Skip to content

Instantly share code, notes, and snippets.

@Coldaine

Coldaine/_ModelLibrary.json

Last active September 16, 2025 00:02
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save Coldaine/990cf48d61b25e55f81a577fd72b855e to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save Coldaine/990cf48d61b25e55f81a577fd72b855e to your computer and use it in GitHub Desktop.
Download ZIP
Recovered _ModelLibrary.json model configurations from consensus-async branch
Raw
_ModelLibrary.json
```json
{
"providers": {
"openai": {
"upstream_provider": "openai",
"models": {
"gpt-5": {
"model_id": "gpt-5",
"aliases": [
"openai:gpt-5",
"openrouter:openai/gpt-5"
],
"status": "available",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 400000,
"max_output_tokens": 128000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high",
"minimal"
],
"budget_tokens_range": [
0,
128000
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"openai": {
"reasoning_effort": [
"low",
"medium",
"high",
"minimal"
]
},
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": "int"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 1.25,
"output_per_million": 10.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 480
},
"endpoints": {
"base": "https://api.openai.com/v1",
"path": "/chat/completions",
"notes": "Supports reasoning_effort and verbosity parameters"
},
"notes": "Released August 2025, 3x larger context than GPT-4o, includes reasoning capabilities"
},
"gpt-5-mini": {
"model_id": "gpt-5-mini",
"aliases": [
"openai:gpt-5-mini",
"openrouter:openai/gpt-5-mini"
],
"status": "available",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 400000,
"max_output_tokens": 128000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high",
"minimal"
],
"budget_tokens_range": [
0,
128000
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"openai": {
"reasoning_effort": [
"low",
"medium",
"high",
"minimal"
]
},
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": "int"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.25,
"output_per_million": 2.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 480
},
"endpoints": {
"base": "https://api.openai.com/v1",
"path": "/chat/completions",
"notes": "Faster, cheaper version of GPT-5"
},
"notes": "Cost-effective version with reasoning support"
},
"gpt-5-nano": {
"model_id": "gpt-5-nano",
"aliases": [
"openai:gpt-5-nano"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 128000,
"max_output_tokens": 128000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"minimal",
"low",
"high"
],
"budget_tokens_range": [
0,
128000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "minimal"
},
"provider_params": {
"openai": {
"reasoning_effort": [
"minimal",
"low",
"high"
]
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.05,
"output_per_million": 0.4,
"currency": "USD"
},
"rate_limits": {
"tier": null,
"requests_per_minute": null
},
"endpoints": {
"base": "https://api.openai.com",
"path": "/v1/chat/completions",
"notes": "Smallest GPT-5 variant, minimal reasoning default"
},
"notes": "Ultra-lightweight version, mostly text modality"
},
"o3-pro": {
"model_id": "o3-pro",
"aliases": [
"openrouter:openai/o3-pro"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 400000,
"max_output_tokens": 128000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high"
],
"budget_tokens_range": [
0,
128000
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "medium"
},
"provider_params": {
"openai": {
"reasoning_effort": [
"low",
"medium",
"high"
]
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 1.25,
"output_per_million": 10.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 240
},
"endpoints": {
"base": "https://api.openai.com/v1",
"path": "/chat/completions",
"notes": "Extended reasoning model with visible thinking"
},
"notes": "Premium reasoning model from April 2025"
}
}
},
"anthropic": {
"upstream_provider": "anthropic",
"models": {
"claude-4.1-opus-20250804": {
"model_id": "claude-4.1-opus-20250804",
"aliases": [
"anthropic:claude-4.1-opus",
"openrouter:anthropic/claude-4.1-opus"
],
"status": "available",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 200000,
"max_output_tokens": 32000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
32000
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "enabled"
},
"provider_params": {
"anthropic": {
"thinking": {
"type": [
"enabled",
"disabled"
],
"budget_tokens": "int"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 15.0,
"output_per_million": 75.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 100
},
"endpoints": {
"base": "https://api.anthropic.com",
