LobstackGateway API
Models & providers
18 models you can ask for today across 4 providers, out of 36 keys in the registry — the other 18 are previous-generation keys kept so older configurations still price. Generated from the registry the router and the meter both read, so it cannot drift from what the Gateway actually serves.
A Lobstack model key is what you send as model. It maps to a provider, a provider-native model id, a capability tier and a price per million tokens. The API listing also includes a required capabilities array that says which Gateway operation accepts the entry. The same registry answers three questions: which model the router may pick, which id goes on the wire, and what the tokens cost.
Prices are list prices in USD per million tokens, used for metering rather than for invoicing. Every one of them was last checked against the provider's own pricing page on 2026-10-16. Prices in this category move often; check again before you quote one.
Current generation
These are the 18 keys a picker should offer first, and the pool the router draws from for auto.
| Key | Provider | Tier | Context | $/M in | $/M out |
|---|---|---|---|---|---|
| claude-fable-5-1 | Anthropic | flagship | 1M | $10.00 | $50.00 |
| gpt-6-astra | OpenAI | flagship | 1.05M | $10.00 | $50.00 |
| claude-opus-5-5 | Anthropic | flagship | 1M | $4.00 | $20.00 |
| gemini-4-argon | flagship | 1.05M | $2.00 | $10.00 | |
| gemini-3.1-pro | premium | 1.05M | $2.00 | $12.00 | |
| gpt-6-sol | OpenAI | premium | 1.05M | $2.00 | $10.00 |
| gpt-6.1-sol | OpenAI | premium | 1.05M | $2.00 | $10.00 |
| grok-4.7 | xAI | premium | 500K | $2.00 | $6.00 |
| grok-4.6 | xAI | premium | 500K | $2.00 | $6.00 |
| grok-4.5 | xAI | premium | 500K | $2.00 | $6.00 |
| claude-sonnet-5-5 | Anthropic | standard | 1M | $2.00 | $10.00 |
| grok-4.3 | xAI | standard | 1M | $1.25 | $2.50 |
| gemini-3.8-flash | standard | 1.05M | $0.75 | $3.75 | |
| grok-build-0.1 | xAI | small | 256K | $1.00 | $2.00 |
| claude-haiku-5-5 | Anthropic | small | 1M | $0.10 | $0.50 |
| gemini-3.5-flash-lite | nano | 1.05M | $0.30 | $2.50 | |
| gemini-3.1-flash-lite | nano | 1.05M | $0.25 | $1.50 | |
| gpt-6-luna | OpenAI | nano | 1.05M | $0.10 | $0.50 |
Previous generation
These 18 keys are kept so stored configurations keep resolving. Where a provider retired a model outright, the key survives and points at the documented successor — and it is priced at the successor's rate, because a retired model now served by a cheaper engine must not keep billing at the old one.
3 of them redirect today: Gemini 3.5 Flash → Gemini 3.6 Flash; Grok 3 → Grok 4.3; Grok 4.1 Fast → Grok 4.3.
| Key | Provider | Tier | Context | $/M in | $/M out |
|---|---|---|---|---|---|
| claude-opus-5 | Anthropic | flagship | 1M | $5.00 | $25.00 |
| claude-opus-4-6 | Anthropic | flagship | 1M | $5.00 | $25.00 |
| gpt-5.6 | OpenAI | flagship | 1.05M | $4.00 | $20.00 |
| gpt-5.2 | OpenAI | flagship | 400K | $1.75 | $14.00 |
| gpt-5.6-terra | OpenAI | premium | 1.05M | $2.00 | $12.00 |
| gpt-5 | OpenAI | premium | 400K | $1.25 | $10.00 |
| claude-sonnet-4-5 | Anthropic | standard | 200K | $3.00 | $15.00 |
| gpt-4o | OpenAI | standard | 128K | $2.50 | $10.00 |
| claude-sonnet-5 | Anthropic | standard | 1M | $2.00 | $10.00 |
| gemini-2.5-pro | standard | 1.05M | $1.25 | $10.00 | |
| grok-3 | xAI | standard | 1M | $1.25 | $2.50 |
| gemini-3.6-flash | standard | 1.05M | $0.75 | $3.75 | |
| gemini-3.5-flash | standard | 1.05M | $0.75 | $3.75 | |
| claude-haiku-4-5 | Anthropic | small | 200K | $1.00 | $5.00 |
| gpt-5-mini | OpenAI | small | 400K | $0.25 | $2.00 |
| grok-4.1-fast | xAI | nano | 1M | $1.25 | $2.50 |
| gpt-5.6-luna | OpenAI | nano | 1.05M | $0.20 | $1.20 |
| gpt-5-nano | OpenAI | nano | 400K | $0.05 | $0.40 |
What is not here
Anthropic Mythos
Mythos exists and it sits above Fable, and it is deliberately absent from this catalog. It ships through trusted-access programmes and is not generally available on the API. Listing it would advertise a model no customer of ours can call.
Models from companies outside the US
Every model here comes from a US company: Anthropic, OpenAI, Google and xAI. The non-US providers previously listed here were removed on 2026-10-11. None of them had served a request through the Gateway. A request that names one of their keys is now refused as an unknown model with 400; named models are never silently changed into auto. Use auto when you want Nex to choose from the available catalog.
Aliases
The resolver accepts a set of non-canonical spellings that turn up in stored configurations: provider-native ids, hyphenated variants, and models listed before this catalog existed. gemini-2-5-pro resolves to gemini-2.5-pro; gpt-4o-mini resolves to gpt-5-mini.
Aliases matter for billing, not just for routing. An unresolved key prices at zero, which is the most expensive way to be wrong here: a live agent ran on gemini-2-5-pro and every one of its requests metered free. Pricing goes through the same resolver as routing so that cannot happen again. Resolving a key for routing but not for pricing would be worse than not resolving it at all.
Listing models over the API
curl https://www.lobstack.ai/api/gateway/v1/models{
"id": "claude-sonnet-5",
"object": "model",
"owned_by": "anthropic",
"label": "Claude Sonnet 5",
"tier": "standard",
"capabilities": ["chat"],
"context_window": 1000000,
"price_per_mtok": { "input": 2, "output": 10 },
"managed": true
}The listing is OpenAI-shaped with Lobstack fields added, so client.models.list() works. Every entry has a non-empty capabilities array: chat means it can be sent to /chat/completions, embedding means it can be sent to /embeddings, and routeridentifies Nex. The auto entry has both chatand router. Filter for capabilities.includes("chat")when building a chat picker; do not infer capabilities from a missing field, the legacy embedding type, or tier. It returns the canonical keys only; aliases resolve on a request but are not enumerated.