Models

List model endpoints

List every eligible provider endpoint that serves one model, with its prices, limits and capabilities.

GEThttps://api.numes.ai/api/v1/models/{author}/{slug}/endpoints

Each endpoint's tag is the selector for provider.order, provider.only and provider.ignore. Prices are exact per-unit rates in your key's currency. An unknown model, or one you can't access, returns 404. Guide: Provider routing.

The list comes from the same published catalogue as List models; the X-Catalogue-* headers report when it was published and whether it's stale. If no recent catalogue is available, the response is 503 catalogue_unavailable.

Authorization

AuthorizationheaderRequired

Bearer inference key. Charges settle in the key's billing currency. Authorization: Bearer $NUMES_API_KEY

Headers

X-Request-Idstring: Correlation ID, not an idempotency key. Inference request IDs recorded with a generation are unique per account. A traffic-admitted request reusing a recorded ID returns 400 invalid_request. Traffic admission rejection takes precedence over this conflict, including for reused IDs; it performs no generation lookup and writes no generation, result or attempt. Rate-limit rejection returns 429 rate_limited with Retry-After; an inference limiter outage retains 500 server.
Length1–128

Path parameters

authorstringRequired: Pattern^[a-z0-9][a-z0-9._-]*$
slugstringRequired: Pattern^[A-Za-z0-9][A-Za-z0-9._:-]*$

Responses

200Model and endpoint detailapplication/json

Headers

X-Catalogue-Generationstring: The completed worker publication identifier.
X-Catalogue-Supply-Captured-Atstring<date-time>: Consistent supply capture time; supply is captured every 30 seconds by default and a new healthy response is at most one minute old.
X-Catalogue-Staleboolean: True during ordinary stale browsing, which ends at five minutes of supply age.
X-Catalogue-Statistics-Availableboolean: Whether the publication has fresh statistical coverage.
X-Catalogue-Statistics-As-Ofstring<date-time>: Completed statistical coverage time, when any coverage is pinned.
X-Request-Idstring: Correlation identifier assigned or accepted by the service.

BodyModelEndpointsResponseapplication/json

dataobjectRequired

Show6 child attributes

idstringRequired

namestringRequired

createdinteger<int64>Required

descriptionstringRequired

Length≤ 32,768

architectureobjectRequired

Show5 child attributes

modalitystringRequired
input_modalitiesarray<enum<string>>Required: One oftextimagefileaudio
output_modalitiesarray<enum<string>>Required: One oftextimageaudioembeddings
tokenizerstringRequired
instruct_typestring | null

endpointsarray<object>Required

Show18 child attributes

namestringRequired

provider_namestringRequired

context_lengthintegerRequired

pricingobjectRequired

Exact per-unit prices in the inference key's immutable billing currency. For BTC keys, values are Bitcoin base units (1 is one satoshi), token prices have up to thirty decimal places, and clients may display them with BIP177 notation such as ₿123/M.

Show10 child attributes

promptstringRequired

Pattern^-?[0-9]+(\.[0-9]+)?$

completionstringRequired

Pattern^-?[0-9]+(\.[0-9]+)?$

requeststringRequired

Pattern^-?[0-9]+(\.[0-9]+)?$

imagestringRequired

Pattern^-?[0-9]+(\.[0-9]+)?$

audiostringRequired

Pattern^-?[0-9]+(\.[0-9]+)?$

pricing_basisenum<string>

One offixedusd_indexed

referenceobject

Show5 child attributes

idstring<uuid>Required
policystringRequired
usd_per_btcstringRequired
observed_atstring<date-time>Required
expires_atstring<date-time>Required

usd_ratesmap<string, string>

USD anchor rates for the same displayed price categories; present only for USD-indexed Bitcoin schedules.

input_cache_readstring

Pattern^[0-9]+(\.[0-9]+)?$

input_cache_writestring

Pattern^[0-9]+(\.[0-9]+)?$

supported_parametersarray<string>Required

tagstring

max_completion_tokensinteger | null

Range≥ 1

max_prompt_tokensinteger

Range≥ 1

reasoningobject

Show5 child attributes

default_effortstring | null
default_enabledboolean
mandatoryboolean
supports_max_tokensboolean
supported_effortsarray<enum<string>>: One ofnoneminimallowmediumhighxhighmax

billing_currencyenum<string>

One ofUSDBTC

usage_meterstring

input_modalitiesarray<enum<string>>

One oftextimagefileaudio

output_modalitiesarray<enum<string>>

One oftextimageaudioembeddings

maximum_output_lengthinteger | null

Range≥ 1

embeddingsboolean

Defaultfalse

supported_hosted_toolsarray<enum<string>>

One ofopenrouter.web_search@1openrouter.web_fetch@1openrouter.datetime@1openrouter.image_generation@1openrouter.apply_patch@1openrouter.fusion@1openrouter.advisor@1openrouter.subagent@1openai.web_search@1openai.file_search@1openai.code_interpreter@1openai.image_generation@1openai.shell@1openai.mcp@1openai.connectors@1openai.tool_search@1openai.skills@1anthropic.web_search@1anthropic.web_fetch@1anthropic.code_execution@1anthropic.advisor@1anthropic.tool_search@1anthropic.mcp@1google.search@1google.maps@1google.url_context@1google.file_search@1google.code_execution@1

quantizationstring | null

uptime_last_30mnumber | null

404The requested model is not in the caller's compatible catalogue: the slug is unknown, the model is not currently published, it is not offered in the key's settlement currency, or the caller may not use it. These cases share one identical response body (`error.code` 404, `error.metadata.error_type` "not_found") so availability to other callers is never disclosed. This classification applies to model endpoint discovery; inference and encrypted resolution preserve routing failures as 503 `provider_unavailable`.application/json

Headers

X-Request-Idstring: Correlation identifier assigned or accepted by the service.

BodyErrorResponseapplication/json

errorobjectRequired

Show3 child attributes

codeintegerRequired
messagestringRequired
metadataobject

openrouter_metadataobject

ErrorCompatible error envelopeapplication/json

Headers

X-Request-Idstring: Correlation identifier assigned or accepted by the service.
Retry-Afterinteger: Optional delay in seconds for retryable rate or availability errors.
Range≥ 1

BodyErrorResponseapplication/json

errorobjectRequired

Show3 child attributes

codeintegerRequired
messagestringRequired
metadataobject

openrouter_metadataobject

curl "https://api.numes.ai/api/v1/models/openai/gpt-6-luna/endpoints" \  -H "Authorization: Bearer $NUMES_API_KEY"

Response

{  "data": {    "id": "openai/gpt-6-luna",    "name": "Example Model",    "created": 1790000000,    "description": "A compact general-purpose model.",    "architecture": {      "modality": "text->text",      "input_modalities": ["text"],      "output_modalities": ["text"],      "tokenizer": "GPT"    },    "endpoints": [      {        "name": "Example Provider: Primary",        "provider_name": "Example Provider",        "tag": "example-provider/primary",        "context_length": 131072,        "max_prompt_tokens": 131072,        "max_completion_tokens": 16384,        "billing_currency": "USD",          "pricing": {          "prompt": "0.0000001",          "completion": "0.0000004",          "request": "0",          "image": "0",          "audio": "0"        },        "supported_parameters": ["max_tokens", "temperature", "tools", "tool_choice"],        "input_modalities": ["text"],        "output_modalities": ["text"],        "quantization": "fp8"      }    ]  }}