"path": "/v1/messages",
"notes": "Supports thinking parameter and tool use"
},
"notes": "Released August 2025, 74.5% on SWE-bench, world's best coding model"
},
"claude-4-sonnet-20250522": {
"model_id": "claude-4-sonnet-20250522",
"aliases": [
"anthropic:claude-4-sonnet",
"openrouter:anthropic/claude-4-sonnet"
],
"status": "available",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 1000000,
"max_output_tokens": 32000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
32000
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "enabled"
},
"provider_params": {
"anthropic": {
"thinking": {
"type": [
"enabled",
"disabled"
],
"budget_tokens": "int"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 3.0,
"output_per_million": 15.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 150
},
"endpoints": {
"base": "https://api.anthropic.com",
"path": "/v1/messages",
"notes": "1M context for prompts >200K tokens incurs higher pricing"
},
"notes": "1M token context window, long context pricing >200K tokens"
}
}
},
"google": {
"upstream_provider": "google",
"models": {
"gemini-2.5-pro": {
"model_id": "gemini-2.5-pro",
"aliases": [
"google:gemini-2.5-pro",
"openrouter:google/gemini-2.5-pro"
],
"status": "available",
"modalities": [
"text",
"vision",
"audio",
"tool_use"
],
"context_window_tokens": 2000000,
"max_output_tokens": 65535,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
65535
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"google": {
"thinkingConfig": {
"thinkingBudget": "int",
"includeThoughts": "bool"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 1.25,
"output_per_million": 10.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 360
},
"endpoints": {
"base": "https://generativelanguage.googleapis.com/v1beta",
"path": "/models/gemini-2.5-pro:generateContent",
"notes": "Pricing increases for prompts >200K tokens"
},
"notes": "Thinking tokens included in output pricing, March 2025 release"
},
"gemini-2.5-flash": {
"model_id": "gemini-2.5-flash",
"aliases": [
"google:gemini-2.5-flash",
"openrouter:google/gemini-2.5-flash"
],
"status": "available",
"modalities": [
"text",
"vision",
"audio",
"tool_use"
],
"context_window_tokens": 1048576,
"max_output_tokens": 65535,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
8192
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"google": {
"thinkingConfig": {
"thinkingBudget": "int",
"includeThoughts": "bool"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 0.1,
"output_per_million": 0.4,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 1000
},
"endpoints": {
"base": "https://generativelanguage.googleapis.com/v1beta",
"path": "/models/gemini-2.5-flash:generateContent",
"notes": "Fast inference, cost-optimized"
},
"notes": "High-speed model for cost-sensitive workloads"
}
}
},
"moonshot": {
"upstream_provider": "moonshot",
"models": {
"kimi-k2-instruct-0905": {
"model_id": "kimi-k2-instruct-0905",
"aliases": [
"moonshot:kimi-k2",
"openrouter:moonshotai/kimi-k2-instruct"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 256000,
"max_output_tokens": 16384,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
16384
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "auto"
},
"provider_params": {
"moonshot": {
"variant_model": "kimi-thinking-preview"
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 1.0,
"output_per_million": 3.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 200
},
"endpoints": {
"base": "https://api.moonshot.cn/v1",
"path": "/chat/completions",
"notes": "MoE with 1T total params, 32B active"
},
"notes": "September 2025, open-source with modified MIT license, 1T parameters"
},
"kimi-thinking-preview": {
"model_id": "kimi-thinking-preview",
"aliases": [
"moonshot:kimi-thinking-preview"
],
"status": "preview",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 128000,
"max_output_tokens": null,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
128000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"moonshot": {
"variant_model": "kimi-thinking-preview"
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": null,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.15,
"output_per_million": 2.5,
"currency": "USD"
},
"rate_limits": {
"tier": null,
"requests_per_minute": null
},
"endpoints": {
"base": "https://api.moonshot.cn",
"path": "/v1/chat/completions",
"notes": "Thinking inherent to model, step-by-step reasoning"
},
"notes": "16B total, 2.8B active via MoE, multimodal reasoning"
}
}
},
"z_ai": {
"upstream_provider": "z_ai",
"models": {
"glm-4.5": {
"model_id": "glm-4.5",
"aliases": [
"z.ai:glm-4.5"
],
