@agentjido/llmdb 2026.8.2

package/dist/providers/digitalocean.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://inference.do-ai.run/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","env":["DIGITALOCEAN_ACCESS_TOKEN"],"exclude_models":null,"extra":null,"id":"digitalocean","models":{"alibaba-qwen3-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":0.55},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"alibaba-qwen3-32b","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":32768,"output":6554},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-04-30","retired":false,"tags":null},"all-mini-lm-l6-v2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.009,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"temperature":false},"family":null,"id":"all-mini-lm-l6-v2","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":256,"output":384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"All-MiniLM-L6-v2","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2021-08-30","retired":false,"tags":null},"anthropic-claude-3-opus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Legacy model retained for compatibility with older integrations","family":"claude-opus","open_weights":false,"status":"deprecated","temperature":true},"family":null,"id":"anthropic-claude-3-opus","knowledge":"2023-08","last_updated":"2024-02-29","lifecycle":null,"limits":{"context":200000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude 3 Opus","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-02-29","retired":false,"tags":null},"anthropic-claude-3.5-haiku":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.08,"cache_write":1,"input":0.8,"output":4},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","family":"claude-haiku","open_weights":false,"status":"deprecated","temperature":true},"family":null,"id":"anthropic-claude-3.5-haiku","knowledge":"2024-07","last_updated":"2024-11-05","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Claude 3.5 Haiku","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-11-05","retired":false,"tags":null},"anthropic-claude-3.5-sonnet":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Legacy model retained for compatibility with older integrations","family":"claude-sonnet","open_weights":false,"status":"deprecated","temperature":true},"family":null,"id":"anthropic-claude-3.5-sonnet","knowledge":"2024-04","last_updated":"2024-10-22","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude 3.5 Sonnet","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-06-20","retired":false,"tags":null},"anthropic-claude-3.7-sonnet":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Legacy model retained for compatibility with older integrations","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"deprecated","temperature":true},"family":null,"id":"anthropic-claude-3.7-sonnet","knowledge":"2024-11","last_updated":"2025-02-24","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude 3.7 Sonnet","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-02-24","retired":false,"tags":null},"anthropic-claude-4.1-opus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic-claude-4.1-opus","knowledge":"2025-03-31","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic Claude 4.1 Opus","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"anthropic-claude-4.5-haiku":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic-claude-4.5-haiku","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Haiku 4.5","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"anthropic-claude-4.5-sonnet":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic-claude-4.5-sonnet","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic Claude 4.5 Sonnet","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"anthropic-claude-4.6-sonnet":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"temperature":true},"family":null,"id":"anthropic-claude-4.6-sonnet","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic Claude Sonnet 4.6","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"anthropic-claude-5-sonnet":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":false},"family":null,"id":"anthropic-claude-5-sonnet","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Anthropic Claude Sonnet 5","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"anthropic-claude-fable-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"anthropic-claude-fable-5","knowledge":null,"last_updated":"2026-06-12","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic Claude Fable 5","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"anthropic-claude-haiku-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic-claude-haiku-4.5","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic Claude Haiku 4.5","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"anthropic-claude-opus-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic-claude-opus-4","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic-claude-opus-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"temperature":true},"family":null,"id":"anthropic-claude-opus-4.5","knowledge":"2025-03-31","last_updated":"2025-11-24","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic Claude Opus 4.5","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"anthropic-claude-opus-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"temperature":true},"family":null,"id":"anthropic-claude-opus-4.6","knowledge":"2025-05-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic Claude Opus 4.6","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"anthropic-claude-opus-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"temperature":false},"family":null,"id":"anthropic-claude-opus-4.7","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic Claude Opus 4.7","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"anthropic-claude-opus-4.8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"temperature":true},"family":null,"id":"anthropic-claude-opus-4.8","knowledge":null,"last_updated":"2026-05-29","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic Claude Opus 4.8","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"anthropic-claude-opus-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"anthropic-claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic