@agentjido/llmdb 2026.8.2

package/dist/providers/neuralwatt.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.neuralwatt.com/v1","catalog_only":true,"config_schema":null,"doc":"https://portal.neuralwatt.com/docs","env":["NEURALWATT_API_KEY"],"exclude_models":null,"extra":null,"id":"neuralwatt","models":{"Qwen/Qwen3.5-397B-A17B-FP8":{"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":0.1725,"input":0.69,"output":4.14},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-397B-A17B-FP8-GGUF"}],"hf_downloads":832304,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3.5-397B-A17B-FP8","memory":{"min_ram_gb":225.4,"min_vram_gb":206.6,"recommended_ram_gb":375.7},"model_id":"Qwen/Qwen3.5-397B-A17B-FP8","moe":{"active_experts":10,"active_parameters":27656495656,"is_moe":true,"num_experts":512},"parameter_count":"403.4B","parameters_raw":403422386928,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B-FP8","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":262128,"output":262128},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 397B A17B FP8","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"Qwen/Qwen3.6-35B-A3B":{"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":0.0725,"input":0.29,"output":1.15},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-35B-A3B-GGUF"}],"hf_downloads":5928967,"hf_likes":2614,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-15","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"Qwen/Qwen3.6-35B-A3B","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":131056,"output":131056},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"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":{"cache_read":0.026,"input":0.104,"output":0.207},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048560,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"gemma-4-31b":{"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":0.036,"input":0.144,"output":0.42},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"gemma-4-31b","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262128,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-04-02","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":0.3625,"input":1.45,"output":4.5},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"temperature":true},"family":null,"id":"glm-5.2","knowledge":null,"last_updated":"2026-06-17","lifecycle":null,"limits":{"context":1048560,"output":1048560},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-06-17","retired":false,"tags":null},"glm-5.2-fast":{"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":0.3625,"input":1.45,"output":4.5},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","open_weights":true,"temperature":true},"family":null,"id":"glm-5.2-fast","knowledge":null,"last_updated":"2026-06-17","lifecycle":null,"limits":{"context":1048560,"output":1048560},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 Fast","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-06-17","retired":false,"tags":null},"glm-5.2-flex":{"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":0.18125,"input":0.725,"output":2.25},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"temperature":true},"family":null,"id":"glm-5.2-flex","knowledge":null,"last_updated":"2026-06-17","lifecycle":null,"limits":{"context":1048560,"output":1048560},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 Flex","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-06-17","retired":false,"tags":null},"glm-5.2-short":{"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":0.3625,"input":1.45,"output":4.5},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"temperature":true},"family":null,"id":"glm-5.2-short","knowledge":null,"last_updated":"2026-06-17","lifecycle":null,"limits":{"context":199984,"output":199984},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 Short","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-06-17","retired":false,"tags":null},"glm-5.2-short-fast":{"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":0.3625,"input":1.45,"output":4.5},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","open_weights":true,"temperature":true},"family":null,"id":"glm-5.2-short-fast","knowledge":null,"last_updated":"2026-06-17","lifecycle":null,"limits":{"context":199984,"output":199984},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 Short Fast","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-06-17","retired":false,"tags":null},"glm-5.2-short-fast-flex":{"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":0.18125,"input":0.725,"output":2.25},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","open_weights":true,"temperature":true},"family":null,"id":"glm-5.2-short-fast-flex","knowledge":null,"last_updated":"2026-06-17","lifecycle":null,"limits":{"context":199984,"output":199984},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 Short Fast Flex","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-06-17","retired":false,"tags":null},"glm-5.2-short-flex":{"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":0.18125,"input":0.725,"output":2.25},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"temperature":true},"family":null,"id":"glm-5.2-short-flex","knowledge":null,"last_updated":"2026-06-17","lifecycle":null,"limits":{"context":199984,"output":199984},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 Short Flex","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-06-17","retired":false,"tags":null},"kimi-k2.5-fast":{"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":0.13,"input":0.52,"output":2.59},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","open_weights":true,"temperature":true},"family":null,"id":"kimi-k2.5-fast","knowledge":null,"last_updated":"2026-01-27","lifecycle":null,"limits":{"context":262128,"output":262128},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5 Fast","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"kimi-k2.6-fast":{"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":0.1725,"input":0.69,"output":3.22},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","open_weights":true,"temperature":true},"family":null,"id":"kimi-k2.6-fast","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262128,"output":262128},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6 Fast","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"kimi-k2.6-flex":{"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":0.08625,"input":0.345,"output":1.61},"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":"toggle"}],"temperature":true},"family":null,"id":"kimi-k2.6-flex","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262128,"output":262128},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6 Flex","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"kimi-k2.7-code-flex":{"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":0.11875,"input":0.475,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2.7-code-flex","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code