# Keyless provider survey

Reviewed 2026-10-12. Discovery used public primary documentation and metadata. Live probes contained small synthetic prompts, never private conversation or repository context, and executed no tools. The complete sanitized survey is recorded with the keyless fallback work order.

## Kilo Gateway

[Kilo authentication documentation](https://kilo.ai/docs/gateway/authentication) explicitly permits anonymous free-model requests, limited to 200 per hour per IP. Its [API reference](https://kilo.ai/docs/gateway/api-reference) specifies the OpenAI-compatible base `https://api.kilo.ai/api/gateway`, `POST /chat/completions`, streaming, native tools and structured output. No authorization or client-identity adapter was required by the probes.

The unauthenticated [model catalog](https://api.kilo.ai/api/gateway/models) returned 391 rows, 486,989 bytes, SHA-256 `5fa77a837d02c12c0a3b68f7fd7bf18c09c4f988c30a25de0a012311fe6330fd`. Sixteen rows advertised explicit zero input and output pricing. [Kilo's free-model methodology](https://kilo.ai/landing/free-models) uses both prices, rather than requiring a free suffix. Current metadata must determine eligibility; paid rows never become keyless routes merely because the catalog itself is public.

| Model ID | Tools | Strict schema advertised | Context | Max output |
| --- | --- | --- | ---: | ---: |
| `kilo-auto/free` | Yes | No | 256000 | 32768 |
| `inclusionai/ling-3.1-flash` | Yes | No | 262144 | 235929 |
| `dots-studio/dots-3-note-preview:free` | Yes | Yes | 512000 | 460800 |
| `liquid/lfm-2.5-2.6b:free` | Yes | Yes | 65536 | 8192 |
| `nvidia/nemotron-3.5-lightning:free` | Yes | No | 1000000 | 65536 |
| `thinkingmachines/inkling-small:free` | Yes | No | 1048576 | 262144 |
| `poolside/laguna-s-2.1:free` | Yes | No | 262144 | 32768 |
| `poolside/laguna-xs-2.1:free` | Yes | No | 262144 | 32768 |
| `cohere/north-mini-code:free` | Yes | No | 256000 | 64000 |
| `nvidia/nemotron-3.5-content-safety:free` | No | No | 128000 | 8192 |
| `nvidia/nemotron-3-ultra-550b-a55b:free` | Yes | No | 1000000 | 65536 |
| `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | Yes | No | 256000 | 65536 |
| `google/lyria-3-pro-preview` | No | No | 1048576 | 65536 |
| `google/lyria-3-clip-preview` | No | No | 1048576 | 65536 |
| `nvidia/nemotron-3-super-120b-a12b:free` | Yes | Yes | 262144 | 235929 |
| `openrouter/free` | Yes | Yes | 200000 | Unknown |

Tools and strict schema in this table reflect `supported_parameters`, including `tools` and `structured_outputs`; absence is not a live capability proof. Context and output limits come from the catalog and its `top_provider`. Content-safety classifiers and Lyria audio-generation models are unsuitable for general conversational fallback despite zero pricing. Auto/router models can change their underlying provider.

Three anonymous streamed probes completed with normal terminal receipts and `usage.cost: 0`, `is_byok: false`:

- Liquid returned exactly `OK` in 1.358 seconds.
- Nemotron 3 Super returned the requested custom `omnius_probe` call with correct arguments in 1.140 seconds. Nothing executed.
- Nemotron 3 Super returned correct JSON under a strict schema in 3.641 seconds.

Nemotron 3 Super is the preferred model established by these native-tool and schema probes. Liquid is a verified fast text alternative. These synthetic checks do not establish performance on complex tasks or every catalog model. Kilo documents [provider-specific data handling and NVIDIA trial terms](https://kilo.ai/docs/gateway/models-and-providers).

## Other reviewed families

The [public inference registry](https://robit-man.github.io/inference/) contains twelve families. LLM7 and OVH have model-specific native chat contracts; ch.at is a catalog-less text route. [OpenCode discovery and accepted compatibility shapes](opencode-free-model-discovery.md) are documented separately.

OVH's [official capabilities](https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-capabilities) distinguish anonymous access at two requests per minute per IP/model from authenticated access. Advertised authenticated catalog prices do not establish a charge for a request that uses the documented pinned anonymous tier. This is a provider-specific distinction, not a general waiver of zero-price checks for other catalogs.

AI Horde accepted an anonymous asynchronous text job, which remained queued and was canceled; a second submission received HTTP 403. Its text job API needs prompt serialization, worker-context validation, bounded polling and cancellation. No completed Horde generation was verified. Public Hugging Face Gradio Spaces need per-application schemas and session handling; the official Qwen3 demo exposed its named API, but the synthetic call failed session initialization. Public dedicated Hugging Face endpoints need owner-published URLs. inference.sh embeds are publisher-funded hosted agents, not generic model endpoints. Jina Reader extracts documents; AHM7's documented image-chat endpoint requires an image. These families cannot be assumed to preserve native chat/tools/schema contracts.

The current Pollinations API, Airforce, HackClub, FreeInference and Puter's CLI-compatible flow require account credentials. llmfaucet and the KeylessAI relay had unresolved advertised API hosts during this survey. Prexzy had no verified active conversational endpoint. None supplied an additional verified anonymous route.