Claude Opus 5","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"anthropic-claude-sonnet-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic-claude-sonnet-4","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"arcee-trinity-large-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.25,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"trinity","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"arcee-trinity-large-thinking","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":128000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Arcee Trinity Large Thinking (Public Preview)","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"bge-m3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.02,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"bge","open_weights":true,"temperature":false},"family":null,"id":"bge-m3","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":8192,"output":1024},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"BGE M3","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-01-30","retired":false,"tags":null},"bge-reranker-v2-m3":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.01,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"bge","open_weights":true,"temperature":false},"family":null,"id":"bge-reranker-v2-m3","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":8192,"output":1},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"BGE Reranker v2 M3","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-03-12","retired":false,"tags":null},"deepseek-3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.25,"output":0.8},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"temperature":true},"family":null,"id":"deepseek-3.2","knowledge":"2024-12","last_updated":"2026-04-30","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek 3.2","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"deepseek-4-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0168,"input":0.084,"output":0.168},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek","open_weights":false,"temperature":true},"family":null,"id":"deepseek-4-flash","knowledge":null,"last_updated":"2026-05-29","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V4 Flash","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-05-27","retired":false,"tags":null},"deepseek-r1-distill-llama-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.99,"output":0.99},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-r1-distill-llama-70b","knowledge":null,"last_updated":"2025-01-30","lifecycle":null,"limits":{"context":32678,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 Distill Llama 70B","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-01-30","retired":false,"tags":null},"deepseek-v3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"temperature":true},"family":null,"id":"deepseek-v3","knowledge":"2024-07","last_updated":"2025-03-24","lifecycle":null,"limits":{"context":163840,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-12-26","retired":false,"tags":null},"deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.174,"input":0.87,"output":1.74},"deprecated":false,"extra":{"attachment":false,"description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":262144,"output":52429},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V4 Pro","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"e5-large-v2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.02,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"temperature":false},"family":null,"id":"e5-large-v2","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":512,"output":1024},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"E5 Large v2","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2023-05-19","retired":false,"tags":null},"fal-ai/elevenlabs/tts/multilingual-v2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"elevenlabs","open_weights":false,"temperature":false},"family":null,"id":"fal-ai/elevenlabs/tts/multilingual-v2","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"ElevenLabs Multilingual TTS v2","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2023-08-22","retired":false,"tags":null},"fal-ai/fast-sdxl":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"stable-diffusion","open_weights":true,"temperature":false},"family":null,"id":"fal-ai/fast-sdxl","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Fast SDXL","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2023-07-26","retired":false,"tags":null},"fal-ai/flux/schnell":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":true,"temperature":false},"family":null,"id":"fal-ai/flux/schnell","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"FLUX.1 [schnell]","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-08-01","retired":false,"tags":null},"fal-ai/stable-audio-25/text-to-audio":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","open_weights":false,"temperature":false},"family":null,"id":"fal-ai/stable-audio-25/text-to-audio","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Stable Audio 2.5 (Text-to-Audio)","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-10-08","retired":false,"tags":null},"gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.036,"input":0.18,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"gemma-4-31B-it","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Gemma 4","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"glm-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":0.75,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"temperature":true},"family":null,"id":"glm-5","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":64000,"output":12800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-02-11","retired":false,"tags":null},"glm-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":0.975,"output":4.3},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"glm-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.7,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":262144,"output":52429},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"gte-large-en-v1.