"status": "available",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 128000,
"max_output_tokens": 4096,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"z_ai": {
"thinking": {
"type": [
"enabled",
"disabled"
]
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": null,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.6,
"output_per_million": 2.2,
"currency": "USD"
},
"rate_limits": {
"tier": null,
"requests_per_minute": null
},
"endpoints": {
"base": "https://api.z.ai",
"path": "/api/paas/v4/chat/completions",
"notes": "Dynamic thinking enabled by default"
},
"notes": "355B params, 32B active via MoE, thinking dynamic"
},
"glm-4.5-air": {
"model_id": "glm-4.5-air",
"aliases": [
"z.ai:glm-4.5-air"
],
"status": "available",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 128000,
"max_output_tokens": 4096,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"z_ai": {
"thinking": {
"type": [
"enabled",
"disabled"
]
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": null,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.2,
"output_per_million": 1.1,
"currency": "USD"
},
"rate_limits": {
"tier": null,
"requests_per_minute": null
},
"endpoints": {
"base": "https://api.z.ai",
"path": "/api/paas/v4/chat/completions",
"notes": "Lightweight version with dynamic thinking"
},
"notes": "106B total, 12B active via MoE, optimized for speed"
}
}
},
"other": {
"upstream_provider": "other",
"models": {
"grok-4-0709": {
"model_id": "grok-4-0709",
"aliases": [
"xai:grok-4",
"openrouter:xai/grok-4"
],
"status": "available",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 256000,
"max_output_tokens": 128000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
128000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "enabled"
},
"provider_params": {
"x_ai": {
"reasoning_mode": "always_on"
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": null,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 3.0,
"output_per_million": 15.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 480
},
"endpoints": {
"base": "https://api.x.ai/v1",
"path": "/chat/completions",
"notes": "Reasoning always enabled, no effort parameter"
},
"notes": "Released July 2025, reasoning-only model, no non-reasoning mode"
},
"grok-3": {
"model_id": "grok-3",
"aliases": [
"xai:grok-3",
"openrouter:xai/grok-3"
],
"status": "available",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 131072,
"max_output_tokens": 65536,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": null,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 1.0,
"output_per_million": 5.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 600
},
"endpoints": {
"base": "https://api.x.ai/v1",
"path": "/chat/completions",
"notes": "Standard model, supports presence/frequency penalties"
},
"notes": "February 2025 release, 10x more compute than Grok-2"
},
"qwen3-max-preview": {
"model_id": "qwen3-max-preview",
"aliases": [
"alibaba:qwen3-max",
"openrouter:qwen/qwen3-max"
],
"status": "preview",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 65535,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
65535
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 1.2,
"output_per_million": 6.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 100
},
"endpoints": {
"base": "https://dashscope.aliyuncs.com/api/v1",
"path": "/services/aigc/text-generation/generation",
"notes": "Tiered pricing based on input length"
},
"notes": "September 2025, trillion-parameter flagship model, preview access only"
},
"llama-4-scout": {
"model_id": "llama-4-scout",
"aliases": [
"meta:llama-4-scout",
"openrouter:meta-llama/llama-4-scout"
],
"status": "available",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 10000000,
"max_output_tokens": 128000,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 0.5,
"output_per_million": 2.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 300
},
"endpoints": {
"base": "https://api.llama.com/v1",
"path": "/chat/completions",
"notes": "17B active params, 16 experts, 10M context"
},
"notes": "April 2025, complete architectural overhaul, 10M context window"
},
"deepseek-r1-0528": {
"model_id": "deepseek-r1-0528",
"aliases": [
"deepseek:deepseek-r1",
"openrouter:deepseek/deepseek-r1"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 128000,
"max_output_tokens": 32000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
32000
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.3,
"output_per_million": 1.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 200
},
"endpoints": {
"base": "https://api.deepseek.com/v1",
"path": "/chat/completions",