Flex","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-06-12","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":"toggle"}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048560,"output":1048560},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"moonshotai/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":0.13,"input":0.52,"output":2.59},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2.5-GGUF"}],"hf_downloads":967470,"hf_likes":2860,"matched_hugging_face_id":"moonshotai/Kimi-K2.5","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.5","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2026-01-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":null,"last_updated":"2026-01-27","lifecycle":null,"limits":{"context":262128,"output":262128},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"moonshotai/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":0.1725,"input":0.69,"output":3.22},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262128,"output":262128},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.7-Code":{"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":0.2375,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":695030,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K2.7-Code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"qwen3.5-397b-fast":{"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":0.1725,"input":0.69,"output":4.14},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen3.5-397b-fast","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":262128,"output":262128},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 397B Fast","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"qwen3.6-35b-fast":{"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":0.0725,"input":0.29,"output":1.15},"deprecated":false,"extra":{"attachment":true,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"qwen3.6","open_weights":true,"temperature":true},"family":null,"id":"qwen3.6-35b-fast","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":131056,"output":131056},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 35B Fast","pricing":null,"provider":"neuralwatt","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null}},"name":"Neuralwatt","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/nova.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "nova",
+  "nova-2-lite-v1" | "nova-2-pro-v1"
+>;
+export default provider;

package/dist/providers/nova.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.nova.amazon.com/v1","catalog_only":true,"config_schema":null,"doc":"https://nova.amazon.com/dev/documentation","env":["NOVA_API_KEY"],"exclude_models":null,"extra":null,"id":"nova","models":{"nova-2-lite-v1":{"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,"output":0,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova-lite","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"nova-2-lite-v1","knowledge":null,"last_updated":"2025-12-01","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"model":null,"name":"Nova 2 Lite","pricing":null,"provider":"nova","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"nova-2-pro-v1":{"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,"output":0,"reasoning":0},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova-pro","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"nova-2-pro-v1","knowledge":null,"last_updated":"2026-01-03","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"model":null,"name":"Nova 2 Pro","pricing":null,"provider":"nova","provider_model_id":null,"release_date":"2025-12-03","retired":false,"tags":null}},"name":"Nova","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/novita_ai.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "novita_ai",
+  "baai/bge-m3" | "baichuan/baichuan-m2-32b" | "baidu/ernie-4.5-21B-a3b" | "baidu/ernie-4.5-21B-a3b-thinking" | "baidu/ernie-4.5-300b-a47b-paddle" | "baidu/ernie-4.5-vl-28b-a3b" | "baidu/ernie-4.5-vl-28b-a3b-thinking" | "baidu/ernie-4.5-vl-424b-a47b" | "deepseek/deepseek-ocr" | "deepseek/deepseek-ocr-2" | "deepseek/deepseek-prover-v2-671b" | "deepseek/deepseek-r1-0528" | "deepseek/deepseek-r1-0528-qwen3-8b" | "deepseek/deepseek-r1-distill-llama-70b" | "deepseek/deepseek-r1-distill-qwen-14b" | "deepseek/deepseek-r1-distill-qwen-32b" | "deepseek/deepseek-r1-turbo" | "deepseek/deepseek-v3-0324" | "deepseek/deepseek-v3-turbo" | "deepseek/deepseek-v3.1" | "deepseek/deepseek-v3.1-terminus" | "deepseek/deepseek-v3.2" | "deepseek/deepseek-v3.2-exp" | "deepseek/deepseek-v4-flash" | "deepseek/deepseek-v4-pro" | "google/gemma-3-12b-it" | "google/gemma-3-27b-it" | "google/gemma-4-26b-a4b-it" | "google/gemma-4-31b-it" | "gryphe/mythomax-l2-13b" | "inclusionai/ling-2.6-1t" | "inclusionai/ling-2.6-flash" | "inclusionai/ring-2.6-1t" | "kwaipilot/kat-coder-pro" | "meta-llama/llama-3-70b-instruct" | "meta-llama/llama-3-8b-instruct" | "meta-llama/llama-3.1-8b-instruct" | "meta-llama/llama-3.2-3b-instruct" | "meta-llama/llama-3.3-70b-instruct" | "meta-llama/llama-4-maverick-17b-128e-instruct-fp8" | "meta-llama/llama-4-scout-17b-16e-instruct" | "microsoft/wizardlm-2-8x22b" | "minimax/minimax-m2" | "minimax/minimax-m2.1" | "minimax/minimax-m2.5" | "minimax/minimax-m2.5-highspeed" | "minimax/minimax-m2.7" | "minimax/minimax-m2.7-highspeed" | "minimaxai/minimax-m1-80k" | "mistralai/mistral-nemo" | "moonshotai/kimi-k2-0905" | "moonshotai/kimi-k2-instruct" | "moonshotai/kimi-k2-thinking" | "moonshotai/kimi-k2.5" | "moonshotai/kimi-k2.6" | "moonshotai/kimi-k2.7-code" | "moonshotai/kimi-k3" | "nousresearch/hermes-2-pro-llama-3-8b" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "paddlepaddle/paddleocr-vl" | "qwen/qwen-2.5-72b-instruct" | "qwen/qwen-mt-plus" | "qwen/qwen2.5-7b-instruct" | "qwen/qwen2.5-vl-72b-instruct" | "qwen/qwen3-235b-a22b-fp8" | "qwen/qwen3-235b-a22b-instruct-2507" | "qwen/qwen3-235b-a22b-thinking-2507" | "qwen/qwen3-30b-a3b-fp8" | "qwen/qwen3-32b-fp8" | "qwen/qwen3-4b-fp8" | "qwen/qwen3-8b-fp8" | "qwen/qwen3-coder-30b-a3b-instruct" | "qwen/qwen3-coder-480b-a35b-instruct" | "qwen/qwen3-coder-next" | "qwen/qwen3-embedding-0.6b" | "qwen/qwen3-embedding-8b" | "qwen/qwen3-max" | "qwen/qwen3-next-80b-a3b-instruct" | "qwen/qwen3-next-80b-a3b-thinking" | "qwen/qwen3-omni-30b-a3b-instruct" | "qwen/qwen3-omni-30b-a3b-thinking" | "qwen/qwen3-vl-235b-a22b-instruct" | "qwen/qwen3-vl-235b-a22b-thinking" | "qwen/qwen3-vl-30b-a3b-instruct" | "qwen/qwen3-vl-30b-a3b-thinking" | "qwen/qwen3-vl-8b-instruct" | "qwen/qwen3.5-122b-a10b" | "qwen/qwen3.5-27b" | "qwen/qwen3.5-35b-a3b" | "qwen/qwen3.5-397b-a17b" | "qwen/qwen3.7-max" | "sao10K/L3-8B-stheno-v3.2" | "sao10K/l3-70b-euryale-v2.1" | "sao10K/l3-8b-lunaris" | "sao10K/l31-70b-euryale-v2.2" | "xiaomimimo/mimo-v2-flash" | "xiaomimimo/mimo-v2-pro" | "xiaomimimo/mimo-v2.5-pro" | "zai-org/autoglm-phone-9b-multilingual" | "zai-org/glm-4.5" | "zai-org/glm-4.5-air" | "zai-org/glm-4.5v" | "zai-org/glm-4.6" | "zai-org/glm-4.6v" | "zai-org/glm-4.7" | "zai-org/glm-4.7-flash" | "zai-org/glm-5" | "zai-org/glm-5.1" | "zai-org/glm-5.2"
+>;
+export default provider;

