns pricing, context window, modalities → live discovery is possible and necessary.
- Free pool (rotates; sample at research time): `minimax/minimax-m2.1:free`, `z-ai/glm-5:free`, `stepfun/step-3.7-flash:free`, `poolside/laguna-s-2.1:free`, `poolside/laguna-xs-2.1:free`, `nvidia/nemotron-3-ultra-550b-a55b:free`, `tencent/hy3:free`, plus virtual `openrouter/free` (best available free model) and `kilo-auto/free` (server-side routing over the free pool, per-session affinity).
- Optional `KILO_API_KEY` (JWT from a Kilo account) raises limits beyond anonymous; paid credits only for non-free models.
- Data caveat: `kilo-auto/free` may route to providers that log prompts/outputs for service improvement; free-pool providers vary.
### Churn evidence
The old extension hardcoded Kilo IDs (`inclusionai/ling-2.6-1t:free`, `tencent/hy3-preview:free`, `baidu/qianfan-ocr-fast:free`, …) in April 2026 — none appear in the current pool.
Confirms the post-mortem: Kilo's failure mode was catalog rot, not auth. Discovery at load + tolerance for empty pools is mandatory.
### Verdict
Kilo belongs in gratis v1 — as the keyless tier:
- Only backend delivering the "zero config" goal literally: no env var, no account, visible out of the box.
- Requires a spec amendment: current spec ties visibility to key resolution; Kilo is visible without a key (network permitting), `KILO_API_KEY` optional as enhancement.
- Anonymity is IP-scoped → shared egress (office/VPN) shares the 200 req/h budget; keyed mode avoids that.
### Unresolved questions
- Whether a `KILO_API_KEY` actually raises the free-model rate limit above 200 req/h/IP (docs state anonymous limiting; keyed free-model limit unpublished).
- `openrouter/free` and `kilo-auto/free` are virtual models whose underlying mapping changes server-side; their effective context window is unknown → catalog must treat virtual models conservatively.