"notes": "Hybrid reasoning architecture"
},
"notes": "May 2025, enhanced reasoning with thinking/non-thinking modes"
},
"mistral-medium-3": {
"model_id": "mistral-medium-3",
"aliases": [
"mistral:mistral-medium-3",
"openrouter:mistralai/mistral-medium-3"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 128000,
"max_output_tokens": 32000,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 2.0,
"output_per_million": 8.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 150
},
"endpoints": {
"base": "https://api.mistral.ai/v1",
"path": "/chat/completions",
"notes": "8x lower cost than previous generation"
},
"notes": "January 2025, 'Medium is the new large', significant cost reduction"
},
"command-a-03-2025": {
"model_id": "command-a-03-2025",
"aliases": [
"cohere:command-a",
"openrouter:cohere/command-a"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 256000,
"max_output_tokens": 32000,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 3.0,
"output_per_million": 12.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 100
},
"endpoints": {
"base": "https://api.cohere.ai/v1",
"path": "/chat",
"notes": "Most performant Cohere model"
},
"notes": "March 2025, 256K context window, most capable Cohere model"
},
"qwen3-max": {
"model_id": "qwen/qwen3-max",
"aliases": [
"openrouter:qwen/qwen3-max",
"kilo:qwen/qwen3-max"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 256000,
"max_output_tokens": 32768,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 1.2,
"output_per_million": 6.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 50
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Use model slug 'qwen/qwen3-max'. Do not include reasoning object — it will be ignored or cause error."
},
"notes": "Highest-performing non-thinking Qwen3 variant. Dense/MoE hybrid architecture. No thinking mode support. Context window matches other Qwen3-Next models. Pricing as of Sep 12, 2025."
},
"qwen3-235b-a22b-thinking-2507": {
"model_id": "qwen/qwen3-235b-a22b-thinking-2507",
"aliases": [
"openrouter:qwen/qwen3-235b-a22b-thinking-2507",
"kilo:qwen/qwen3-235b-a22b-thinking-2507"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 32768,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high"
],
"budget_tokens_range": [
1024,
32000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "high"
},
"provider_params": {
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": "int",
"exclude": "boolean"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 2.5,
"output_per_million": 12.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 50
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Thinking-only model. Use 'exclude':true in reasoning to hide trace. Higher cost than standard Qwen3 variants."
},
"notes": "MoE model activating ~22B parameters of 235B total. Released Sep 11, 2025. Explicit reasoning, step-by-step trace vs final answers."
},
"qwen3-30b-a3b-thinking-2507": {
"model_id": "qwen/qwen3-30b-a3b-thinking-2507",
"aliases": [
"openrouter:qwen/qwen3-30b-a3b-thinking-2507",
"kilo:qwen/qwen3-30b-a3b-thinking-2507"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 32768,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high"
],
"budget_tokens_range": [
1024,
32000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "high"
},
"provider_params": {
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": "int",
"exclude": "boolean"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 1.8,
"output_per_million": 9.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 50
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Thinking-only model. Use 'exclude':true in reasoning to hide trace. 30B parameters, MoE activating 3B approx."
},
"notes": "Released Sep 11, 2025. Thinking mode only. Explicit reasoning, step-by-step trace vs final answers."
},
"qwen3-30b-a3b:free": {
"model_id": "qwen/qwen3-30b-a3b:free",
"aliases": [
"openrouter:qwen/qwen3-30b-a3b:free",
"kilo:qwen/qwen3-30b-a3b:free"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 40960,
"max_output_tokens": 32768,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high"
],
"budget_tokens_range": [
1024,
32000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "high"
},
"provider_params": {
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": "int",
"exclude": "boolean"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0,
"output_per_million": 0,
"currency": "USD"
},
"rate_limits": {
"tier": "free",
"requests_per_minute": 100
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Dual-mode model. Free variant has smaller context window (40,960 tokens)."