package/dist/providers/novita_ai.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.novita.ai/openai","catalog_only":true,"config_schema":null,"doc":"https://novita.ai/docs/guides/introduction","env":["NOVITA_API_KEY"],"exclude_models":null,"extra":null,"id":"novita_ai","models":{"baai/bge-m3":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":{"min_dimensions":1},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"type":"embedding"},"family":null,"id":"baai/bge-m3","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["embedding"]},"model":null,"name":"BGE M3","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"baichuan/baichuan-m2-32b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.07,"output":0.07},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"baichuan","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"baichuan/baichuan-m2-32b","knowledge":"2024-12","last_updated":"2025-08-13","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"baichuan-m2-32b","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-08-13","retired":false,"tags":null},"baidu/ernie-4.5-21B-a3b":{"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":0.07,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"ernie","open_weights":true,"temperature":true},"family":null,"id":"baidu/ernie-4.5-21B-a3b","knowledge":"2025-03","last_updated":"2025-06-30","lifecycle":null,"limits":{"context":120000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"ERNIE 4.5 21B A3B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-06-30","retired":false,"tags":null},"baidu/ernie-4.5-21B-a3b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.07,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ernie","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"baidu/ernie-4.5-21B-a3b-thinking","knowledge":"2025-03","last_updated":"2025-09-19","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"ERNIE-4.5-21B-A3B-Thinking","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-19","retired":false,"tags":null},"baidu/ernie-4.5-300b-a47b-paddle":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.28,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"baidu/ernie-4.5-300b-a47b-paddle","knowledge":null,"last_updated":"2025-06-30","lifecycle":null,"limits":{"context":123000,"output":12000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"ERNIE 4.5 300B A47B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-06-30","retired":false,"tags":null},"baidu/ernie-4.5-vl-28b-a3b":{"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":0.14,"output":0.56},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"baidu/ernie-4.5-vl-28b-a3b","knowledge":null,"last_updated":"2026-06-14","lifecycle":null,"limits":{"context":30000,"output":8000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"ERNIE 4.5 VL 28B A3B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-06-30","retired":false,"tags":null},"baidu/ernie-4.5-vl-28b-a3b-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":{"input":0.39,"output":0.39},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"baidu/ernie-4.5-vl-28b-a3b-thinking","knowledge":null,"last_updated":"2025-11-26","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"ERNIE-4.5-VL-28B-A3B-Thinking","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-11-26","retired":false,"tags":null},"baidu/ernie-4.5-vl-424b-a47b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.42,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"baidu/ernie-4.5-vl-424b-a47b","knowledge":null,"last_updated":"2025-06-30","lifecycle":null,"limits":{"context":123000,"output":16000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"ERNIE 4.5 VL 424B A47B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-06-30","retired":false,"tags":null},"deepseek/deepseek-ocr":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.03,"output":0.03},"deprecated":false,"extra":{"attachment":true,"description":"OCR model for extracting structured text from documents and screenshots","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-ocr","knowledge":null,"last_updated":"2025-10-24","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"DeepSeek-OCR","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-10-24","retired":false,"tags":null},"deepseek/deepseek-ocr-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.03,"output":0.03},"deprecated":false,"extra":{"attachment":true,"description":"OCR model for extracting structured text from documents and screenshots","open_weights":true},"family":null,"id":"deepseek/deepseek-ocr-2","knowledge":null,"last_updated":"2026-01-27","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"deepseek/deepseek-ocr-2","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"deepseek/deepseek-prover-v2-671b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.7,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Flagship DeepSeek model for coding, reasoning, and agentic work","open_weights":true,"temperature":true},"family":null,"id":"deepseek/deepseek-prover-v2-671b","knowledge":null,"last_updated":"2025-04-30","lifecycle":null,"limits":{"context":160000,"output":160000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek Prover V2 671B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-04-30","retired":false,"tags":null},"deepseek/deepseek-r1-0528":{"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":0.35,"input":0.7,"output":2.5},"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":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-r1-0528","knowledge":"2024-07","last_updated":"2025-05-28","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 0528","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-05-28","retired":false,"tags":null},"deepseek/deepseek-r1-0528-qwen3-8b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.06,"output":0.09},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek/deepseek-r1-0528-qwen3-8b","knowledge":null,"last_updated":"2025-05-29","lifecycle":null,"limits":{"context":128000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 0528 Qwen3 8B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-05-29","retired":false,"tags":null},"deepseek/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":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.8,"output":0.8},"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":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-r1-distill-llama-70b","knowledge":null,"last_updated":"2025-01-27","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 Distill LLama 70B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-01-27","retired":false,"tags":null},"deepseek/deepseek-r1-distill-qwen-14b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"deepseek-thinking","open_weights":true,"temperature":true},"family":null,"id":"deepseek/deepseek-r1-distill-qwen-14b","knowledge":null,"last_updated":"2025-01-20","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 Distill Qwen 14B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek/deepseek-r1-distill-qwen-32b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.3,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"deepseek-thinking","open_weights":true,"temperature":true},"family":null,"id":"deepseek/deepseek-r1-distill-qwen-32b","knowledge":null,"last_updated":"2025-01-20","lifecycle":null,"limits":{"context":64000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 Distill Qwen 32B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek/deepseek-r1-turbo":{"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":0.7,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek/deepseek-r1-turbo","knowledge":null,"last_updated":"2025-03-05","lifecycle":null,"limits":{"context":64000,"output":16000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 (Turbo)\t","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-03-05","retired":false,"tags":null},"deepseek/deepseek-v3-0324":{"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":0.135,"input":0.27,"output":1.12},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v3-0324","knowledge":"2024-07","last_updated":"2025-03-25","lifecycle":null,"limits":{"context":163840,"output":163840},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3 0324","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-03-25","retired":false,"tags":null},"deepseek/deepseek-v3-turbo":{"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":0.4,"output":1.3},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","open_weights":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v3-turbo","knowledge":null,"last_updated":"2025-03-05","lifecycle":null,"limits":{"context":64000,"output":16000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3 (Turbo)\t","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-03-05","retired":false,"tags":null},"deepseek/deepseek-v3.1":{"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":0.135,"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.1","knowledge":null,"last_updated":"2025-08-21","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-08-21","retired":false,"tags":null},"deepseek/deepseek-v3.1-terminus":{"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":0.135,"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.1-terminus","knowledge":null,"last_updated":"2025-09-22","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V3.1 Terminus","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-22","retired":false,"tags":null},"deepseek/deepseek-v3.2":{"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":0.1345,"input":0.269,"output":0.4},"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":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.2","knowledge":null,"last_updated":"2025-12-01","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V3.2","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek/deepseek-v3.2-exp":{"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":0.27,"output":0.41},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.2-exp","knowledge":null,"last_updated":"2025-09-29","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V3.2 Exp","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"deepseek/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":{"cache_read":0.028,"input":0.14,"output":0.28},"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":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":393216},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek/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":0.135,"input":1.6,"output":3.2},"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":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":393216},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"google/gemma-3-12b-it":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.05,"output":0.1},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma3","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-3-12b-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-3-12b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-3-12b-it-GGUF"}],"hf_downloads":1281955,"hf_likes":797,"matched_hugging_face_id":"google/gemma-3-12b-it","memory":{"min_ram_gb":6.8,"min_vram_gb":6.2,"recommended_ram_gb":11.4},"model_id":"google/gemma-3-12b-it","parameter_count":"12.2B","parameters_raw":12187325040,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2025-03-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"temperature":true},"family":null,"id":"google/gemma-3-12b-it","knowledge":null,"last_updated":"2025-03-13","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 3 12B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"google/gemma-3-27b-it":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.119,"output":0.2},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma3","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-3-27b-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-3-27b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-3-27b-it-GGUF"}],"hf_downloads":847078,"hf_likes":2005,"matched_hugging_face_id":"google/gemma-3-27b-it","memory":{"min_ram_gb":15.3,"min_vram_gb":14.1,"recommended_ram_gb":25.5},"model_id":"google/gemma-3-27b-it","parameter_count":"27.4B","parameters_raw":27432406640,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2025-03-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"temperature":true},"family":null,"id":"google/gemma-3-27b-it","knowledge":null,"last_updated":"2025-03-25","lifecycle":null,"limits":{"context":98304,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 3 27B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-03-25","retired":false,"tags":null},"google/gemma-4-26b-a4b-it":{"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":0.13,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-26b-a4b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-31b-it":{"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":0.14,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"gryphe/mythomax-l2-13b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.09,"output":0.09},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":true,"temperature":true},"family":null,"id":"gryphe/mythomax-l2-13b","knowledge":null,"last_updated":"2024-04-25","lifecycle":null,"limits":{"context":4096,"output":3200},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mythomax L2 13B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-04-25","retired":false,"tags":null},"inclusionai/ling-2.6-1t":{"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":0.06,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"ling","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"inclusionai/ling-2.6-1t","knowledge":null,"last_updated":"2026-06-29","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ling-2.6-1T","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"inclusionai/ling-2.6-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":0.02,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"inclusionai/ling-2.6-flash","knowledge":null,"last_updated":"2026-04-24","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ling-2.6-flash","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"inclusionai/ring-2.6-1t":{"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":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ring","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"inclusionai/ring-2.6-1t","knowledge":null,"last_updated":"2026-05-27","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ring-2.6-1T","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-05-08","retired":false,"tags":null},"kwaipilot/kat-coder-pro":{"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":0.06,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"kwaipilot/kat-coder-pro","knowledge":null,"last_updated":"2026-01-05","lifecycle":null,"limits":{"context":256000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kat Coder Pro","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-01-05","retired":false,"tags":null},"meta-llama/llama-3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.51,"output":0.74},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/llama-3-70b-instruct","knowledge":null,"last_updated":"2024-04-25","lifecycle":null,"limits":{"context":8192,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama3 70B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-04-25","retired":false,"tags":null},"meta-llama/llama-3-8b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.04,"output":0.04},"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":"meta-llama/llama-3-8b-instruct","knowledge":null,"last_updated":"2024-04-25","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3 8B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-04-25","retired":false,"tags":null},"meta-llama/llama-3.1-8b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.02,"output":0.05},"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":"meta-llama/llama-3.1-8b-instruct","knowledge":null,"last_updated":"2024-07-24","lifecycle":null,"limits":{"context":16384,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-07-24","retired":false,"tags":null},"meta-llama/llama-3.2-3b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.03,"output":0.05},"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":"meta-llama/llama-3.2-3b-instruct","knowledge":null,"last_updated":"2024-09-18","lifecycle":null,"limits":{"context":32768,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 