Skip to content

Self-improving AI Employees for everyone

chore: refresh model registry cache (344 -> 347 models)

trohitga76c1bf8c0bd
diff --git a/server/config/model_registry.json b/server/config/model_registry.json
index c95084a5..8d007591 100644
--- a/server/config/model_registry.json
+++ b/server/config/model_registry.json
@@ -1,8 +1,182 @@
{
- "_generated": "2026-07-09T05:58:28.184635+00:00",
+ "_generated": "2026-07-10T06:03:13.088476+00:00",
"_source": "openrouter",
- "_model_count": 344,
+ "_model_count": 347,
"models": {
+ "openai/gpt-5.6-luna-pro": {
+ "id": "openai/gpt-5.6-luna-pro",
+ "name": "OpenAI: GPT-5.6 Luna Pro",
+ "provider": "openai",
+ "local_id": "gpt-5.6-luna-pro",
+ "context_length": 1050000,
+ "max_output_tokens": 128000,
+ "input_price_per_mtok": 1.0,
+ "output_price_per_mtok": 6.0,
+ "supports_thinking": true,
+ "thinking_type": "effort",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_completion_tokens",
+ "max_tokens",
+ "reasoning",
+ "reasoning_effort",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ]
+ },
+ "openai/gpt-5.6-luna": {
+ "id": "openai/gpt-5.6-luna",
+ "name": "OpenAI: GPT-5.6 Luna",
+ "provider": "openai",
+ "local_id": "gpt-5.6-luna",
+ "context_length": 1050000,
+ "max_output_tokens": 128000,
+ "input_price_per_mtok": 1.0,
+ "output_price_per_mtok": 6.0,
+ "supports_thinking": true,
+ "thinking_type": "effort",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_completion_tokens",
+ "max_tokens",
+ "reasoning",
+ "reasoning_effort",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ]
+ },
+ "openai/gpt-5.6-terra-pro": {
+ "id": "openai/gpt-5.6-terra-pro",
+ "name": "OpenAI: GPT-5.6 Terra Pro",
+ "provider": "openai",
+ "local_id": "gpt-5.6-terra-pro",
+ "context_length": 1050000,
+ "max_output_tokens": 128000,
+ "input_price_per_mtok": 2.5,
+ "output_price_per_mtok": 15.0,
+ "supports_thinking": true,
+ "thinking_type": "effort",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_completion_tokens",
+ "max_tokens",
+ "reasoning",
+ "reasoning_effort",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ]
+ },
+ "openai/gpt-5.6-terra": {
+ "id": "openai/gpt-5.6-terra",
+ "name": "OpenAI: GPT-5.6 Terra",
+ "provider": "openai",
+ "local_id": "gpt-5.6-terra",
+ "context_length": 1050000,
+ "max_output_tokens": 128000,
+ "input_price_per_mtok": 2.5,
+ "output_price_per_mtok": 15.0,
+ "supports_thinking": true,
+ "thinking_type": "effort",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_completion_tokens",
+ "max_tokens",
+ "reasoning",
+ "reasoning_effort",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ]
+ },
+ "openai/gpt-5.6-sol-pro": {
+ "id": "openai/gpt-5.6-sol-pro",
+ "name": "OpenAI: GPT-5.6 Sol Pro",
+ "provider": "openai",
+ "local_id": "gpt-5.6-sol-pro",
+ "context_length": 1050000,
+ "max_output_tokens": 128000,
+ "input_price_per_mtok": 5.0,
+ "output_price_per_mtok": 30.0,
+ "supports_thinking": true,
+ "thinking_type": "effort",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_completion_tokens",
+ "max_tokens",
+ "reasoning",
+ "reasoning_effort",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ]
+ },
+ "openai/gpt-5.6-sol": {
+ "id": "openai/gpt-5.6-sol",
+ "name": "OpenAI: GPT-5.6 Sol",
+ "provider": "openai",
+ "local_id": "gpt-5.6-sol",
+ "context_length": 1050000,
+ "max_output_tokens": 128000,
+ "input_price_per_mtok": 5.0,
+ "output_price_per_mtok": 30.0,
+ "supports_thinking": true,
+ "thinking_type": "effort",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "include_reasoning",
+ "max_completion_tokens",
+ "max_tokens",
+ "reasoning",
+ "reasoning_effort",
+ "response_format",
+ "seed",
+ "structured_outputs",
+ "tool_choice",
+ "tools"
+ ]
+ },
"xai/grok-4.5": {
"id": "x-ai/grok-4.5",
"name": "xAI: Grok 4.5",
@@ -26,6 +200,7 @@
"max_tokens",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -60,6 +235,7 @@
"max_tokens",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -147,6 +323,7 @@
"max_tokens",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"seed",
"stop",
