llm-arithmetic-explorer / model_info_snapshot.json
hoololi's picture
Upload 7 files
29f893d verified
Raw
History Blame Contribute Delete
60.9 kB
{
"openai/gpt-3.5-turbo": {
"id": "openai/gpt-3.5-turbo",
"canonical_slug": "openai/gpt-3.5-turbo",
"hugging_face_id": null,
"name": "OpenAI: GPT-3.5 Turbo",
"created": 1685232000,
"description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.",
"context_length": 16385,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "GPT",
"instruct_type": null
},
"pricing": {
"prompt": "0.0000005",
"completion": "0.0000015"
},
"top_provider": {
"context_length": 16385,
"max_completion_tokens": 4096,
"is_moderated": true
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
"logprobs",
"max_tokens",
"presence_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_logprobs",
"top_p"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": "2021-09-30",
"expiration_date": null,
"links": {
"details": "/api/v1/models/openai/gpt-3.5-turbo/endpoints"
},
"benchmarks": {
"design_arena": [],
"artificial_analysis": {
"intelligence_index": null,
"coding_index": 10.7,
"agentic_index": null
}
},
"model_family": "openai"
},
"openai/gpt-4": {
"id": "openai/gpt-4",
"canonical_slug": "openai/gpt-4",
"hugging_face_id": null,
"name": "OpenAI: GPT-4",
"created": 1685232000,
"description": "OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...",
"context_length": 8191,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "GPT",
"instruct_type": null
},
"pricing": {
"prompt": "0.00003",
"completion": "0.00006"
},
"top_provider": {
"context_length": 8191,
"max_completion_tokens": 4096,
"is_moderated": true
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
"logprobs",
"max_completion_tokens",
"max_tokens",
"presence_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_logprobs",
"top_p"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": "2021-09-30",
"expiration_date": null,
"links": {
"details": "/api/v1/models/openai/gpt-4/endpoints"
},
"benchmarks": {
"design_arena": [],
"artificial_analysis": {
"intelligence_index": null,
"coding_index": 13.1,
"agentic_index": null
}
},
"model_family": "openai"
},
"openai/gpt-4o-mini": {
"id": "openai/gpt-4o-mini",
"canonical_slug": "openai/gpt-4o-mini",
"hugging_face_id": null,
"name": "OpenAI: GPT-4o-mini",
"created": 1721260800,
"description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...",
"context_length": 128000,
"architecture": {
"modality": "text+image+file->text",
"input_modalities": [
"text",
"image",
"file"
],
"output_modalities": [
"text"
],
"tokenizer": "GPT",
"instruct_type": null
},
"pricing": {
"prompt": "0.00000015",
"completion": "0.0000006",
"input_cache_read": "0.000000075"
},
"top_provider": {
"context_length": 128000,
"max_completion_tokens": 16384,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
"logprobs",
"max_completion_tokens",
"max_tokens",
"presence_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_logprobs",
"top_p",
"web_search_options"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": "2023-10-31",
"expiration_date": null,
"links": {
"details": "/api/v1/models/openai/gpt-4o-mini/endpoints"
},
"benchmarks": {
"design_arena": [],
"artificial_analysis": {
"intelligence_index": null,
"coding_index": 11.4,
"agentic_index": 1
}
},
"model_family": "openai"
},
"openai/gpt-oss-120b": {
"id": "openai/gpt-oss-120b",
"canonical_slug": "openai/gpt-oss-120b",
"hugging_face_id": "openai/gpt-oss-120b",
"name": "OpenAI: gpt-oss-120b",
"created": 1754414231,
"description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...",
"context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "GPT",
"instruct_type": null
},
"pricing": {
"prompt": "0.00000003",
"completion": "0.00000015"
},
"top_provider": {
"context_length": 131072,
"max_completion_tokens": 131072,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_a",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"frequency_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": "2024-06-30",
"expiration_date": null,
"links": {
"details": "/api/v1/models/openai/gpt-oss-120b/endpoints"
},
"benchmarks": {
"design_arena": [
{
"arena": "models",
"category": "3d",
"elo": 978,
"win_rate": 29.4,
"rank": 91
},
{
"arena": "models",
"category": "codecategories",
"elo": 1012,
"win_rate": 33.4,
"rank": 98
},
