Skip to main content
On this page

Models

GET /v1/models lists the models a key may use, with the metadata a client needs to configure itself. The list is per key: a key limited to some models lists only those.

The models#

Model idContextMax outputVisionToolsReasoning effortsInput modalities
glm-5.31,048,576131,072noyeslow, high, maxtext
deepseek-v4.1-flash1,048,576393,216yesyeslow, high, maxtext, image
deepseek-dgx1,048,576393,216yesyeslow, high, maxtext, image
glm-5.3-flash1,048,576131,072yesyesno effort values publishedtext, image, video, file
deepseek-v4.1-flash-abliterated1,048,576131,072yesyeslow, high, maxtext, image
glm-5.3-abliterated1,048,576131,072noyeslow, high, maxtext
glm-5.3-flash-abliterated1,048,576131,072noyeslow, high, maxtext

An embedding model is listed with output_modalities: ["embedding"] and its dimensions; Embeddings is its endpoint. GET /v1/models is the current list for any key.

A prompt plus the output it may ask for must fit the context window. A request over it is refused with the context length error, context_length_exceeded in the OpenAI format, so an agent that compacts on it keeps doing so.

deepseek-dgx is DeepSeek V4.1 Flash served on our own DGX Spark, and it is the only model the Sparks serve.

One id per model#

A model has one id: what GET /v1/models lists and what a request sends. A request may add the :zdr suffix to ask for zero-retention serving only (glm-5.3:zdr): the suffix is stripped before routing, and the request answers 503 zdr_unavailable rather than being served by a transient rented-GPU route. A key carries the same restriction as a switch, "zero-retention routes only", on the key's settings page: the simpler choice for a client that must never leave the zero-retention tier. A zero-retention key's GET /v1/models lists only the models a zero-retention route serves, so an agent does not learn an id it cannot use. Zero retention explains the two serving tiers.

Abliterated variants#

An id that ends in -abliterated is the model as released with the refusal behaviour the provider trained into it removed. A variant has no retention rule of its own: it is served under the same retention rules and the same acceptable use policy as every other model, and it is priced like any other model. The models page marks the variant and says what the change does, and zero retention explains which routes are contractually zero-retention and which are the transient rented-GPU tier.

Pricing#

Prices are in EUR per 1M tokens, in three buckets: input, cached input and output. A cached input token is charged the cached price, at or below the input rate (equal where the model's provider gives no cache discount), and a cache write is free because it is included in the input price. Reasoning tokens are output tokens, never a fourth price.

Prices are published and fixed per model. The price of a bucket does not depend on how a request is served, so a request is charged the price shown when it ran. The published price is the promise. This page prints no figure because the list changes; GET /v1/models returns the current prices for the key that asks, and the dashboard shows the same numbers.

Ask for the list#

cURLbash
curl -sSf https://api.zdr.sh/v1/models \  -H "Authorization: Bearer $ZDR_API_KEY"
json
{"object":"list","data":[{"id":"glm-5.3","object":"model","created":1759400000,"owned_by":"zdr.sh","name":"GLM 5.3","context_window":1048576,"context_length":1048576,"max_output_tokens":131072,"input_modalities":["text"],"reasoning":true,"supported_reasoning_efforts":["low","high","max"],"supports_tools":true}]}

The fields#

FieldMeaning
idThe string to send as model
objectAlways model
createdWhen the model was added, Unix seconds
owned_byAlways zdr.sh
nameThe display name, for example GLM 5.3
context_window, context_lengthThe context window under both names
max_output_tokensThe largest output the model accepts
input_modalitiestext, image, video, file
output_modalitiestext on a chat model, embedding on an embedding model
embedding_dimensionsThe vector size on an embedding model, 0 on a chat model
reasoningWhether the model can think before answering
supported_reasoning_effortsThe values reasoning_effort may take, [] when the model has no effort control
supports_toolsWhether the model can call tools
input_eur_per_1m, cached_eur_per_1m, output_eur_per_1mThe price of each bucket, in EUR per million tokens

Anthropic shape#

Send an anthropic-version header and the answer is the Anthropic list shape. The ids are the same; the metadata is the minimum the shape carries.

cURLbash
curl -sSf https://api.zdr.sh/v1/models \  -H "x-api-key: $ZDR_API_KEY" \  -H "anthropic-version: 2023-06-01"
json
{"data":[{"type":"model","id":"glm-5.3","display_name":"GLM 5.3","created_at":"2026-10-02T12:00:00Z"}],"has_more":false,"first_id":"glm-5.3","last_id":"glm-5.3"}

A claude- id is never listed, even when the key maps one. Messages has the mapping.

Discovery in practice#

  • opencode does not call this endpoint for a custom provider: list the models in opencode.json
  • Hermes Agent probes it, so a model added to the list shows up without a config change
  • Claude Code keeps only ids containing claude or anthropic, so add zdr.sh ids by hand as in the Claude Code page

This site uses only the technical cookies the sign-in and the security need. No analytics, no advertising, no tracking. Cookie policy