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.09,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"temperature":false},"family":null,"id":"gte-large-en-v1.5","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":8192,"output":1024},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GTE Large (v1.5)","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-03-27","retired":false,"tags":null},"kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.203,"input":0.375,"output":2.025},"deprecated":false,"extra":{"attachment":true,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2.5","knowledge":"2025-01","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":262144,"output":52429},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"kimi-k2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19,"input":0.76,"output":3.2},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":52429},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"kimi-k3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"llama-4-maverick":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.696},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"llama-4-maverick","knowledge":"2024-08","last_updated":"2026-04-30","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Maverick","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"llama3-8b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.198,"output":0.198},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama3-8b-instruct","knowledge":"2023-12","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 Instruct (8B)","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"llama3.3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.65,"output":0.65},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama3.3-70b-instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 Instruct (70B)","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"mimo-v2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.8,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"temperature":true},"family":null,"id":"mimo-v2.5-pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":52429},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo V2.5 Pro","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"minimax-m2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.225,"output":0.9},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax-m2.5","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"minimax-m2.5","knowledge":"2025-08","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":65536,"output":13107},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MiniMax M2.5 (Public Preview)","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"ministral-3-8b-instruct-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"temperature":true},"family":null,"id":"ministral-3-8b-instruct-2512","knowledge":null,"last_updated":"2025-12-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 3 8B","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"mistral-3-14B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistral-3-14B","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":262144,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ministral 3 14B","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"mistral-7b-instruct-v0.3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","open_weights":true,"temperature":true},"family":null,"id":"mistral-7b-instruct-v0.3","knowledge":null,"last_updated":"2024-05-22","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral 7B Instruct v0.3","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-05-22","retired":false,"tags":null},"mistral-nemo-instruct-2407":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","family":"mistral","open_weights":true,"status":"deprecated","temperature":true},"family":null,"id":"mistral-nemo-instruct-2407","knowledge":null,"last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Nemo Instruct","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"multi-qa-mpnet-base-dot-v1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.009,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"temperature":false},"family":null,"id":"multi-qa-mpnet-base-dot-v1","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":512,"output":768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Multi-QA-mpnet-base-dot-v1","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2021-08-30","retired":false,"tags":null},"nemotron-3-nano-30b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"temperature":true},"family":null,"id":"nemotron-3-nano-30b","knowledge":null,"last_updated":"2025-04-14","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B A3B","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"nemotron-3-nano-omni":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.5,"output":0.9},"deprecated":false,"extra":{"attachment":true,"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"nemotron-3-nano-omni","knowledge":null,"last_updated":"2026-04-28","lifecycle":null,"limits":{"context":65536,"output":13107},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano Omni","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-04-28","retired":false,"tags":null},"nemotron-3-ultra-550b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.9,"output":1.7},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","open_weights":false,"temperature":true},"family":null,"id":"nemotron-3-ultra-550b","knowledge":null,"last_updated":"2026-06-12","lifecycle":null,"limits":{"context":131072,"output":26214},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Ultra","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"nemotron-nano-12b-v2-vl":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"temperature":true},"family":null,"id":"nemotron-nano-12b-v2-vl","knowledge":null,"last_updated":"2025-10-28","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Nemotron-nano 12b v2-vl","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-10-28","retired":false,"tags":null},"nvidia-nemotron-3-super-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.165,"output":0.3575},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia-nemotron-3-super-120b","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA Nemotron 3 Super 120B  (Public