@@ -182,6 +359,7 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -265,6 +443,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -293,6 +472,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"temperature",
@@ -349,6 +529,7 @@
"supported_parameters": [
"include_reasoning",
"reasoning",
+ "reasoning_effort",
"structured_outputs",
"tool_choice",
"tools",
@@ -375,6 +556,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -449,9 +631,9 @@
"provider": "z-ai",
"local_id": "glm-5.2",
"context_length": 1048576,
- "max_output_tokens": 131072,
- "input_price_per_mtok": 0.84,
- "output_price_per_mtok": 2.64,
+ "max_output_tokens": 1048576,
+ "input_price_per_mtok": 0.92,
+ "output_price_per_mtok": 3.0,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -507,9 +689,9 @@
"provider": "moonshotai",
"local_id": "kimi-k2.7-code",
"context_length": 262144,
- "max_output_tokens": 16384,
- "input_price_per_mtok": 0.74,
- "output_price_per_mtok": 3.5,
+ "max_output_tokens": 262144,
+ "input_price_per_mtok": 0.72,
+ "output_price_per_mtok": 3.49,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -527,7 +709,6 @@
"parallel_tool_calls",
"presence_penalty",
"reasoning",
- "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -562,6 +743,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -591,6 +773,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -674,6 +857,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"seed",
"temperature",
"tool_choice",
@@ -705,6 +889,7 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -755,7 +940,7 @@
"provider": "minimax",
"local_id": "minimax-m3",
"context_length": 1048576,
- "max_output_tokens": 512000,
+ "max_output_tokens": 131072,
"input_price_per_mtok": 0.3,
"output_price_per_mtok": 1.2,
"supports_thinking": false,
@@ -812,6 +997,7 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -845,6 +1031,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -874,6 +1061,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -969,6 +1157,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -999,6 +1188,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -1057,6 +1247,7 @@
"max_tokens",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -1088,6 +1279,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -1152,6 +1344,7 @@
"max_tokens",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -1219,6 +1412,7 @@
"max_tokens",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -1256,56 +1450,6 @@
"top_p"
]
},
- "poolside/laguna-xs.2:free": {
- "id": "poolside/laguna-xs.2:free",
- "name": "Poolside: Laguna XS.2 (free)",
- "provider": "poolside",
- "local_id": "laguna-xs.2:free",
- "context_length": 262144,
- "max_output_tokens": 32768,
- "input_price_per_mtok": 0.0,
- "output_price_per_mtok": 0.0,
- "supports_thinking": false,
- "thinking_type": "none",
- "temperature_range": [
- 0.0,
- 2.0
- ],
- "is_reasoning_model": false,
- "supported_parameters": [
- "include_reasoning",
- "max_tokens",
- "reasoning",
- "temperature",
- "tool_choice",
- "tools"
- ]
- },
- "poolside/laguna-xs.2": {
- "id": "poolside/laguna-xs.2",
- "name": "Poolside: Laguna XS.2",
- "provider": "poolside",
- "local_id": "laguna-xs.2",
- "context_length": 262144,
- "max_output_tokens": 32768,
- "input_price_per_mtok": 0.1,
- "output_price_per_mtok": 0.2,
- "supports_thinking": false,
- "thinking_type": "none",
- "temperature_range": [
- 0.0,
- 2.0
- ],
- "is_reasoning_model": false,
- "supported_parameters": [
- "include_reasoning",
- "max_tokens",
- "reasoning",
- "temperature",
- "tool_choice",
- "tools"
- ]
- },
"poolside/laguna-m.1:free": {
"id": "poolside/laguna-m.1:free",
"name": "Poolside: Laguna M.1 (free)",
@@ -1408,6 +1552,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -1435,6 +1580,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -1452,7 +1598,7 @@
"local_id": "kimi-latest",
"context_length": 262144,
"max_output_tokens": 262144,
- "input_price_per_mtok": 0.65,
+ "input_price_per_mtok": 0.66,
"output_price_per_mtok": 3.41,
"supports_thinking": false,
"thinking_type": "none",