},
"notes": "30B parameters, MoE activating 3B approx. Free tier with dual-mode support for thinking and non-thinking."
},
"qwen3-8b:free": {
"model_id": "qwen/qwen3-8b:free",
"aliases": [
"openrouter:qwen/qwen3-8b:free",
"kilo:qwen/qwen3-8b:free"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 40960,
"max_output_tokens": 32768,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high"
],
"budget_tokens_range": [
1024,
32000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "high"
},
"provider_params": {
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": "int",
"exclude": "boolean"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0,
"output_per_million": 0,
"currency": "USD"
},
"rate_limits": {
"tier": "free",
"requests_per_minute": 100
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Dual-mode model. Free variant has smaller context window (40,960 tokens)."
},
"notes": "Dense 8.2B parameters. Free tier with dual-mode support for thinking and non-thinking."
},
"qwen3-32b": {
"model_id": "qwen/qwen3-32b",
"aliases": [
"openrouter:qwen/qwen3-32b",
"kilo:qwen/qwen3-32b"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 131072,
"max_output_tokens": 32768,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high"
],
"budget_tokens_range": [
1024,
32000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "high"
},
"provider_params": {
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": "int",
"exclude": "boolean"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 1.5,
"output_per_million": 7.5,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 50
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Dual-mode model. Likely paid beyond free tier."
},
"notes": "Dense 32.8B parameters. Context window ~131,072 tokens. Free status may be limited."
},
"qwen3-next-80b-a3b-thinking": {
"model_id": "qwen/qwen3-next-80b-a3b-thinking",
"aliases": [
"openrouter:qwen/qwen3-next-80b-a3b-thinking",
"kilo:qwen/qwen3-next-80b-a3b-thinking"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 32768,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high"
],
"budget_tokens_range": [
1024,
32000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "high"
},
"provider_params": {
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": "int",
"exclude": "boolean"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 1.8,
"output_per_million": 9.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 50
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Thinking-only model. Use 'exclude':true in reasoning to hide trace."
},
"notes": "Released Sep 11, 2025. Qwen3-Next-80B-A3B thinking variant. Context window matches other Qwen3-Next models."
},
"qwen3-next-80b-a3b-instruct": {
"model_id": "qwen/qwen3-next-80b-a3b-instruct",
"aliases": [
"openrouter:qwen/qwen3-next-80b-a3b-instruct",
"kilo:qwen/qwen3-next-80b-a3b-instruct"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 32768,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 1.5,
"output_per_million": 7.5,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 50
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Non-thinking variant. Do not include reasoning object — it will be ignored or cause error."
},
"notes": "Released Sep 11, 2025. Qwen3-Next-80B-A3B instruct variant. Context window matches other Qwen3-Next models."
},
"qwen3-235b-a22b-instruct-2507": {
"model_id": "qwen/qwen3-235b-a22b-instruct-2507",
"aliases": [
"openrouter:qwen/qwen3-235b-a22b-instruct-2507",
"kilo:qwen/qwen3-235b-a22b-instruct-2507"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 32768,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 2.2,
"output_per_million": 11.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 50
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Non-thinking variant. Do not include reasoning object — it will be ignored or cause error."
},
"notes": "MoE model activating ~22B parameters of 235B total. Non-thinking variant of the 235B model."
},
"qwen3-30b-a3b-instruct-2507": {
"model_id": "qwen/qwen3-30b-a3b-instruct-2507",
"aliases": [
"openrouter:qwen/qwen3-30b-a3b-instruct-2507",
"kilo:qwen/qwen3-30b-a3b-instruct-2507"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 32768,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 1.5,
"output_per_million": 7.5,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 50
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Non-thinking variant. Do not include reasoning object — it will be ignored or cause error."