Preview)","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"openai-gpt-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai-gpt-4.1","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-4.1","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai-gpt-4o":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai-gpt-4o","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-4o","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"openai-gpt-4o-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai-gpt-4o-mini","knowledge":"2023-09","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-4o mini","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"openai-gpt-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5","knowledge":"2024-09-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai-gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5-mini","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5 Mini","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai-gpt-5-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.005,"input":0.05,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5-nano","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5 Nano","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai-gpt-5.1-codex-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5.1-codex-max","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex Max","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai-gpt-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5.2","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5.2","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai-gpt-5.2-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":21,"output":168},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":false},"family":null,"id":"openai-gpt-5.2-pro","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5.2 Pro","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai-gpt-5.3-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5.3-codex","knowledge":"2025-08-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5.3 Codex","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"openai-gpt-5.4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5.4","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5.4","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai-gpt-5.4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5.4 Mini","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai-gpt-5.4-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.2,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5.4 Nano","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai-gpt-5.4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"temperature":false},"family":null,"id":"openai-gpt-5.4-pro","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5.4 Pro","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai-gpt-5.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5.5","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai-gpt-5.6-luna":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.2,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5.6-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5.6 Luna","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-5.6-sol":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5.6-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5.6 Sol","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-5.6-terra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-5.6-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5.6 Terra","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-image-1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":1.25,"input":5,"output":40},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","open_weights":false,"temperature":false},"family":null,"id":"openai-gpt-image-1","knowledge":null,"last_updated":"2025-04-24","lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"GPT Image 1","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-04-24","retired":false,"tags":null},"openai-gpt-image-1.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":1,"input":5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","open_weights":false,"temperature":false},"family":null,"id":"openai-gpt-image-1.5","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"output":16384},"modalities":{"input":["text","image"],"output":["image","text"]},"model":null,"name":"OpenAI GPT Image 1.5","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-11-25","retired":false,"tags":null},"openai-gpt-image-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":8,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","open_weights":false,"temperature":false},"family":null,"id":"openai-gpt-image-2","knowledge":null,"last_updated":"2025-04-24","lifecycle":null,"limits":{"output":16384},"modalities":{"input":["text","image"],"output":["image","text"]},"model":null,"name":"OpenAI GPT Image 2","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-04-24","retired":false,"tags":null},"openai-gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.055,"output":0.385},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai-gpt-oss-120b","knowledge":"2024-06","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI GPT-oss-120b","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai-gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.05,"output":0.45},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai-gpt-oss-20b","knowledge":"2024-06","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI GPT-oss-20b","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai-o1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":7.5,"input":15,"output":60},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-o1","knowledge":"2023-09","last_updated":"2024-12-05","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI o1","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"openai-o3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-o3","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI o3","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai-o3-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-o3-mini","knowledge":"2024-05","last_updated":"2025-01-29","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI o3 mini","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-12-20","retired":false,"tags":null},"qwen-2.5-14b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen-2.5-14b-instruct","knowledge":"2024-09","last_updated":"2024-09-19","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 