@@ -1504,6 +1650,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -1535,6 +1682,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -1564,6 +1712,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -1763,6 +1912,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -1791,6 +1941,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -1823,6 +1974,7 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -1861,6 +2013,7 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -1930,6 +2083,7 @@
"max_tokens",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"seed",
"stop",
"temperature",
@@ -2039,6 +2193,7 @@
"max_tokens",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -2101,6 +2256,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -2135,7 +2291,7 @@
"local_id": "kimi-k2.6",
"context_length": 262144,
"max_output_tokens": 262144,
- "input_price_per_mtok": 0.65,
+ "input_price_per_mtok": 0.66,
"output_price_per_mtok": 3.41,
"supports_thinking": false,
"thinking_type": "none",
@@ -2188,6 +2344,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -2486,6 +2643,7 @@
"logprobs",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -2648,8 +2806,8 @@
"local_id": "minimax-m2.7",
"context_length": 204800,
"max_output_tokens": 196608,
- "input_price_per_mtok": 0.18,
- "output_price_per_mtok": 0.72,
+ "input_price_per_mtok": 0.24,
+ "output_price_per_mtok": 0.96,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -2700,6 +2858,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -2728,6 +2887,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -2757,6 +2917,7 @@
"max_tokens",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -2823,6 +2984,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -2857,6 +3019,7 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -2891,6 +3054,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -2959,6 +3123,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -2987,6 +3152,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -3014,6 +3180,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -3068,6 +3235,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -3099,6 +3267,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -3128,6 +3297,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -3279,36 +3449,6 @@
"top_p"
]
},
- "liquid/lfm-2-24b-a2b": {
- "id": "liquid/lfm-2-24b-a2b",
- "name": "LiquidAI: LFM2-24B-A2B",
- "provider": "liquid",
- "local_id": "lfm-2-24b-a2b",
- "context_length": 128000,
- "max_output_tokens": 0,
- "input_price_per_mtok": 0.03,
- "output_price_per_mtok": 0.12,
- "supports_thinking": false,
- "thinking_type": "none",
- "temperature_range": [
- 0.0,
- 2.0
- ],
- "is_reasoning_model": false,
- "supported_parameters": [
- "frequency_penalty",
- "logit_bias",
- "max_tokens",
- "min_p",
- "presence_penalty",
- "repetition_penalty",
- "response_format",
- "stop",
- "temperature",
- "top_k",
- "top_p"
- ]
- },
"gemini/gemini-3.1-pro-preview-customtools": {
"id": "google/gemini-3.1-pro-preview-customtools",
"name": "Google: Gemini 3.1 Pro Preview Custom Tools",
@@ -3329,6 +3469,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -3359,6 +3500,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -3413,6 +3555,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -3444,6 +3587,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -3532,8 +3676,8 @@
"local_id": "minimax-m2.5",
"context_length": 204800,
"max_output_tokens": 196608,
- "input_price_per_mtok": 0.12,
- "output_price_per_mtok": 0.48,
+ "input_price_per_mtok": 0.15,
+ "output_price_per_mtok": 0.9,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -3551,7 +3695,6 @@
"parallel_tool_calls",
"presence_penalty",
"reasoning",
- "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -3656,6 +3799,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"stop",
"structured_outputs",
@@ -3726,6 +3870,7 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -4068,6 +4213,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -4226,6 +4372,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"stop",
@@ -4347,6 +4494,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -4375,6 +4523,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -4511,6 +4660,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -4715,8 +4865,8 @@
"local_id": "deepseek-v3.2",
"context_length": 131072,
"max_output_tokens": 64000,
- "input_price_per_mtok": 0.2288,
- "output_price_per_mtok": 0.3432,
+ "input_price_per_mtok": 0.2145,
+ "output_price_per_mtok": 0.3217,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -4892,6 +5042,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -4946,6 +5097,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -4974,6 +5126,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -5642,6 +5795,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -5809,36 +5963,6 @@
"stop"
]
},
- "gemini/gemini-2.5-flash-lite-preview-09-2025": {
- "id": "google/gemini-2.5-flash-lite-preview-09-2025",
- "name": "Google: Gemini 2.5 Flash Lite Preview 09-2025",
- "provider": "gemini",
- "local_id": "gemini-2.5-flash-lite-preview-09-2025",
- "context_length": 1048576,
- "max_output_tokens": 65535,
- "input_price_per_mtok": 0.1,
- "output_price_per_mtok": 0.4,
- "supports_thinking": true,
- "thinking_type": "budget",
- "temperature_range": [
- 0.0,
- 2.0
- ],
- "is_reasoning_model": false,
- "supported_parameters": [
- "include_reasoning",
- "max_tokens",
- "reasoning",
- "response_format",
- "seed",
- "stop",
- "structured_outputs",
- "temperature",
- "tool_choice",
- "tools",
- "top_p"
- ]
- },
"qwen/qwen3-vl-235b-a22b-thinking": {
"id": "qwen/qwen3-vl-235b-a22b-thinking",
"name": "Qwen: Qwen3 VL 235B A22B Thinking",
@@ -6544,6 +6668,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -6572,6 +6697,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -6600,6 +6726,7 @@
"max_completion_tokens",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -6628,6 +6755,7 @@
"max_tokens",
"min_p",
"reasoning",
+ "reasoning_effort",
"seed",
"stop",
"temperature",
@@ -6644,9 +6772,9 @@
"provider": "openai",
"local_id": "gpt-oss-120b",
"context_length": 131072,
- "max_output_tokens": 131072,
- "input_price_per_mtok": 0.03,
- "output_price_per_mtok": 0.15,
+ "max_output_tokens": 0,
+ "input_price_per_mtok": 0.036,
+ "output_price_per_mtok": 0.18,
"supports_thinking": true,
"thinking_type": "effort",
"temperature_range": [
@@ -6663,6 +6791,7 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -6701,6 +6830,7 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -6740,6 +6870,7 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",
@@ -7201,6 +7332,33 @@
"top_p"
]
},
+ "cognitivecomputations/dolphin-mistral-24b-venice-edition": {
+ "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition",
+ "name": "Venice: Uncensored",
+ "provider": "cognitivecomputations",
+ "local_id": "dolphin-mistral-24b-venice-edition",
+ "context_length": 128000,
+ "max_output_tokens": 8192,
+ "input_price_per_mtok": 0.2,
+ "output_price_per_mtok": 0.9,
+ "supports_thinking": false,
+ "thinking_type": "none",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "response_format",
+ "stop",
+ "temperature",
+ "top_k",
+ "top_p"
+ ]
+ },
"tencent/hunyuan-a13b-instruct": {
"id": "tencent/hunyuan-a13b-instruct",
"name": "Tencent: Hunyuan A13B Instruct",
@@ -7959,6 +8117,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -8639,6 +8798,7 @@
"include_reasoning",
"max_tokens",
"reasoning",
+ "reasoning_effort",
"response_format",
"seed",
"structured_outputs",
@@ -9424,11 +9584,11 @@
"top_p"
]
},
- "inflection/inflection-3-pi": {
- "id": "inflection/inflection-3-pi",
- "name": "Inflection: Inflection 3 Pi",
+ "inflection/inflection-3-productivity": {
+ "id": "inflection/inflection-3-productivity",
+ "name": "Inflection: Inflection 3 Productivity",
"provider": "inflection",
- "local_id": "inflection-3-pi",
+ "local_id": "inflection-3-productivity",
"context_length": 8000,
"max_output_tokens": 1024,
"input_price_per_mtok": 2.5,
@@ -9447,11 +9607,11 @@
"top_p"
]
},
- "inflection/inflection-3-productivity": {
- "id": "inflection/inflection-3-productivity",