3B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-09-18","retired":false,"tags":null},"meta-llama/llama-3.3-70b-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":0.135,"output":0.4},"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":"meta-llama/llama-3.3-70b-instruct","knowledge":"2023-12","last_updated":"2024-12-07","lifecycle":null,"limits":{"context":131072,"output":120000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-12-07","retired":false,"tags":null},"meta-llama/llama-4-maverick-17b-128e-instruct-fp8":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.27,"output":0.85},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for strong reasoning and fast responses","open_weights":true,"temperature":true},"family":null,"id":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","knowledge":null,"last_updated":"2025-04-06","lifecycle":null,"limits":{"context":1048576,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Maverick Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-04-06","retired":false,"tags":null},"meta-llama/llama-4-scout-17b-16e-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.18,"output":0.59},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for long-context analysis and efficient agents","open_weights":true,"temperature":true},"family":null,"id":"meta-llama/llama-4-scout-17b-16e-instruct","knowledge":null,"last_updated":"2025-04-06","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Scout Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-04-06","retired":false,"tags":null},"microsoft/wizardlm-2-8x22b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.62,"output":0.62},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":true,"temperature":true},"family":null,"id":"microsoft/wizardlm-2-8x22b","knowledge":null,"last_updated":"2024-04-24","lifecycle":null,"limits":{"context":65535,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Wizardlm 2 8x22B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-04-24","retired":false,"tags":null},"minimax/minimax-m2":{"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":0.03,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2","knowledge":null,"last_updated":"2025-10-27","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-10-27","retired":false,"tags":null},"minimax/minimax-m2.1":{"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":0.03,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","interleaved":{"field":"reasoning_content"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"minimax/minimax-m2.1","knowledge":null,"last_updated":"2025-12-23","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Minimax M2.1","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"minimax/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":0.03,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"minimax/minimax-m2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131100},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"minimax/minimax-m2.5-highspeed":{"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":0.03,"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax-m2.5","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"minimax/minimax-m2.5-highspeed","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131100},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5 Highspeed","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"minimax/minimax-m2.7":{"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":0.06,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax-m2.7","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"minimax/minimax-m2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.7","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"minimax/minimax-m2.7-highspeed":{"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,"cache_write":0.375,"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"minimax/minimax-m2.7-highspeed","knowledge":null,"last_updated":"2026-05-27","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7-highspeed","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"minimaxai/minimax-m1-80k":{"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":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimaxai/minimax-m1-80k","knowledge":null,"last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1000000,"output":40000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M1","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"mistralai/mistral-nemo":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.04,"output":0.17},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/mistral-nemo","knowledge":null,"last_updated":"2024-07-30","lifecycle":null,"limits":{"context":60288,"output":16000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Nemo","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-07-30","retired":false,"tags":null},"moonshotai/kimi-k2-0905":{"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":0.6,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2-0905","knowledge":"2024-10","last_updated":"2025-09-05","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 0905","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-05","retired":false,"tags":null},"moonshotai/kimi-k2-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":0.57,"output":2.3},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","open_weights":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2-instruct","knowledge":null,"last_updated":"2025-07-11","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-07-11","retired":false,"tags":null},"moonshotai/kimi-k2-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":0.15,"input":0.6,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2-thinking","knowledge":null,"last_updated":"2026-06-29","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Thinking","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-11-07","retired":false,"tags":null},"moonshotai/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":0.1,"input":0.6,"output":3},"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":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01-27","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"moonshotai/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":0.16,"input":0.8,"output":3.4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/kimi-k2.7-code":{"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":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/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","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nousresearch/hermes-2-pro-llama-3-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.14,"output":0.14},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"nousresearch/hermes-2-pro-llama-3-8b","knowledge":null,"last_updated":"2024-06-27","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hermes 2 Pro Llama 3 8B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-06-27","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":{"input":0.05,"output":0.25},"deprecated":false,"extra":{"attachment":true,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-06","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT OSS 120B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-08-06","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":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.04,"output":0.15},"deprecated":false,"extra":{"attachment":true,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-06","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI: GPT OSS 20B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-08-06","retired":false,"tags":null},"paddlepaddle/paddleocr-vl":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.02,"output":0.02},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","open_weights":true,"temperature":true},"family":null,"id":"paddlepaddle/paddleocr-vl","knowledge":null,"last_updated":"2025-10-22","lifecycle":null,"limits":{"context":16384,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"PaddleOCR-VL","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-10-22","retired":false,"tags":null},"qwen/qwen-2.5-72b-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":0.38,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen-2.5-72b-instruct","knowledge":"2024-04","last_updated":"2024-10-15","lifecycle":null,"limits":{"context":32000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 2.5 72B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-10-15","retired":false,"tags":null},"qwen/qwen-mt-plus":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.25,"output":0.75},"deprecated":false,"extra":{"attachment":false,"description":"Translation model for multilingual conversion, localization, and cross-language workflows","open_weights":true,"temperature":true},"family":null,"id":"qwen/qwen-mt-plus","knowledge":null,"last_updated":"2025-09-03","lifecycle":null,"limits":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen MT Plus","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-03","retired":false,"tags":null},"qwen/qwen2.5-7b-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":0.07,"output":0.07},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen2.5-7b-instruct","knowledge":null,"last_updated":"2025-04-16","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen2.5 7B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"qwen/qwen2.5-vl-72b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.8,"output":0.8},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen/qwen2.5-vl-72b-instruct","knowledge":null,"last_updated":"2025-03-25","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen2.5 VL 72B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-03-25","retired":false,"tags":null},"qwen/qwen3-235b-a22b-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.2,"output":0.8},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b-fp8","knowledge":null,"last_updated":"2025-04-29","lifecycle":null,"limits":{"context":40960,"output":20000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"qwen/qwen3-235b-a22b-instruct-2507":{"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":0.09,"output":0.58},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b-instruct-2507","knowledge":"2025-04","last_updated":"2025-07-22","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct 2507","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-07-22","retired":false,"tags":null},"qwen/qwen3-235b-a22b-thinking-2507":{"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":0.3,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b-thinking-2507","knowledge":"2025-04","last_updated":"2025-07-25","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22b Thinking 2507","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"qwen/qwen3-30b-a3b-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.09,"output":0.45},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen/qwen3-30b-a3b-fp8","knowledge":null,"last_updated":"2025-04-29","lifecycle":null,"limits":{"context":40960,"output":20000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"qwen/qwen3-32b-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.1,"output":0.45},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen/qwen3-32b-fp8","knowledge":null,"last_updated":"2025-04-29","lifecycle":null,"limits":{"context":40960,"output":20000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"qwen/qwen3-4b-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.03,"output":0.03},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen/qwen3-4b-fp8","knowledge":null,"last_updated":"2025-04-29","lifecycle":null,"limits":{"context":128000,"output":20000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 4B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"qwen/qwen3-8b-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.035,"output":0.138},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen/qwen3-8b-fp8","knowledge":null,"last_updated":"2025-04-29","lifecycle":null,"limits":{"context":128000,"output":20000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 8B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"qwen/qwen3-coder-30b-a3b-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":0.07,"output":0.27},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-30b-a3b-instruct","knowledge":null,"last_updated":"2025-10-09","lifecycle":null,"limits":{"context":160000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 30b A3B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-10-09","retired":false,"tags":null},"qwen/qwen3-coder-480b-a35b-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":0.38,"output":1.55},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-480b-a35b-instruct","knowledge":"2025-04","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 480B A35B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"qwen/qwen3-coder-next":{"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":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-next","knowledge":null,"last_updated":"2026-02-03","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Next","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-02-03","retired":false,"tags":null},"qwen/qwen3-embedding-0.6b":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":{"min_dimensions":1},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"type":"embedding"},"family":null,"id":"qwen/qwen3-embedding-0.6b","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["embedding"]},"model":null,"name":"Qwen3 Embedding 0.6B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"qwen/qwen3-embedding-8b":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":{"min_dimensions":1},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"type":"embedding"},"family":null,"id":"qwen/qwen3-embedding-8b","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["embedding"]},"model":null,"name":"Qwen3 Embedding 8B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"qwen/qwen3-max":{"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":2.11,"output":8.45},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-max","knowledge":"2025-04","last_updated":"2025-09-24","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-24","retired":false,"tags":null},"qwen/qwen3-next-80b-a3b-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":0.15,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-next-80b-a3b-instruct","knowledge":null,"last_updated":"2025-09-10","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Next 80B A3B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-10","retired":false,"tags":null},"qwen/qwen3-next-80b-a3b-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":{"input":0.15,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-next-80b-a3b-thinking","knowledge":null,"last_updated":"2025-09-10","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Next 80B A3B