2.5 14B Instruct","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-09-19","retired":false,"tags":null},"qwen3-coder-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.09,"input":0.45,"output":1.7},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen3-coder-flash","knowledge":"2025-04","last_updated":"2026-04-30","lifecycle":null,"limits":{"context":262144,"output":52429},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Flash","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"qwen3-embedding-0.6b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.04,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"status":"beta","temperature":false},"family":null,"id":"qwen3-embedding-0.6b","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":8000,"output":1024},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Embedding 0.6B","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-06-03","retired":false,"tags":null},"qwen3-tts-voicedesign":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"qwen","open_weights":true,"temperature":false},"family":null,"id":"qwen3-tts-voicedesign","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":32768,"output":1},"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Qwen3 TTS VoiceDesign","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"qwen3.5-397b-a17b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.111,"input":0.3025,"output":1.925},"deprecated":false,"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen3.5","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.5-397b-a17b","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":131072,"output":26214},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.5 397B A17B","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"stable-diffusion-3.5-large":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.08,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"stable-diffusion","open_weights":true,"temperature":false},"family":null,"id":"stable-diffusion-3.5-large","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":256,"output":1},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Stable Diffusion 3.5 Large","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2024-10-22","retired":false,"tags":null},"wan2-2-t2v-a14b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.6,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","open_weights":true,"temperature":false},"family":null,"id":"wan2-2-t2v-a14b","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":100,"output":1},"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Wan2.2-T2V-A14B","pricing":null,"provider":"digitalocean","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null}},"name":"DigitalOcean","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/dinference.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "dinference",
+  "glm-4.7" | "glm-5" | "glm-5.1" | "glm-5.2" | "gpt-oss-120b" | "minimax-m2.5"
+>;
+export default provider;

package/dist/providers/dinference.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.dinference.com/v1","catalog_only":true,"config_schema":null,"doc":"https://dinference.com","env":["DINFERENCE_API_KEY"],"exclude_models":null,"extra":null,"id":"dinference","models":{"glm-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.45,"output":1.65},"deprecated":false,"extra":{"attachment":false,"description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"glm-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"dinference","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"glm-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.75,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"glm-5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"dinference","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"glm-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.25,"output":3.89},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"dinference","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"glm-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.25,"output":3.89},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"dinference","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.0675,"output":0.27},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","open_weights":true,"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":null,"last_updated":"2025-08","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"dinference","provider_model_id":null,"release_date":"2025-08","retired":false,"tags":null},"minimax-m2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.22,"output":0.88},"deprecated":false,"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax-m2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"dinference","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null}},"name":"DInference","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/drun.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "drun",
+  "public/deepseek-r1" | "public/deepseek-v3" | "public/minimax-m25"
+>;
+export default provider;

package/dist/providers/drun.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://chat.d.run/v1","catalog_only":true,"config_schema":null,"doc":"https://www.d.run","env":["DRUN_API_KEY"],"exclude_models":null,"extra":null,"id":"drun","models":{"public/deepseek-r1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.55,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"public/deepseek-r1","knowledge":"2024-12","last_updated":"2025-01-20","lifecycle":null,"limits":{"context":131072,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1","pricing":null,"provider":"drun","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"public/deepseek-v3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.28,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"temperature":true},"family":null,"id":"public/deepseek-v3","knowledge":"2024-07","last_updated":"2024-12-26","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3","pricing":null,"provider":"drun","provider_model_id":null,"release_date":"2024-12-26","retired":false,"tags":null},"public/minimax-m25":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.29,"output":1.16},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","interleaved":{"field":"reasoning_details"},"open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"public/minimax-m25","knowledge":null,"last_updated":"2025-03-01","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5","pricing":null,"provider":"drun","provider_model_id":null,"release_date":"2025-03-01","retired":false,"tags":null}},"name":"D.Run (China)","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/ebcloud.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "ebcloud",
