Docs / Catalog

Models and providers

Every model ID identifies both the upstream provider and that provider's model. The live catalog is embedded in the running gateway.

Namespaced model IDs

Use the exact provider/model form. The provider prefix selects an adapter and credential. The rest of the ID is sent to that provider.

anthropicprovider prefix / claude-sonnet-4-6provider model

Provider prefixes are lowercase and case-sensitive. Empty path segments are invalid. A well-formed ID must also exist in the embedded catalog. If any entry in a models fallback array is unknown, LaneZero rejects the whole request before contacting a provider.

Supported providers

The same prefixes are used in model IDs, named passthrough headers such as x-provider-key-openai, and provider-key management routes.

Anthropic

anthropic/

OpenAI

openai/

Google

google/

xAI

xai/

DeepSeek

deepseek/

Qwen

qwen/

Moonshot (Kimi)

moonshot/

Z.ai

zai/

MiniMax

minimax/

Tencent (Hunyuan)

tencent/

Mistral

mistral/

Meta (Llama API)

meta/

Live model catalog

The running server exposes its accepted model IDs at GET /v1/models. The result is sorted by ID. Each item includes id, object: "model", and the provider prefix in owned_by.

Open GET /v1/models

The live route requires a gateway bearer key, including when opened in a browser. Use the command below when the browser request returns 401.

curl "$RACEWAY_URL/v1/models" \
  -H "Authorization: Bearer $RACEWAY_KEY"

The endpoint lists catalog membership only. It does not expose price, context-window, output-limit, or tool-support metadata.

Pricing and cost estimates

The catalog is seeded from LiteLLM's public model_prices_and_context_window.json pricing dataset, used under its MIT license. LaneZero attributes that source in the catalog loader and project notices. Z.ai and Tencent entries are locally curated from their public price tables because the embedded LiteLLM data does not supply those mappings.

When a provider reports token usage and the catalog has both input and output prices, LaneZero calculates:

est_cost_usd = input tokens × input USD per token + output tokens × output USD per token

It is an estimate

est_cost_usd is analytics. It is not an invoice, charge, or billed amount. Provider pricing and billing rules remain authoritative.

It can be absent

The stored estimate is null when usage is unavailable or either catalog price is unavailable. Usage summaries treat missing estimates as zero.

LaneZero never bills for model use. Advisory spend caps compare the current month's accumulated estimates with a configured cap. They do not stop requests.