- "name": "Inflection: Inflection 3 Productivity",
+ "inflection/inflection-3-pi": {
+ "id": "inflection/inflection-3-pi",
+ "name": "Inflection: Inflection 3 Pi",
"provider": "inflection",
- "local_id": "inflection-3-productivity",
+ "local_id": "inflection-3-pi",
"context_length": 8000,
"max_output_tokens": 1024,
"input_price_per_mtok": 2.5,
@@ -9504,15 +9664,15 @@
"top_p"
]
},
- "meta/llama-3.2-3b-instruct:free": {
- "id": "meta-llama/llama-3.2-3b-instruct:free",
- "name": "Meta: Llama 3.2 3B Instruct (free)",
+ "meta/llama-3.2-1b-instruct": {
+ "id": "meta-llama/llama-3.2-1b-instruct",
+ "name": "Meta: Llama 3.2 1B Instruct",
"provider": "meta",
- "local_id": "llama-3.2-3b-instruct:free",
+ "local_id": "llama-3.2-1b-instruct",
"context_length": 131072,
- "max_output_tokens": 0,
- "input_price_per_mtok": 0.0,
- "output_price_per_mtok": 0.0,
+ "max_output_tokens": 60000,
+ "input_price_per_mtok": 0.027,
+ "output_price_per_mtok": 0.201,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -9522,23 +9682,27 @@
"is_reasoning_model": false,
"supported_parameters": [
"frequency_penalty",
+ "logit_bias",
"max_tokens",
+ "min_p",
"presence_penalty",
+ "repetition_penalty",
+ "seed",
"stop",
"temperature",
"top_k",
"top_p"
]
},
- "meta/llama-3.2-3b-instruct": {
- "id": "meta-llama/llama-3.2-3b-instruct",
- "name": "Meta: Llama 3.2 3B Instruct",
+ "meta/llama-3.2-11b-vision-instruct": {
+ "id": "meta-llama/llama-3.2-11b-vision-instruct",
+ "name": "Meta: Llama 3.2 11B Vision Instruct",
"provider": "meta",
- "local_id": "llama-3.2-3b-instruct",
+ "local_id": "llama-3.2-11b-vision-instruct",
"context_length": 131072,
- "max_output_tokens": 131072,
- "input_price_per_mtok": 0.05,
- "output_price_per_mtok": 0.33,
+ "max_output_tokens": 16384,
+ "input_price_per_mtok": 0.345,
+ "output_price_per_mtok": 0.345,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -9549,29 +9713,27 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
- "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"repetition_penalty",
+ "response_format",
"seed",
"stop",
- "structured_outputs",
"temperature",
"top_k",
- "top_logprobs",
"top_p"
]
},
- "meta/llama-3.2-1b-instruct": {
- "id": "meta-llama/llama-3.2-1b-instruct",
- "name": "Meta: Llama 3.2 1B Instruct",
+ "meta/llama-3.2-3b-instruct:free": {
+ "id": "meta-llama/llama-3.2-3b-instruct:free",
+ "name": "Meta: Llama 3.2 3B Instruct (free)",
"provider": "meta",
- "local_id": "llama-3.2-1b-instruct",
+ "local_id": "llama-3.2-3b-instruct:free",
"context_length": 131072,
- "max_output_tokens": 60000,
- "input_price_per_mtok": 0.027,
- "output_price_per_mtok": 0.201,
+ "max_output_tokens": 0,
+ "input_price_per_mtok": 0.0,
+ "output_price_per_mtok": 0.0,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -9581,27 +9743,23 @@
"is_reasoning_model": false,
"supported_parameters": [
"frequency_penalty",
- "logit_bias",
"max_tokens",
- "min_p",
"presence_penalty",
- "repetition_penalty",
- "seed",
"stop",
"temperature",
"top_k",
"top_p"
]
},
- "meta/llama-3.2-11b-vision-instruct": {
- "id": "meta-llama/llama-3.2-11b-vision-instruct",
- "name": "Meta: Llama 3.2 11B Vision Instruct",
+ "meta/llama-3.2-3b-instruct": {
+ "id": "meta-llama/llama-3.2-3b-instruct",
+ "name": "Meta: Llama 3.2 3B Instruct",
"provider": "meta",
- "local_id": "llama-3.2-11b-vision-instruct",
+ "local_id": "llama-3.2-3b-instruct",
"context_length": 131072,
- "max_output_tokens": 16384,
- "input_price_per_mtok": 0.345,
- "output_price_per_mtok": 0.345,
+ "max_output_tokens": 131072,
+ "input_price_per_mtok": 0.05,
+ "output_price_per_mtok": 0.33,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -9612,15 +9770,17 @@
"supported_parameters": [
"frequency_penalty",
"logit_bias",
+ "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
"repetition_penalty",
- "response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"top_k",
+ "top_logprobs",
"top_p"
]
},
@@ -10458,6 +10618,7 @@
"min_p",
"presence_penalty",
"reasoning",
+ "reasoning_effort",
"repetition_penalty",
"response_format",
"seed",