+  "DeepSeek-V4-Flash" | "DeepSeek-V4-Pro" | "GLM-5.1" | "Kimi-K2.6"
+>;
+export default provider;

package/dist/providers/ebcloud.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://maas-api.ebcloud.com/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.ebtech.com/ai/model-api.html","env":["EBCLOUD_API_KEY"],"exclude_models":null,"extra":null,"id":"ebcloud","models":{"DeepSeek-V4-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.143,"output":0.2857},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"DeepSeek-V4-Flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"ebcloud","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"DeepSeek-V4-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4286,"output":0.8571},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"DeepSeek-V4-Pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"ebcloud","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"GLM-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.8571,"output":3.4286},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"GLM-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"ebcloud","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.9286,"output":3.8571},"deprecated":false,"extra":{"attachment":false,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"ebcloud","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null}},"name":"EBCloud","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/elevenlabs.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "elevenlabs",
+  "eleven_flash_v2_5" | "eleven_multilingual_v2" | "eleven_turbo_v2_5" | "eleven_v3"
+>;
+export default provider;

package/dist/providers/elevenlabs.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.elevenlabs.io","config_schema":null,"doc":"https://elevenlabs.io/docs/api-reference/introduction","env":["ELEVENLABS_API_KEY"],"exclude_models":null,"extra":null,"id":"elevenlabs","models":{"eleven_flash_v2_5":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":false},"tools":{"enabled":false}},"cost":null,"deprecated":false,"execution":{"speech":{"family":"elevenlabs_speech","path":"/v1/text-to-speech/{provider_model_id}","supported":true,"wire_protocol":"elevenlabs_speech"}},"extra":{"api":"tts","character_limit":40000,"description":"Ultra-fast model optimized for real-time use (~75ms)","languages_supported":32},"family":"eleven_flash","id":"eleven_flash_v2_5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Eleven Flash v2.5","pricing":null,"provider":"elevenlabs","provider_model_id":null,"release_date":null,"retired":false,"tags":["tts","speech"]},"eleven_multilingual_v2":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":false},"tools":{"enabled":false}},"cost":null,"deprecated":false,"execution":{"speech":{"family":"elevenlabs_speech","path":"/v1/text-to-speech/{provider_model_id}","supported":true,"wire_protocol":"elevenlabs_speech"}},"extra":{"api":"tts","character_limit":10000,"description":"Our most lifelike model with rich emotional expression","languages_supported":29},"family":"eleven_multilingual","id":"eleven_multilingual_v2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Eleven Multilingual v2","pricing":null,"provider":"elevenlabs","provider_model_id":null,"release_date":null,"retired":false,"tags":["tts","speech"]},"eleven_turbo_v2_5":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":false},"tools":{"enabled":false}},"cost":null,"deprecated":false,"execution":{"speech":{"family":"elevenlabs_speech","path":"/v1/text-to-speech/{provider_model_id}","supported":true,"wire_protocol":"elevenlabs_speech"}},"extra":{"api":"tts","character_limit":40000,"description":"High quality, low-latency model with a good balance of quality and speed (~250ms-300ms)","languages_supported":32},"family":"eleven_turbo","id":"eleven_turbo_v2_5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Eleven Turbo v2.5","pricing":null,"provider":"elevenlabs","provider_model_id":null,"release_date":null,"retired":false,"tags":["tts","speech"]},"eleven_v3":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":false},"tools":{"enabled":false}},"cost":null,"deprecated":false,"execution":{"speech":{"family":"elevenlabs_speech","path":"/v1/text-to-speech/{provider_model_id}","supported":true,"wire_protocol":"elevenlabs_speech"}},"extra":{"api":"tts","character_limit":5000,"description":"Human-like and expressive speech generation","languages_supported":70},"family":"eleven_v3","id":"eleven_v3","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Eleven v3","pricing":null,"provider":"elevenlabs","provider_model_id":null,"release_date":null,"retired":false,"tags":["tts","speech"]}},"name":"ElevenLabs","pricing_defaults":null,"runtime":{"auth":{"env":["ELEVENLABS_API_KEY"],"header_name":"xi-api-key","headers":[],"type":"header"},"base_url":"https://api.elevenlabs.io","config_schema":null,"default_headers":{},"default_query":{},"doc_url":"https://elevenlabs.io/docs/api-reference/introduction"}};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/empiriolabs.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "empiriolabs",
+  "deepseek-v4-flash" | "deepseek-v4-flash-0731" | "deepseek-v4-pro" | "gemma-4-26b-a4b" | "glm-4-5-flash" | "glm-4-7-flash" | "glm-5-1" | "glm-5-2" | "kimi-k2-6" | "kimi-k2-7-code" | "kimi-k2-7-code-highspeed" | "kimi-k3" | "mimo-v2-5" | "mimo-v2-5-pro" | "minimax-m2-7" | "minimax-m2-7-highspeed" | "minimax-m3" | "mistral-medium-3" | "mistral-small-4" | "muse-spark-1-1" | "qwen3-5-122b-a10b" | "qwen3-5-27b" | "qwen3-5-35b-a3b" | "qwen3-5-397b-a17b" | "qwen3-5-4b" | "qwen3-5-9b" | "qwen3-5-plus" | "qwen3-6-27b" | "qwen3-6-35b-a3b" | "qwen3-6-flash" | "qwen3-6-max-preview" | "qwen3-6-plus" | "qwen3-7-flash" | "qwen3-7-max" | "qwen3-7-plus" | "qwen3-8-max" | "qwen3-max" | "step-3-5-flash" | "step-3-5-flash-2603" | "step-3-7-flash"
+>;
+export default provider;