Thinking","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-10","retired":false,"tags":null},"qwen/qwen3-omni-30b-a3b-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":0.25,"input_audio":2.2,"output":0.97,"output_audio":1.788},"deprecated":false,"extra":{"attachment":true,"description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-omni-30b-a3b-instruct","knowledge":"2024-04","last_updated":"2025-09-24","lifecycle":null,"limits":{"context":65536,"output":16384},"modalities":{"input":["text","video","audio","image"],"output":["text","audio"]},"model":null,"name":"Qwen3 Omni 30B A3B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-24","retired":false,"tags":null},"qwen/qwen3-omni-30b-a3b-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":{"input":0.25,"input_audio":2.2,"output":0.97,"output_audio":1.788},"deprecated":false,"extra":{"attachment":true,"description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-omni-30b-a3b-thinking","knowledge":null,"last_updated":"2025-09-24","lifecycle":null,"limits":{"context":65536,"output":16384},"modalities":{"input":["text","audio","video","image"],"output":["text"]},"model":null,"name":"Qwen3 Omni 30B A3B Thinking","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-24","retired":false,"tags":null},"qwen/qwen3-vl-235b-a22b-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":0.3,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-vl-235b-a22b-instruct","knowledge":null,"last_updated":"2025-09-24","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3 VL 235B A22B Instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-24","retired":false,"tags":null},"qwen/qwen3-vl-235b-a22b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.98,"output":3.95},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen/qwen3-vl-235b-a22b-thinking","knowledge":null,"last_updated":"2025-09-24","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3 VL 235B A22B Thinking","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-24","retired":false,"tags":null},"qwen/qwen3-vl-30b-a3b-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":0.2,"output":0.7},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-vl-30b-a3b-instruct","knowledge":null,"last_updated":"2025-10-11","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","video","image"],"output":["text"]},"model":null,"name":"qwen/qwen3-vl-30b-a3b-instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-10-11","retired":false,"tags":null},"qwen/qwen3-vl-30b-a3b-thinking":{"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":1},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-vl-30b-a3b-thinking","knowledge":null,"last_updated":"2025-10-11","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"qwen/qwen3-vl-30b-a3b-thinking","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-10-11","retired":false,"tags":null},"qwen/qwen3-vl-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":0.08,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-vl-8b-instruct","knowledge":null,"last_updated":"2025-10-17","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"qwen/qwen3-vl-8b-instruct","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-10-17","retired":false,"tags":null},"qwen/qwen3.5-122b-a10b":{"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":0.4,"output":3.2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-122b-a10b","knowledge":null,"last_updated":"2026-02-26","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5-122B-A10B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"qwen/qwen3.5-27b":{"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":0.3,"output":2.4},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-27b","knowledge":null,"last_updated":"2026-02-26","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5-27B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"qwen/qwen3.5-35b-a3b":{"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":2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-35b-a3b","knowledge":null,"last_updated":"2026-02-26","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5-35B-A3B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"qwen/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":{"input":0.6,"output":3.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-397b-a17b","knowledge":null,"last_updated":"2026-02-17","lifecycle":null,"limits":{"context":262144,"output":64000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5-397B-A17B","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"qwen/qwen3.7-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":0.25,"cache_write":1.5625,"input":1.25,"output":3.75},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.7-max","knowledge":null,"last_updated":"2026-05-27","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.7-Max","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"sao10K/L3-8B-stheno-v3.2":{"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":0.05,"output":0.05},"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":"sao10K/L3-8B-stheno-v3.2","knowledge":null,"last_updated":"2024-11-29","lifecycle":null,"limits":{"context":8192,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"L3 8B Stheno V3.2","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-11-29","retired":false,"tags":null},"sao10K/l3-70b-euryale-v2.1":{"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":{"input":1.48,"output":1.48},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":true,"temperature":true},"family":null,"id":"sao10K/l3-70b-euryale-v2.1","knowledge":null,"last_updated":"2024-06-18","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"L3 70B Euryale V2.1\t","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-06-18","retired":false,"tags":null},"sao10K/l3-8b-lunaris":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.05,"output":0.05},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"sao10K/l3-8b-lunaris","knowledge":null,"last_updated":"2024-11-28","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sao10k L3 8B Lunaris\t","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-11-28","retired":false,"tags":null},"sao10K/l31-70b-euryale-v2.2":{"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":1.48,"output":1.48},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","open_weights":true,"temperature":true},"family":null,"id":"sao10K/l31-70b-euryale-v2.2","knowledge":null,"last_updated":"2024-09-19","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"L31 70B Euryale V2.2","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2024-09-19","retired":false,"tags":null},"xiaomimimo/mimo-v2-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":{"cache_read":0.3,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"xiaomimimo/mimo-v2-flash","knowledge":"2024-12","last_updated":"2025-12-19","lifecycle":null,"limits":{"context":262144,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"XiaomiMiMo/MiMo-V2-Flash","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-12-19","retired":false,"tags":null},"xiaomimimo/mimo-v2-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":0.4,"input":2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"xiaomimimo/mimo-v2-pro","knowledge":"2024-12","last_updated":"2026-05-27","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2-Pro","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"xiaomimimo/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":0.0043,"input":0.522,"output":1.044},"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":[],"structured_output":true,"temperature":true},"family":null,"id":"xiaomimimo/mimo-v2.5-pro","knowledge":"2024-12","last_updated