--- title: "Preview the impact of ZDR on the available endpoints" method: GET path: "/endpoints/zdr" tags: ["Endpoints"] --- # Preview the impact of ZDR on the available endpoints `GET /endpoints/zdr` ## Response `200` Returns a list of endpoints - object - `data` PublicEndpoint[], required - `context_length` integer, required - `latency_last_30m` PercentileStats, nullable, required — Latency percentiles in milliseconds over the last 30 minutes. Latency measures time to first token. Only visible when authenticated with an API key or cookie; returns null for unauthenticated requests. - `p50` number, double, required — Median (50th percentile) - `p75` number, double, required — 75th percentile - `p90` number, double, required — 90th percentile - `p99` number, double, required — 99th percentile - `max_completion_tokens` integer, nullable, required - `max_prompt_tokens` integer, nullable, required - `model_id` string, required — The unique identifier for the model (permaslug) - `model_name` string, required - `name` string, required - `pricing` object, required - `audio` string — Price in USD per audio input token - `audio_output` string — Price in USD per audio output token - `completion` string, required — Price in USD per token for completion (output) generation - `discount` number, double — Fractional discount applied to this endpoint's pricing; the price is multiplied by (1 - discount) (0 = no discount, 1 = free) - `image` string — Price in USD per input image - `image_output` string — Price in USD per output image - `image_token` string — Price in USD per image token - `input_audio_cache` string — Price in USD per cached audio input token - `input_cache_read` string — Price in USD per cached input token (read) - `input_cache_write` string — Price per cache-write token, in USD per token. For providers with multiple cache TTLs (e.g. Anthropic), this is the default (5-minute) cache-write rate. - `input_cache_write_1h` string — Price per 1-hour cache-write token, in USD per token. Only present for providers that price an extended (1-hour) cache TTL separately, such as Anthropic. - `internal_reasoning` string — Price in USD per internal reasoning token - `overrides` PricingOverride[] — Conditional overrides of the base pricing (e.g. long-context or time-based pricing). An entry applies when all of its condition fields (e.g. min_prompt_tokens, or the utc_start/utc_end time window) match the request; among applicable entries, later entries win per key; price keys absent from an entry inherit the base price. The top-level pricing keys always reflect the price that applies under default conditions. - `audio` string — Overridden price in USD per audio input token - `completion` string — Overridden price in USD per token for completion (output) generation - `input_audio_cache` string — Overridden price in USD per cached audio input token - `input_cache_read` string — Overridden price in USD per cached input token (read) - `input_cache_write` string — Overridden price in USD per cache-write token - `input_cache_write_1h` string — Overridden price in USD per 1-hour cache-write token - `min_prompt_tokens` number, double — Condition: the entry applies when the total prompt tokens of a request are strictly greater than this threshold - `prompt` string — Overridden price in USD per token for prompt (input) processing - `utc_end` number, double — Condition: exclusive end of a daily UTC time window as an HHMM clock number (e.g. 400 = 04:00) - `utc_start` number, double — Condition: inclusive start of a daily UTC time window as an HHMM clock number (e.g. 100 = 01:00, 1030 = 10:30). The entry applies while the current UTC time is inside the half-open window [utc_start, utc_end), which may wrap past midnight (utc_start > utc_end). - `prompt` string, required — Price in USD per token for prompt (input) processing - `request` string — Price in USD per request - `web_search` string — Price in USD per web search - `provider_name` 'Meta' | 'AkashML' | 'AI21' | 'AionLabs' | 'Alibaba' | 'Ambient' | 'Baidu' | 'Amazon Bedrock' | 'Amazon Nova' | 'Anthropic' | 'Arcee AI' | 'AtlasCloud' | 'Avian' | 'Azure' | 'BaseTen' | 'BytePlus' | 'Black Forest Labs' | 'Cerebras' | 'Chutes' | 'Cirrascale' | 'Clarifai' | 'Cloudflare' | 'Cohere' | 'Crucible' | 'Crusoe' | 'Darkbloom' | 'Decart' | 'Deepgram' | 'DeepInfra' | 'DeepSeek' | 'DekaLLM' | 'DigitalOcean' | 'Featherless' | 'Fireworks' | 'Friendli' | 'GMICloud' | 'Google' | 'Google AI Studio' | 'Groq' | 'HeyGen' | 'Inception' | 'Inceptron' | 'InferenceNet' | 'Ionstream' | 'Infermatic' | 'Io Net' | 'Inferact vLLM' | 'Inflection' | 'Liquid' | 'Mara' | 'Mancer 2' | 'Minimax' | 'ModelRun' | 'Mistral' | 'Modular' | 'Moonshot AI' | 'Morph' | 'NCompass' | 'Nebius' | 'Nex AGI' | 'NextBit' | 'Novita' | 'Nvidia' | 'OpenAI' | 'OpenInference' | 'Parasail' | 'Poolside' | 'Perceptron' | 'Perplexity' | 'Phala' | 'Recraft' | 'Reka' | 'Relace' | 'Sail Research' | 'Sakana AI' | 'SambaNova' | 'Seed' | 'SiliconFlow' | 'Sourceful' | 'StepFun' | 'Stealth' | 'StreamLake' | 'Switchpoint' | 'Tenstorrent' | 'Together' | 'Upstage' | 'Venice' | 'Wafer' | 'WandB' | 'Quiver' | 'Krea' | 'Xiaomi' | 'xAI' | 'Z.AI' | 'FakeProvider', required - `quantization` 'int4' | 'int8' | 'fp4' | 'fp6' | 'fp8' | 'fp16' | 'bf16' | 'fp32' | 'unknown', nullable, required - `status` 0 | -1 | -2 | -3 | -5 | -10 - `supported_parameters` Parameter[], required - `supports_implicit_caching` boolean, required - `tag` string, required - `throughput_last_30m` object, nullable, required — Throughput percentiles in tokens per second over the last 30 minutes. Throughput measures output token generation speed. Only visible when authenticated with an API key or cookie; returns null for unauthenticated requests. - `p50` number, double, required — Median (50th percentile) - `p75` number, double, required — 75th percentile - `p90` number, double, required — 90th percentile - `p99` number, double, required — 99th percentile - `uptime_last_1d` number, double, nullable, required — Uptime percentage over the last 1 day, calculated as successful requests / (successful + error requests) * 100. Rate-limited requests are excluded. Returns null if insufficient data. - `uptime_last_30m` number, double, nullable, required - `uptime_last_5m` number, double, nullable, required — Uptime percentage over the last 5 minutes, calculated as successful requests / (successful + error requests) * 100. Rate-limited requests are excluded. Returns null if insufficient data. ## Other responses - `500` — Internal Server Error - Unexpected server error ## Changes - **2026-07-15** `ada7dbde69ed` — 1 warning - added the new `Krea` enum value to the `data/items/provider_name` response property for the response status `200` - **2026-07-15** `becc20273345` — 1 warning - added the new `prediction` enum value to the `data/items/supported_parameters/items/` response property for the response status `200` - **2026-07-14** `8b656727d0a3` — 1 warning - added the new `Sail Research` enum value to the `data/items/provider_name` response property for the response status `200` - **2026-07-14** `e25e67040f6d` — 2 info - added the optional property `data/items/pricing/overrides/items/utc_end` to the response with the `200` status - added the optional property `data/items/pricing/overrides/items/utc_start` to the response with the `200` status - **2026-07-13** `b0e196d046d6` — 1 info - added the optional property `data/items/pricing/overrides` to the response with the `200` status [Full history](https://skmtc.dev/openrouterteam/apis/openrouter-api/changes/endpoints/zdr/get.md) --- [API](https://skmtc.dev/openrouterteam/apis/openrouter-api.md) · [All operations](https://skmtc.dev/openrouterteam/apis/openrouter-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/openrouterteam/openrouter-api/revisions/75ebcbc69785/schema)