Docs / Concepts / Lanes

Lanes

A lane is a URL prefix that selects which catalog and routing rules a request uses. Append the standard OpenAI/Anthropic path after it. Every lane serves both wire protocols.

/oss — curated open-weight catalog

The default public lane, serving open-weight models only: curated coding flagships (Kimi, MiniMax, Qwen, DeepSeek, GLM and GPT-OSS) with live provider routing. The catalog is curated independently of upstream config, so model discovery is reliable for Claude Code Desktop, IDE, and CLI.

ProtocolEndpoint
OpenAI ChatPOST /oss/v1/chat/completions
OpenAI ResponsesPOST /oss/v1/responses
Anthropic MessagesPOST /oss/v1/messages
EmbeddingsPOST /oss/v1/embeddings
DiscoveryGET /oss/v1/models

Friendly aliases

The curated catalog exposes discovery aliases for IDE and Desktop pickers. Each entry's display_name leads with the real underlying model — e.g. GLM 5.2 · agentic coding — so the names stay honest. Claude Code's picker (which only surfaces claude* ids) is populated from these entries. For CLI and scripts, prefer friendly ids like glm-5.2, kimi-k2.6, and qwen3-coder. Call GET /oss/v1/models for the freshest list.

Open modelCLI idBest for
GLM 5.2glm-5.2Agentic coding (1M context)
Kimi K2.7 Codemoonshotai/Kimi-K2.7-Code:preferredLong-context agentic coding
Qwen3-Coder 480Bqwen3-coderAgentic coding
DeepSeek V4-Prodeepseek-v4-proMax reasoning
MiniMax M3MiniMaxAI/MiniMax-M3:preferredMillion-token coding
GPT-OSS 120Bgpt-oss-120bFast reasoning
GPT-OSS 20Bgpt-oss-20bFast & low-cost

Raw ids & routing policies

You can also call any catalog model by its raw org/model id and pin provider-selection behavior with a suffix:

SuffixMeaning
:preferredThe gateway's preferred provider for that model.
:fastestLowest-latency live provider.
:cheapestLowest-cost live provider.
:<provider>Pin a specific provider by name.
text
moonshotai/Kimi-K2.7-Code:preferred
Qwen/Qwen3-Coder-480B-A35B-Instruct:fastest
openai/gpt-oss-120b:cheapest

For cost control, route bulk or low-stakes work to :cheapest and reserve :fastest or :preferred for latency- and quality-sensitive requests.

/hf — full passthrough

Specify any Hugging Face model id and OpenGateway validates and routes it to a provider. Discovery is served from the cron-built catalog cache. Same wire protocols as /oss; passthrough is opt-in by specifying an id and never changes the curated default surface. Ids are validated and upstream identity is always scrubbed from responses and errors.

Scope of these docs

These public docs cover open-weight lanes only. Stay on /oss for curated, reliable open-weight work.