":"2026-05-27","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2.5-Pro","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"zai-org/autoglm-phone-9b-multilingual":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.035,"output":0.138},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","open_weights":true,"temperature":true},"family":null,"id":"zai-org/autoglm-phone-9b-multilingual","knowledge":null,"last_updated":"2025-12-10","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"AutoGLM-Phone-9B-Multilingual","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-12-10","retired":false,"tags":null},"zai-org/glm-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":0.11,"input":0.6,"output":2.2},"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":"toggle"}],"temperature":true},"family":null,"id":"zai-org/glm-4.5","knowledge":null,"last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131072,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"zai-org/glm-4.5-air":{"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":0.13,"output":0.85},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai-org/glm-4.5-air","knowledge":"2025-04","last_updated":"2025-10-13","lifecycle":null,"limits":{"context":131072,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.5 Air","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-10-13","retired":false,"tags":null},"zai-org/glm-4.5v":{"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":0.11,"input":0.6,"output":1.8},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glmv","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-4.5v","knowledge":"2025-04","last_updated":"2025-08-11","lifecycle":null,"limits":{"context":65536,"output":16384},"modalities":{"input":["text","video","image"],"output":["text"]},"model":null,"name":"GLM 4.5V","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-08-11","retired":false,"tags":null},"zai-org/glm-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":0.11,"input":0.55,"output":2.2},"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":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-4.6","knowledge":null,"last_updated":"2025-09-30","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.6","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"zai-org/glm-4.6v":{"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":0.055,"input":0.3,"output":0.9},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glmv","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-4.6v","knowledge":"2025-04","last_updated":"2025-12-08","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","video","image"],"output":["text"]},"model":null,"name":"GLM 4.6V","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-12-08","retired":false,"tags":null},"zai-org/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":{"cache_read":0.11,"input":0.6,"output":2.2},"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":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-4.7","knowledge":null,"last_updated":"2025-12-22","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"zai-org/glm-4.7-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":{"cache_read":0.01,"input":0.07,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-4.7-flash","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"zai-org/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":1,"output":3.2},"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":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":202800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-02-11","retired":false,"tags":null},"zai-org/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":1.38,"output":4.4},"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":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-5.1","knowledge":null,"last_updated":"2026-03-27","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-03-27","retired":false,"tags":null},"zai-org/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":0.26,"input":1.4,"output":4.4},"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":["none","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"novita_ai","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"NovitaAI","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/nvidia.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "nvidia",
+  "abacusai/dracarys-llama-3.1-70b-instruct" | "baai/bge-m3" | "black-forest-labs/flux.1-dev" | "black-forest-labs/flux_1-kontext-dev" | "black-forest-labs/flux_1-schnell" | "black-forest-labs/flux_2-klein-4b" | "bytedance/seed-oss-36b-instruct" | "deepseek-ai/deepseek-v4-flash" | "deepseek-ai/deepseek-v4-pro" | "google/gemma-2-2b-it" | "google/gemma-3-12b-it" | "google/gemma-3-4b-it" | "google/gemma-3n-e2b-it" | "google/gemma-3n-e4b-it" | "google/gemma-4-31b-it" | "google/google-paligemma" | "meta/esm2-650m" | "meta/esmfold" | "meta/llama-3.1-70b-instruct" | "meta/llama-3.1-8b-instruct" | "meta/llama-3.2-11b-vision-instruct" | "meta/llama-3.2-1b-instruct" | "meta/llama-3.2-3b-instruct" | "meta/llama-3.2-90b-vision-instruct" | "meta/llama-3.3-70b-instruct" | "meta/llama-4-maverick-17b-128e-instruct" | "meta/llama-guard-4-12b" | "microsoft/phi-4-mini-instruct" | "microsoft/phi-4-multimodal-instruct" | "minimaxai/minimax-m2.7" | "minimaxai/minimax-m3" | "mistralai/magistral-small-2506" | "mistralai/ministral-14b-instruct-2512" | "mistralai/mistral-7b-instruct-v0.3" | "mistralai/mistral-large-3-675b-instruct-2512" | "mistralai/mistral-medium-3-instruct" | "mistralai/mistral-medium-3.5-128b" | "mistralai/mistral-nemotron" | "mistralai/mistral-small-4-119b-2603" | "mistralai/mixtral-8x22b-instruct" | "mistralai/mixtral-8x7b-instruct" | "moonshotai/kimi-k2-instruct-0905" | "moonshotai/kimi-k2.6" | "nvidia/active-speaker-detection" | "nvidia/bevformer" | "nvidia/cosmos-predict1-5b" | "nvidia/cosmos-reason2-8b" | "nvidia/cosmos-transfer1-7b" | "nvidia/cosmos-transfer2_5-2b" | "nvidia/gliner-pii" | "nvidia/llama-3.1-nemotron-70b-instruct" | "nvidia/llama-3.1-nemotron-nano-8b-v1" | "nvidia/llama-3.1-nemotron-nano-vl-8b-v1" | "nvidia/llama-3.1-nemotron-safety-guard-8b-v3" | "nvidia/llama-3.1-nemotron-ultra-253b-v1" | "nvidia/llama-3.3-nemotron-super-49b-v1" | "nvidia/llama-3.3-nemotron-super-49b-v1.5" | "nvidia/llama-3_2-nemoretriever-300m-embed-v1" | "nvidia/llama-nemotron-embed-vl-1b-v2" | "nvidia/llama-nemotron-rerank-vl-1b-v2" | "nvidia/magpie-tts-zeroshot" | "nvidia/nemotron-3-content-safety" | "nvidia/nemotron-3-nano-30b-a3b" | "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning" | "nvidia/nemotron-3-super-120b-a12b" | "nvidia/nemotron-3-ultra-550b-a55b" | "nvidia/nemotron-content-safety-reasoning-4b" | "nvidia/nemotron-mini-4b-instruct" | "nvidia/nemotron-nano-12b-v2-vl" | "nvidia/nemotron-voicechat" | "nvidia/nv-embed-v1" | "nvidia/nv-embedcode-7b-v1" | "nvidia/nvidia-nemotron-nano-9b-v2" | "nvidia/rerank-qa-mistral-4b" | "nvidia/riva-translate-4b-instruct-v1.1" | "nvidia/sparsedrive" | "nvidia/streampetr" | "nvidia/studiovoice" | "nvidia/synthetic-video-detector" | "nvidia/usdcode" | "nvidia/usdvalidate" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "openai/whisper-large-v3" | "poolside/laguna-xs-2.1" | "qwen/qwen-image" | "qwen/qwen-image-edit" | "qwen/qwen2.5-coder-32b-instruct" | "qwen/qwen3-coder-480b-a35b-instruct" | "qwen/qwen3-next-80b-a3b-instruct" | "qwen/qwen3.5-122b-a10b" | "qwen/qwen3.5-397b-a17b" | "sarvamai/sarvam-m" | "stepfun-ai/step-3.5-flash" | "stepfun-ai/step-3.7-flash" | "thinkingmachines/inkling" | "upstage/solar-10.7b-instruct" | "z-ai/glm-5.2"
+>;
+export default provider;