},
"notes": "30B parameters, MoE activating 3B approx. Non-thinking variant of the 30B model."
},
"qwen3-1.7b": {
"model_id": "qwen/qwen3-1.7b",
"aliases": [
"openrouter:qwen/qwen3-1.7b",
"kilo:qwen/qwen3-1.7b"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 32768,
"max_output_tokens": 32768,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high"
],
"budget_tokens_range": [
512,
16000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "high"
},
"provider_params": {
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": "int",
"exclude": "boolean"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.5,
"output_per_million": 2.5,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 100
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Small model. Dual-mode support for thinking and non-thinking."
},
"notes": "1.7B parameter model. Lower cost option with dual-mode capabilities."
},
"qwen3-0.6b-04-28:free": {
"model_id": "qwen/qwen3-0.6b-04-28:free",
"aliases": [
"openrouter:qwen/qwen3-0.6b-04-28:free",
"kilo:qwen/qwen3-0.6b-04-28:free"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 16384,
"max_output_tokens": 32768,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high"
],
"budget_tokens_range": [
256,
8000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "high"
},
"provider_params": {
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": "int",
"exclude": "boolean"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0,
"output_per_million": 0,
"currency": "USD"
},
"rate_limits": {
"tier": "free",
"requests_per_minute": 100
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Very small model. Free variant with dual-mode support."
},
"notes": "0.6B parameter model. Free tier with dual-mode capabilities. Smallest context window among Qwen3 variants."
},
"qwen3-coder": {
"model_id": "qwen/qwen3-coder",
"aliases": [
"openrouter:qwen/qwen3-coder",
"kilo:qwen/qwen3-coder"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 131072,
"max_output_tokens": 32768,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high"
],
"budget_tokens_range": [
1024,
32000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "high"
},
"provider_params": {
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": "int",
"exclude": "boolean"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 1.7,
"output_per_million": 8.5,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": 50
},
"endpoints": {
"base": "https://api.kilocodex.com/v1",
"path": "/chat/completions",
"notes": "Kilo Code forwards to OpenRouter. Coder-specific variant. Dual-mode support for thinking and non-thinking."
},
"notes": "Also known as 480B-A35B Instruct. Optimized for code generation tasks with dual-mode capabilities."
},
"grok-code-fast-1": {
"model_id": "x-ai/grok-code-fast-1",
"aliases": [
"openrouter:x-ai/grok-code-fast-1",
"grok-code-fast-1"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 128000,
"max_output_tokens": 32000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [
"low",
"medium",
"high"
],
"budget_tokens_range": [
1000,
64000
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "medium"
},
"provider_params": {
"openrouter": {
"reasoning": {
"effort": [
"low",
"medium",
"high"
],
"max_tokens": 32000
}
},
"other": {
"reasoning_effort": [
"low",
"medium",
"high"
]
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 3.0,
"output_per_million": 15.0,
"currency": "USD"
},
"rate_limits": {
"tier": "premium",
"requests_per_minute": 480
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "supports reasoning parameter, cached inputs at $0.75/1M"
},
"notes": "Fast agentic coding model with visible reasoning traces, leads OpenRouter usage for coding tasks"
}
}
}
}
}
```
[
{
"provider": "other",
"upstream_provider": "other",
"model_id": "sonoma-sky-alpha",
"aliases": [
"openrouter:sonoma-sky-alpha"
],
"status": "available",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 2000000,
"max_output_tokens": 2000000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
2000000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "enabled"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0,
"output_per_million": 0,
"currency": "USD"
},
"rate_limits": {
"tier": "free",
"requests_per_minute": null
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "Free during alpha period, prompts and completions logged"
},
"notes": "Maximally intelligent general-purpose frontier model, likely Grok 4.2 based on community analysis"
},
{
"provider": "other",
"upstream_provider": "other",
"model_id": "sonoma-dusk-alpha",
"aliases": [
"openrouter:sonoma-dusk-alpha"