{
"arena": "models",
"category": "dataviz",
"elo": 1043,
"win_rate": 45.1,
"rank": 87
},
{
"arena": "models",
"category": "gamedev",
"elo": 1059,
"win_rate": 40.6,
"rank": 85
},
{
"arena": "models",
"category": "uicomponent",
"elo": 978,
"win_rate": 35.5,
"rank": 92
},
{
"arena": "models",
"category": "website",
"elo": 1010,
"win_rate": 32.5,
"rank": 100
}
],
"artificial_analysis": {
"intelligence_index": 23.8,
"coding_index": 30.4,
"agentic_index": 13.2
}
},
"reasoning": {
"mandatory": true,
"supported_efforts": [
"high",
"medium",
"low"
],
"default_effort": "medium"
},
"model_family": "openai"
},
"openai/gpt-5.5": {
"id": "openai/gpt-5.5",
"canonical_slug": "openai/gpt-5.5-20260423",
"hugging_face_id": "",
"name": "OpenAI: GPT-5.5",
"created": 1777051893,
"description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...",
"context_length": 1050000,
"architecture": {
"modality": "text+image+file->text",
"input_modalities": [
"file",
"image",
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "GPT",
"instruct_type": null
},
"pricing": {
"prompt": "0.000005",
"completion": "0.00003",
"web_search": "0.01",
"input_cache_read": "0.0000005"
},
"top_provider": {
"context_length": 1050000,
"max_completion_tokens": 128000,
"is_moderated": true
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"max_completion_tokens",
"max_tokens",
"reasoning",
"response_format",
"seed",
"structured_outputs",
"tool_choice",
"tools"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": "2025-12-01",
"expiration_date": null,
"links": {
"details": "/api/v1/models/openai/gpt-5.5-20260423/endpoints"
},
"benchmarks": {
"design_arena": [
{
"arena": "agents",
"category": "agenticgamedev",
"elo": 1207,
"win_rate": 53,
"rank": 5
},
{
"arena": "agents",
"category": "agentichtmlslides",
"elo": 1084,
"win_rate": 34.2,
"rank": 9
},
{
"arena": "agents",
"category": "agenticslides",
"elo": 1150,
"win_rate": 43.5,
"rank": 7
},
{
"arena": "agents",
"category": "agenticslides(html)",
"elo": 1077,
"win_rate": 33.2,
"rank": 9
},
{
"arena": "agents",
"category": "agenticslides(python-pptx)",
"elo": 1155,
"win_rate": 45.2,
"rank": 7
},
{
"arena": "agents",
"category": "androidnative",
"elo": 1260,
"win_rate": 55.4,
"rank": 4
},
{
"arena": "agents",
"category": "fullstack",
"elo": 1151,
"win_rate": 44.5,
"rank": 15
},
{
"arena": "agents",
"category": "godotgamedev",
"elo": 1217,
"win_rate": 53,
"rank": 9
},
{
"arena": "agents",
"category": "htmlslides",
"elo": 1082,
"win_rate": 34.3,
"rank": 11
},
{
"arena": "agents",
"category": "mobileapps",
"elo": 1220,
"win_rate": 51,
"rank": 9
},
{
"arena": "agents",
"category": "pptxslides",
"elo": 1157,
"win_rate": 45.3,
"rank": 7
},
{
"arena": "agents",
"category": "python-pptxslides",
"elo": 1152,
"win_rate": 43.3,
"rank": 8
},
{
"arena": "agents",
"category": "webapps",
"elo": 1182,
"win_rate": 45.2,
"rank": 18
},
{
"arena": "models",
"category": "3d",
"elo": 1264,
"win_rate": 53.2,
"rank": 29
},
{
"arena": "models",
"category": "asciiart",
"elo": 1316,
"win_rate": 63.2,
"rank": 3
},
{
"arena": "models",
"category": "codecategories",
"elo": 1296,
"win_rate": 56.7,
"rank": 17
},
{
"arena": "models",
"category": "dataviz",
"elo": 1300,
"win_rate": 58.3,
"rank": 9
},
{
"arena": "models",
"category": "gamedev",
"elo": 1348,
"win_rate": 62.8,
"rank": 3
},
{
"arena": "models",
"category": "svg",
"elo": 1283,
"win_rate": 59.9,
"rank": 6
},
{
"arena": "models",
"category": "uicomponent",
"elo": 1298,
"win_rate": 57,
"rank": 16
},
{
"arena": "models",
"category": "website",
"elo": 1290,
"win_rate": 56,
"rank": 19
}
],
"artificial_analysis": {
"intelligence_index": 54.8,
"coding_index": 74.9,
"agentic_index": 44.9
}
},
"reasoning": {
"mandatory": false,
"default_enabled": true,
"supported_efforts": [
"xhigh",
"high",
"medium",
"low",
"none"
],
"default_effort": "medium"
},
"model_family": "openai"
},
"qwen/qwen-2.5-72b-instruct": {
"id": "qwen/qwen-2.5-72b-instruct",
"canonical_slug": "qwen/qwen-2.5-72b-instruct",
"hugging_face_id": "Qwen/Qwen2.5-72B-Instruct",
"name": "Qwen2.5 72B Instruct",
"created": 1726704000,
"description": "Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...",
"context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "Qwen",
"instruct_type": "chatml"
},
"pricing": {
"prompt": "0.00000036",
"completion": "0.0000004"
},
"top_provider": {
"context_length": 32768,
"max_completion_tokens": 16384,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
"max_tokens",
"min_p",
"presence_penalty",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_p"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": "2024-06-30",
"expiration_date": null,
"links": {
"details": "/api/v1/models/qwen/qwen-2.5-72b-instruct/endpoints"
},
"model_family": "qwen"
},
"qwen/qwen3-30b-a3b-thinking-2507": {
"id": "qwen/qwen3-30b-a3b-thinking-2507",
"canonical_slug": "qwen/qwen3-30b-a3b-thinking-2507",
"hugging_face_id": "Qwen/Qwen3-30B-A3B-Thinking-2507",
"name": "Qwen: Qwen3 30B A3B Thinking 2507",
"created": 1756399192,
"description": "Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...",
"context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "Qwen3",
"instruct_type": null
},
"pricing": {
"prompt": "0.00000013",
"completion": "0.00000156"
},
"top_provider": {
"context_length": 81920,
"max_completion_tokens": 32768,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"max_tokens",
"presence_penalty",
"reasoning",
"response_format",
"seed",
"temperature",
"tool_choice",
"tools",
"top_p"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": "2025-06-30",
"expiration_date": null,
"links": {
"details": "/api/v1/models/qwen/qwen3-30b-a3b-thinking-2507/endpoints"
},
"benchmarks": {
"design_arena": [
{
"arena": "models",
"category": "dataviz",
"elo": 969,
"win_rate": 33.3,
"rank": 95
},
{
"arena": "models",
"category": "website",
"elo": 973,
"win_rate": 35.5,
"rank": 103
}
],
"artificial_analysis": {
"intelligence_index": 14.4,
"coding_index": 12.1,
"agentic_index": 1.8
}
},
"reasoning": {
"mandatory": true
},
"model_family": "qwen"
},
"qwen/qwen3.5-flash-02-23": {
"id": "qwen/qwen3.5-flash-02-23",
"canonical_slug": "qwen/qwen3.5-flash-20260224",
"hugging_face_id": null,
"name": "Qwen: Qwen3.5-Flash",
"created": 1772053776,
"description": "The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...",
"context_length": 1000000,
"architecture": {
"modality": "text+image+video->text",
"input_modalities": [
"text",
"image",
"video"
],
"output_modalities": [
"text"
],
"tokenizer": "Qwen3",
"instruct_type": null
},
"pricing": {
"prompt": "0.000000065",
"completion": "0.00000026"
},
"top_provider": {
"context_length": 1000000,
"max_completion_tokens": 65536,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"max_tokens",
"presence_penalty",
"reasoning",
"response_format",
"seed",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_p"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"frequency_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/qwen/qwen3.5-flash-20260224/endpoints"
},
"reasoning": {
"mandatory": false
},
"model_family": "qwen"
},
"qwen/qwen3.7-plus": {
"id": "qwen/qwen3.7-plus",
"canonical_slug": "qwen/qwen3.7-plus-20260602",
"hugging_face_id": null,
"name": "Qwen: Qwen3.7 Plus",
"created": 1780491783,
"description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...",
"context_length": 1000000,
"architecture": {
"modality": "text+image->text",
"input_modalities": [
"text",
"image"
],
"output_modalities": [
"text"
],
"tokenizer": "Qwen",
"instruct_type": null
},
"pricing": {
"prompt": "0.00000032",
"completion": "0.00000128",
"input_cache_read": "0.000000064",
"input_cache_write": "0.0000004"
},
"top_provider": {
"context_length": 1000000,
"max_completion_tokens": 65536,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"logprobs",
"max_tokens",
"presence_penalty",
"reasoning",
"response_format",
"seed",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_logprobs",
"top_p"
],
"default_parameters": {},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints"
},
"benchmarks": {
"design_arena": [],
"artificial_analysis": {
"intelligence_index": 39,
"coding_index": 55.9,
"agentic_index": 20.8
}
},
"reasoning": {
"mandatory": false,
"default_enabled": true
},
"model_family": "qwen"
},
"deepseek/deepseek-v3.2": {
"id": "deepseek/deepseek-v3.2",
"canonical_slug": "deepseek/deepseek-v3.2-20251201",
"hugging_face_id": "deepseek-ai/DeepSeek-V3.2",
"name": "DeepSeek: DeepSeek V3.2",
"created": 1764594642,
"description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...",
"context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "DeepSeek",
"instruct_type": null
},
"pricing": {
"prompt": "0.0000002288",
"completion": "0.0000003432",
"input_cache_read": "0.00000002288"
},
"top_provider": {
"context_length": 128000,
"max_completion_tokens": 64000,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {
"temperature": 1,
"top_p": 0.95,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/deepseek/deepseek-v3.2-20251201/endpoints"
},
"benchmarks": {
"design_arena": [
{
"arena": "models",
"category": "3d",
"elo": 1212,
"win_rate": 49.9,
"rank": 42
},
{
"arena": "models",
"category": "asciiart",
"elo": 1130,
"win_rate": 40.9,
"rank": 43
},
{
"arena": "models",
"category": "codecategories",
"elo": 1213,
"win_rate": 49.6,
"rank": 49
},
{
"arena": "models",
"category": "dataviz",
"elo": 1202,
"win_rate": 48.6,
"rank": 49
},
{
"arena": "models",
"category": "gamedev",
"elo": 1198,
"win_rate": 46.7,
"rank": 51
},
{
"arena": "models",
"category": "svg",
"elo": 1089,
"win_rate": 40.9,
"rank": 55
},
{
"arena": "models",
"category": "uicomponent",
"elo": 1202,
"win_rate": 46.9,
"rank": 48
},
{
"arena": "models",
"category": "website",
"elo": 1216,
"win_rate": 50.5,
"rank": 48
}
]
},
"reasoning": {
"mandatory": false,
"default_enabled": false
},
"model_family": "deepseek"
},
"deepseek/deepseek-v4-flash": {
"id": "deepseek/deepseek-v4-flash",
"canonical_slug": "deepseek/deepseek-v4-flash-20260423",
"hugging_face_id": "deepseek-ai/DeepSeek-V4-Flash",
"name": "DeepSeek: DeepSeek V4 Flash",
"created": 1777000666,
"description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...",
"context_length": 1048576,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "DeepSeek",
"instruct_type": null
},
"pricing": {
"prompt": "0.00000009",
"completion": "0.00000018",
"input_cache_read": "0.000000018"
},
"top_provider": {
"context_length": 1048576,
"max_completion_tokens": 16384,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/deepseek/deepseek-v4-flash-20260423/endpoints"
},
"benchmarks": {
"design_arena": [
{
"arena": "models",
"category": "3d",
"elo": 1268,
"win_rate": 50,
"rank": 27
},
{
"arena": "models",
"category": "asciiart",
"elo": 1165,
"win_rate": 44.4,
"rank": 36
},
{
"arena": "models",
"category": "codecategories",
"elo": 1256,
"win_rate": 50.1,
"rank": 31
},
{
"arena": "models",
"category": "dataviz",
"elo": 1166,
"win_rate": 41.5,
"rank": 63
},
{
"arena": "models",
"category": "gamedev",
"elo": 1263,
"win_rate": 50.7,
"rank": 28
},
{
"arena": "models",
"category": "svg",
"elo": 1215,
"win_rate": 49.3,
"rank": 24
},
{
"arena": "models",
"category": "uicomponent",
"elo": 1218,
"win_rate": 46.2,
"rank": 41
},
{
"arena": "models",
"category": "website",
"elo": 1251,
"win_rate": 50.8,
"rank": 31
}
],
"artificial_analysis": {
"intelligence_index": 40.3,
"coding_index": 56.2,
"agentic_index": 31.1
}
},
"reasoning": {
"mandatory": false,
"supported_efforts": [
"xhigh",
"high"
],
"default_effort": "high"
},
"model_family": "deepseek"
},
"deepseek/deepseek-v4-pro": {
"id": "deepseek/deepseek-v4-pro",
"canonical_slug": "deepseek/deepseek-v4-pro-20260423",
"hugging_face_id": "deepseek-ai/DeepSeek-V4-Pro",
"name": "DeepSeek: DeepSeek V4 Pro",
"created": 1777000679,
"description": "DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...",
"context_length": 1048576,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "DeepSeek",
"instruct_type": null
},
"pricing": {
"prompt": "0.000000435",
"completion": "0.00000087",
"input_cache_read": "0.000000003625"
},
"top_provider": {
"context_length": 1048576,
"max_completion_tokens": 384000,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {
"temperature": 1,
"top_p": 1,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/deepseek/deepseek-v4-pro-20260423/endpoints"
},
"benchmarks": {
"design_arena": [
{
"arena": "agents",
"category": "fullstack",
"elo": 948,
"win_rate": 22.1,
"rank": 29
},
{
"arena": "agents",
"category": "godotgamedev",
"elo": 1097,
"win_rate": 34,
"rank": 20
},
{
"arena": "agents",
"category": "webapps",
"elo": 1018,
"win_rate": 26.6,
"rank": 25
},
{
"arena": "models",
"category": "3d",
"elo": 1325,
"win_rate": 60.5,
"rank": 7
},
{
"arena": "models",
"category": "asciiart",
"elo": 1202,
"win_rate": 47.6,
"rank": 22
},
{
"arena": "models",
"category": "codecategories",
"elo": 1287,
"win_rate": 54.9,
"rank": 20
},
{
"arena": "models",
"category": "dataviz",
"elo": 1221,
"win_rate": 48.6,
"rank": 38
},
{
"arena": "models",
"category": "gamedev",
"elo": 1296,
"win_rate": 56.1,
"rank": 18
},
{
"arena": "models",
"category": "svg",
"elo": 1193,
"win_rate": 46.9,
"rank": 34
},
{
"arena": "models",
"category": "uicomponent",
"elo": 1271,
"win_rate": 52,
"rank": 25
},
{
"arena": "models",
"category": "website",
"elo": 1278,
"win_rate": 53.7,
"rank": 23
}
],
"artificial_analysis": {
"intelligence_index": 44.3,
"coding_index": 59.4,
"agentic_index": 36.4
}
},
"reasoning": {
"mandatory": false,
"supported_efforts": [
"xhigh",
"high"
],
"default_effort": "high"
},
"model_family": "deepseek"
},
"google/gemini-3-flash-preview": {
"id": "google/gemini-3-flash-preview",
"canonical_slug": "google/gemini-3-flash-preview-20251217",
"hugging_face_id": "",
"name": "Google: Gemini 3 Flash Preview",
"created": 1765987078,
"description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...",
"context_length": 1048576,
"architecture": {
"modality": "text+image+file+audio+video->text",
"input_modalities": [
"text",
"image",
"file",
"audio",
"video"
],
"output_modalities": [
"text"
],
"tokenizer": "Gemini",
"instruct_type": null
},
"pricing": {
"prompt": "0.0000005",
"completion": "0.000003",
"image": "0.0000005",
"audio": "0.000001",
"web_search": "0.014",
"internal_reasoning": "0.000003",
"input_cache_read": "0.00000005",
"input_cache_write": "0.00000008333333333333334"
},
"top_provider": {
"context_length": 1048576,
"max_completion_tokens": 65535,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"max_tokens",
"reasoning",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_p"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/google/gemini-3-flash-preview-20251217/endpoints"
},
"benchmarks": {
"design_arena": [
{
"arena": "agents",
"category": "agenticslides",
"elo": 1073,
"win_rate": 39.3,
"rank": 9
},
{
"arena": "agents",
"category": "agenticslides(python-pptx)",
"elo": 1075,
"win_rate": 39.3,
"rank": 9
},
{
"arena": "agents",
"category": "androidnative",
"elo": 1059,
"win_rate": 48,
"rank": 24
},
{
"arena": "agents",
"category": "fullstack",
"elo": 1128,
"win_rate": 47.1,
"rank": 17
},
{
"arena": "agents",
"category": "godotgamedev",
"elo": 1218,
"win_rate": 52.3,
"rank": 8
},
{
"arena": "agents",
"category": "mobileapps",
"elo": 1183,
"win_rate": 49.8,
"rank": 17
},
{
"arena": "agents",
"category": "webapps",
"elo": 1186,
"win_rate": 49.5,
"rank": 17
},
{
"arena": "models",
"category": "3d",
"elo": 1261,
"win_rate": 62.7,
"rank": 30
},
{
"arena": "models",
"category": "codecategories",
"elo": 1238,
"win_rate": 57.6,
"rank": 34
},
{
"arena": "models",
"category": "gamedev",
"elo": 1232,
"win_rate": 58.3,
"rank": 39
},
{
"arena": "models",
"category": "website",
"elo": 1238,
"win_rate": 57,
"rank": 34
}
]
},
"reasoning": {
"mandatory": false,
"supported_efforts": [
"high",
"medium",
"low",
"minimal"
],
"default_effort": "medium"
},
"model_family": "google"
},
"google/gemini-2.5-flash-lite": {
"id": "google/gemini-2.5-flash-lite",
"canonical_slug": "google/gemini-2.5-flash-lite",
"hugging_face_id": "",
"name": "Google: Gemini 2.5 Flash Lite",
"created": 1753200276,
"description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...",
"context_length": 1048576,
"architecture": {
"modality": "text+image+file+audio+video->text",
"input_modalities": [
"text",
"image",
"file",
"audio",
"video"
],
"output_modalities": [
"text"
],
"tokenizer": "Gemini",
"instruct_type": null
},
"pricing": {
"prompt": "0.0000001",
"completion": "0.0000004",
"image": "0.0000001",
"audio": "0.0000003",
"web_search": "0.014",
"internal_reasoning": "0.0000004",
"input_cache_read": "0.00000001",
"input_cache_write": "0.00000008333333333333334"
},
"top_provider": {
"context_length": 1048576,
"max_completion_tokens": 65535,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"max_tokens",
"reasoning",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_p"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"frequency_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": "2025-01-31",
"expiration_date": null,
"links": {
"details": "/api/v1/models/google/gemini-2.5-flash-lite/endpoints"
},
"reasoning": {
"mandatory": false
},
"model_family": "google"
},
"google/gemma-4-31b-it": {
"id": "google/gemma-4-31b-it",
"canonical_slug": "google/gemma-4-31b-it-20260402",
"hugging_face_id": "google/gemma-4-31B-it",
"name": "Google: Gemma 4 31B",
"created": 1775148486,
"description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...",
"context_length": 262144,
"architecture": {
"modality": "text+image+video->text",
"input_modalities": [
"image",
"text",
"video"
],
"output_modalities": [
"text"
],
"tokenizer": "Gemma",
"instruct_type": null
},
"pricing": {
"prompt": "0.00000012",
"completion": "0.00000035",
"input_cache_read": "0.00000009"
},
"top_provider": {
"context_length": 262144,
"max_completion_tokens": 262144,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {
"temperature": 1,
"top_p": 0.95,
"top_k": 64,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/google/gemma-4-31b-it-20260402/endpoints"
},
"benchmarks": {
"design_arena": [],
"artificial_analysis": {
"intelligence_index": 29.4,
"coding_index": 43.4,
"agentic_index": 14.4
}
},
"reasoning": {
"mandatory": false,
"default_enabled": false
},
"model_family": "google"
},
"google/gemini-3.5-flash": {
"id": "google/gemini-3.5-flash",
"canonical_slug": "google/gemini-3.5-flash-20260519",
"hugging_face_id": null,
"name": "Google: Gemini 3.5 Flash",
"created": 1779193800,
"description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...",
"context_length": 1048576,
"architecture": {
"modality": "text+image+file+audio+video->text",
"input_modalities": [
"text",
"image",
"video",
"file",
"audio"
],
"output_modalities": [
"text"
],
"tokenizer": "Gemini",
"instruct_type": null
},
"pricing": {
"prompt": "0.0000015",
"completion": "0.000009",
"image": "0.0000015",
"audio": "0.000003",
"web_search": "0.014",
"internal_reasoning": "0.000009",
"input_cache_read": "0.00000015",
"input_cache_write": "0.00000008333333333333334"
},
"top_provider": {
"context_length": 1048576,
"max_completion_tokens": 65536,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"max_tokens",
"reasoning",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_p"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": "2025-01-01",
"expiration_date": null,
"links": {
"details": "/api/v1/models/google/gemini-3.5-flash-20260519/endpoints"
},
"benchmarks": {
"design_arena": [
{
"arena": "agents",
"category": "agenticgamedev",
"elo": 1212,
"win_rate": 54.9,
"rank": 3
},
{
"arena": "agents",
"category": "agentichtmlslides",
"elo": 1162,
"win_rate": 45.8,
"rank": 7
},
{
"arena": "agents",
"category": "agenticslides",
"elo": 1244,
"win_rate": 57.5,
"rank": 4
},
{
"arena": "agents",
"category": "agenticslides(html)",
"elo": 1162,
"win_rate": 45.7,
"rank": 7
},
{
"arena": "agents",
"category": "agenticslides(python-pptx)",
"elo": 1242,
"win_rate": 57.8,
"rank": 3
},
{
"arena": "agents",
"category": "androidnative",
"elo": 1256,
"win_rate": 54.4,
"rank": 5
},
{
"arena": "agents",
"category": "fullstack",
"elo": 1264,
"win_rate": 58,
"rank": 6
},
{
"arena": "agents",
"category": "htmlslides",
"elo": 1181,
"win_rate": 49,
"rank": 9
},
{
"arena": "agents",
"category": "mobileapps",
"elo": 1257,
"win_rate": 56.5,
"rank": 3
},
{
"arena": "agents",
"category": "pptxslides",
"elo": 1244,
"win_rate": 57.7,
"rank": 3
},
{
"arena": "agents",
"category": "python-pptxslides",
"elo": 1247,
"win_rate": 57.4,
"rank": 4
},
{
"arena": "agents",
"category": "webapps",
"elo": 1264,
"win_rate": 54.2,
"rank": 6
},
{
"arena": "models",
"category": "3d",
"elo": 1313,
"win_rate": 60.2,
"rank": 14
},
{
"arena": "models",
"category": "asciiart",
"elo": 1310,
"win_rate": 62.1,
"rank": 5
},
{
"arena": "models",
"category": "codecategories",
"elo": 1306,
"win_rate": 58.4,
"rank": 12
},
{
"arena": "models",
"category": "dataviz",
"elo": 1266,
"win_rate": 54.9,
"rank": 24
},
{
"arena": "models",
"category": "gamedev",
"elo": 1330,
"win_rate": 59.3,
"rank": 9
},
{
"arena": "models",
"category": "svg",
"elo": 1307,
"win_rate": 63,
"rank": 3
},
{
"arena": "models",
"category": "uicomponent",
"elo": 1311,
"win_rate": 59.4,
"rank": 12
},
{
"arena": "models",
"category": "website",
"elo": 1299,
"win_rate": 57.5,
"rank": 15
}
],
"artificial_analysis": {
"intelligence_index": 50.2,
"coding_index": 70.1,
"agentic_index": 37.4
}
},
"reasoning": {
"mandatory": true,
"default_enabled": true,
"supported_efforts": [
"high",
"medium",
"low",
"minimal"
],
"default_effort": "medium"
},
"model_family": "google"
},
"cohere/north-mini-code:free": {
"id": "cohere/north-mini-code:free",
"canonical_slug": "cohere/north-mini-code-20260617",
"hugging_face_id": "CohereLabs/North-Mini-Code-1.0",
"name": "Cohere: North Mini Code (free)",
"created": 1781723748,
"description": "North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...",
"context_length": 256000,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "Cohere",
"instruct_type": null
},
"pricing": {
"prompt": "0",
"completion": "0"
},
"top_provider": {
"context_length": 256000,
"max_completion_tokens": 64000,
"is_moderated": true
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"max_tokens",
"presence_penalty",
"reasoning",
"seed",
"stop",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_p"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/cohere/north-mini-code-20260617/endpoints"
},
"reasoning": {
"mandatory": false
},
"model_family": "others"
},
"mistralai/mistral-nemo": {
"id": "mistralai/mistral-nemo",
"canonical_slug": "mistralai/mistral-nemo",
"hugging_face_id": "mistralai/Mistral-Nemo-Instruct-2407",
"name": "Mistral: Mistral Nemo",
"created": 1721347200,
"description": "A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...",
"context_length": 131072,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "Mistral",
"instruct_type": "mistral"
},
"pricing": {
"prompt": "0.00000002",
"completion": "0.00000003"
},
"top_provider": {
"context_length": 131072,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {
"temperature": 0.3
},
"supported_voices": null,
"knowledge_cutoff": "2024-04-30",
"expiration_date": null,
"links": {
"details": "/api/v1/models/mistralai/mistral-nemo/endpoints"
},
"model_family": "others"
},
"poolside/laguna-m.1": {
"id": "poolside/laguna-m.1",
"canonical_slug": "poolside/laguna-m.1-20260312",
"hugging_face_id": "poolside/Laguna-M.1",
"name": "Poolside: Laguna M.1",
"created": 1777388504,
"description": "Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...",
"context_length": 262144,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "Other",
"instruct_type": null
},
"pricing": {
"prompt": "0.0000002",
"completion": "0.0000004",
"input_cache_read": "0.0000001"
},
"top_provider": {
"context_length": 262144,
"max_completion_tokens": 32768,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"max_tokens",
"reasoning",
"temperature",
"tool_choice",
"tools"
],
"default_parameters": {
"temperature": null,
"top_p": null,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/poolside/laguna-m.1-20260312/endpoints"
},
"reasoning": {
"mandatory": false,
"default_enabled": true
},
"model_family": "others"
},
"xiaomi/mimo-v2.5": {
"id": "xiaomi/mimo-v2.5",
"canonical_slug": "xiaomi/mimo-v2.5-20260422",
"hugging_face_id": "XiaomiMiMo/MiMo-V2.5",
"name": "Xiaomi: MiMo-V2.5",
"created": 1776874269,
"description": "MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...",
"context_length": 1048576,
"architecture": {
"modality": "text+image+audio+video->text",
"input_modalities": [
"text",
"audio",
"image",
"video"
],
"output_modalities": [
"text"
],
"tokenizer": "Other",
"instruct_type": null
},
"pricing": {
"prompt": "0.000000105",
"completion": "0.00000028"
},
"top_provider": {
"context_length": 32000,
"max_completion_tokens": null,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {
"temperature": 1,
"top_p": 0.95,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/xiaomi/mimo-v2.5-20260422/endpoints"
},
"benchmarks": {
"design_arena": [
{
"arena": "models",
"category": "3d",
"elo": 1298,
"win_rate": 54.1,
"rank": 19
},
{
"arena": "models",
"category": "asciiart",
"elo": 1189,
"win_rate": 47.5,
"rank": 28
},
{
"arena": "models",
"category": "codecategories",
"elo": 1303,
"win_rate": 55,
"rank": 15
},
{
"arena": "models",
"category": "dataviz",
"elo": 1282,
"win_rate": 54,
"rank": 16
},
{
"arena": "models",
"category": "gamedev",
"elo": 1298,
"win_rate": 55.6,
"rank": 17
},
{
"arena": "models",
"category": "svg",
"elo": 1219,
"win_rate": 52.3,
"rank": 22
},
{
"arena": "models",
"category": "uicomponent",
"elo": 1311,
"win_rate": 56.1,
"rank": 13
},
{
"arena": "models",
"category": "website",
"elo": 1304,
"win_rate": 55.2,
"rank": 12
}
]
},
"reasoning": {
"mandatory": false
},
"model_family": "others"
},
"minimax/minimax-m3": {
"id": "minimax/minimax-m3",
"canonical_slug": "minimax/minimax-m3-20260531",
"hugging_face_id": "MiniMaxAI/Minimax-M3",
"name": "MiniMax: MiniMax M3",
"created": 1780245374,
"description": "MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...",
"context_length": 1048576,
"architecture": {
"modality": "text+image+video->text",
"input_modalities": [
"text",
"image",
"video"
],
"output_modalities": [
"text"
],
"tokenizer": "Other",
"instruct_type": null
},
"pricing": {
"prompt": "0.0000003",
"completion": "0.0000012",
"input_cache_read": "0.00000006"
},
"top_provider": {
"context_length": 524288,
"max_completion_tokens": 512000,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {
"temperature": 1,
"top_p": 0.95,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/minimax/minimax-m3-20260531/endpoints"
},
"benchmarks": {
"design_arena": [
{
"arena": "agents",
"category": "androidnative",
"elo": 1047,
"win_rate": 26,
"rank": 26
},
{
"arena": "models",
"category": "3d",
"elo": 1305,
"win_rate": 56.6,
"rank": 17
},
{
"arena": "models",
"category": "asciiart",
"elo": 1221,
"win_rate": 49.8,
"rank": 15
},
{
"arena": "models",
"category": "codecategories",
"elo": 1306,
"win_rate": 55.6,
"rank": 14
},
{
"arena": "models",
"category": "dataviz",
"elo": 1291,
"win_rate": 56.7,
"rank": 11
},
{
"arena": "models",
"category": "gamedev",
"elo": 1288,
"win_rate": 51.6,
"rank": 20
},
{
"arena": "models",
"category": "svg",
"elo": 1243,
"win_rate": 54.3,
"rank": 15
},
{
"arena": "models",
"category": "uicomponent",
"elo": 1294,
"win_rate": 54.1,
"rank": 17
},
{
"arena": "models",
"category": "website",
"elo": 1304,
"win_rate": 55.6,
"rank": 13
}
],
"artificial_analysis": {
"intelligence_index": 44.4,
"coding_index": 58.6,
"agentic_index": 35.4
}
},
"reasoning": {
"mandatory": false
},
"model_family": "others"
},
"z-ai/glm-5.2": {
"id": "z-ai/glm-5.2",
"canonical_slug": "z-ai/glm-5.2-20260616",
"hugging_face_id": "zai-org/GLM-5.2",
"name": "Z.ai: GLM 5.2",
"created": 1781631930,
"description": "GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...",
"context_length": 1048576,
"architecture": {
"modality": "text->text",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "Other",
"instruct_type": null
},
"pricing": {
"prompt": "0.00000056",
"completion": "0.00000176",
"input_cache_read": "0.000000104"
},
"top_provider": {
"context_length": 1048576,
"max_completion_tokens": 131072,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
"logit_bias",
"logprobs",
"max_tokens",
"min_p",
"parallel_tool_calls",
"presence_penalty",
"reasoning",
"reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
"stop",
"structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
"top_logprobs",
"top_p"
],
"default_parameters": {
"temperature": 1,
"top_p": 0.95,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
},
"supported_voices": null,
"knowledge_cutoff": null,
"expiration_date": null,
"links": {
"details": "/api/v1/models/z-ai/glm-5.2-20260616/endpoints"
},
"benchmarks": {
"design_arena": [
{
"arena": "agents",
"category": "androidnative",
"elo": 1252,
"win_rate": 57,
"rank": 6
},
{
"arena": "agents",
"category": "fullstack",
"elo": 1293,
"win_rate": 63.6,
"rank": 3
},
{
"arena": "agents",
"category": "htmlslides",
"elo": 1204,
"win_rate": 52.5,
"rank": 8
},
{
"arena": "agents",
"category": "mobileapps",
"elo": 1240,
"win_rate": 54,
"rank": 5
},
{
"arena": "agents",
"category": "python-pptxslides",
"elo": 1217,
"win_rate": 50.3,
"rank": 5
},
{
"arena": "agents",
"category": "webapps",
"elo": 1284,
"win_rate": 57.5,
"rank": 3
},
{
"arena": "models",
"category": "3d",
"elo": 1373,
"win_rate": 64,
"rank": 1
},
{
"arena": "models",
"category": "codecategories",
"elo": 1360,
"win_rate": 62,
"rank": 1
},
{
"arena": "models",
"category": "dataviz",
"elo": 1326,
"win_rate": 59.8,
"rank": 3
},
{
"arena": "models",
"category": "gamedev",
"elo": 1357,
"win_rate": 61.3,
"rank": 2
},
{
"arena": "models",
"category": "uicomponent",
"elo": 1339,
"win_rate": 59.8,
"rank": 5
},
{
"arena": "models",
"category": "website",
"elo": 1356,
"win_rate": 61.6,
"rank": 1
}
],
"artificial_analysis": {
"intelligence_index": 51.1,
"coding_index": 68.8,
"agentic_index": 43.1
}
},
"reasoning": {
"mandatory": false,
"default_enabled": true,
"supported_efforts": [
"xhigh",
"high"
],
"default_effort": "high"
},
"model_family": "others"
}
}