],
"status": "available",
"modalities": [
"text",
"vision",
"tool_use"
],
"context_window_tokens": 2000000,
"max_output_tokens": 2000000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
2000000
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "enabled"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0,
"output_per_million": 0,
"currency": "USD"
},
"rate_limits": {
"tier": "free",
"requests_per_minute": null
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "Free during alpha period, prompts and completions logged"
},
"notes": "Fast and intelligent general-purpose frontier model, likely Grok 4.2 mini variant"
},
{
"provider": "other",
"upstream_provider": "alibaba",
"model_id": "qwen3-235b-a22b-thinking-2507",
"aliases": [
"qwen:qwen3-235b-a22b-thinking-2507",
"openrouter:qwen/qwen3-235b-a22b-thinking-2507"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 262144,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
262144
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "enabled"
},
"provider_params": {
"qwen": {
"thinking": {
"type": "enabled"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.098,
"output_per_million": 0.39,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": null
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "Thinking-only mode, cannot disable thinking"
},
"notes": "High-performance MoE model with 235B total parameters, 22B active, optimized for complex reasoning"
},
{
"provider": "other",
"upstream_provider": "alibaba",
"model_id": "qwen3-next-80b-a3b-thinking",
"aliases": [
"qwen:qwen3-next-80b-a3b-thinking",
"openrouter:qwen/qwen3-next-80b-a3b-thinking"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 262144,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
262144
],
"dynamic_budget_supported": false,
"include_thoughts_supported": true,
"default_mode": "enabled"
},
"provider_params": {
"qwen": {
"thinking": {
"type": "enabled"
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.14,
"output_per_million": 1.4,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": null
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "Thinking-only mode, designed for hard multi-step problems"
},
"notes": "Designed for math proofs, code synthesis/debugging, logic, and agentic planning"
},
{
"provider": "other",
"upstream_provider": "alibaba",
"model_id": "qwen3-next-80b-a3b-instruct",
"aliases": [
"qwen:qwen3-next-80b-a3b-instruct",
"openrouter:qwen/qwen3-next-80b-a3b-instruct"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 262144,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 0.14,
"output_per_million": 1.4,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": null
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "Non-thinking mode only, optimized for fast stable responses"
},
"notes": "Optimized for fast, stable responses without thinking traces"
},
{
"provider": "other",
"upstream_provider": "alibaba",
"model_id": "qwen3-30b-a3b-instruct-2507",
"aliases": [
"qwen:qwen3-30b-a3b-instruct-2507",
"openrouter:qwen/qwen3-30b-a3b-instruct-2507"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 262144,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 0.071,
"output_per_million": 0.283,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": null
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "Non-thinking mode only, 30.5B total parameters, 3.3B active"
},
"notes": "30.5B-parameter MoE model with 3.3B active parameters, non-thinking mode only"
},
{
"provider": "other",
"upstream_provider": "alibaba",
"model_id": "qwen3-30b-a3b",
"aliases": [
"qwen:qwen3-30b-a3b",
"openrouter:qwen/qwen3-30b-a3b"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 131072,
"max_output_tokens": 131072,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
131072
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"qwen": {
"thinking": {
"type": [
"enabled",
"disabled"
]
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.036,
"output_per_million": 0.144,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": null
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "Hybrid model supporting both thinking and non-thinking modes"
},
"notes": "30.5B total parameters, 3.3B active, can switch between thinking and non-thinking modes"
},
{
"provider": "other",
"upstream_provider": "alibaba",
"model_id": "qwen3-8b",
"aliases": [
"qwen:qwen3-8b",
"openrouter:qwen/qwen3-8b"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 128000,
"max_output_tokens": 20000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
20000
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"qwen": {
"thinking": {
"type": [
"enabled",
"disabled"
]
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.035,
"output_per_million": 0.138,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": null
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "Dense 8.2B parameter model with hybrid thinking capabilities"
},
"notes": "8.2B dense parameters, 32K native context extendable to 131K with YaRN"
},
{
"provider": "other",
"upstream_provider": "alibaba",
"model_id": "qwen3-4b",
"aliases": [
"qwen:qwen3-4b",
"openrouter:qwen/qwen3-4b:free"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 40960,
"max_output_tokens": 40960,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
40960
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"qwen": {
"thinking": {
"type": [
"enabled",
"disabled"
]
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0,
"output_per_million": 0,
"currency": "USD"
},
"rate_limits": {
"tier": "free",
"requests_per_minute": null
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "Free version available, dual-mode architecture"
},
"notes": "4B dense parameters with dual-mode architecture for thinking and non-thinking"
},
{
"provider": "other",
"upstream_provider": "alibaba",
"model_id": "qwen3-coder-480b-a35b-instruct",
"aliases": [
"qwen:qwen3-coder-480b-a35b-instruct",
"openrouter:qwen/qwen3-coder"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 262144,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 0.25,
"output_per_million": 1.0,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": null
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "Optimized for agentic coding tasks, pricing varies by context length"
},
"notes": "480B total parameters, 35B active, optimized for agentic coding tasks"
},
{
"provider": "other",
"upstream_provider": "alibaba",
"model_id": "qwen3-coder-30b-a3b-instruct",
"aliases": [
"qwen:qwen3-coder-30b-a3b-instruct",
"openrouter:qwen/qwen3-coder-30b-a3b-instruct"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 262144,
"max_output_tokens": 262144,
"thinking": {
"supported": false,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
0
],
"dynamic_budget_supported": false,
"include_thoughts_supported": false,
"default_mode": "off"
},
"provider_params": {}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": true,
"cot_visible_to_user_by_default": false
},
"pricing": {
"input_per_million": 0.071,
"output_per_million": 0.283,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": null
},
"endpoints": {
"base": "https://openrouter.ai/api/v1",
"path": "/chat/completions",
"notes": "256K native context extendable to 1M with Yarn"
},
"notes": "30.5B parameter MoE with 128 experts (8 active), optimized for coding"
},
{
"provider": "other",
"upstream_provider": "z.ai",
"model_id": "glm-4.5",
"aliases": [
"glm-4.5"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 128000,
"max_output_tokens": 128000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
128000
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"z.ai": {
"thinking": {
"type": [
"enabled",
"disabled"
]
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.6,
"output_per_million": 2.2,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": null
},
"endpoints": {
"base": "https://api.z.ai/api/paas/v4/",
"path": "/chat/completions",
"notes": "Hybrid reasoning model with thinking and non-thinking modes"
},
"notes": "355B total parameters, 32B active, purpose-built for agent-oriented applications"
},
{
"provider": "other",
"upstream_provider": "z.ai",
"model_id": "glm-4.5-air",
"aliases": [
"glm-4.5-air"
],
"status": "available",
"modalities": [
"text",
"tool_use"
],
"context_window_tokens": 128000,
"max_output_tokens": 128000,
"thinking": {
"supported": true,
"controls": {
"effort_levels": [],
"budget_tokens_range": [
0,
128000
],
"dynamic_budget_supported": true,
"include_thoughts_supported": true,
"default_mode": "auto"
},
"provider_params": {
"z.ai": {
"thinking": {
"type": [
"enabled",
"disabled"
]
}
}
}
},
"tool_calling": {
"supported": true,
"json_schema_outputs": true
},
"safety": {
"stores_inputs_by_default": false,
"cot_visible_to_user_by_default": true
},
"pricing": {
"input_per_million": 0.2,
"output_per_million": 1.1,
"currency": "USD"
},
"rate_limits": {
"tier": "paid",
"requests_per_minute": null
},
"endpoints": {
"base": "https://api.z.ai/api/paas/v4/",
"path": "/chat/completions",
"notes": "Lightweight variant with same dual-mode capabilities"
},
"notes": "106B total parameters, 12B active, more compact design with same capabilities"
}
]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment