ionet.json

  1{
  2  "name": "io.net",
  3  "id": "ionet",
  4  "api_key": "$IONET_API_KEY",
  5  "api_endpoint": "https://api.intelligence.io.solutions/api/v1",
  6  "type": "openai-compat",
  7  "default_large_model_id": "zai-org/GLM-4.7",
  8  "default_small_model_id": "zai-org/GLM-4.7-Flash",
  9  "models": [
 10    {
 11      "id": "zai-org/GLM-4.6",
 12      "name": "GLM 4.6",
 13      "cost_per_1m_in": 0.35,
 14      "cost_per_1m_out": 1.5,
 15      "cost_per_1m_in_cached": 0.175,
 16      "cost_per_1m_out_cached": 0.7,
 17      "context_window": 200000,
 18      "default_max_tokens": 20000,
 19      "can_reason": true,
 20      "reasoning_levels": [
 21        "low",
 22        "medium",
 23        "high"
 24      ],
 25      "default_reasoning_effort": "medium",
 26      "supports_attachments": false,
 27      "options": {}
 28    },
 29    {
 30      "id": "zai-org/GLM-4.7",
 31      "name": "GLM 4.7",
 32      "cost_per_1m_in": 0.33,
 33      "cost_per_1m_out": 1.54,
 34      "cost_per_1m_in_cached": 0.165,
 35      "cost_per_1m_out_cached": 0.66,
 36      "context_window": 200000,
 37      "default_max_tokens": 20000,
 38      "can_reason": true,
 39      "reasoning_levels": [
 40        "low",
 41        "medium",
 42        "high"
 43      ],
 44      "default_reasoning_effort": "medium",
 45      "supports_attachments": false,
 46      "options": {}
 47    },
 48    {
 49      "id": "zai-org/GLM-4.7-Flash",
 50      "name": "GLM 4.7 Flash",
 51      "cost_per_1m_in": 0.07,
 52      "cost_per_1m_out": 0.39999999999999997,
 53      "cost_per_1m_in_cached": 0.035,
 54      "cost_per_1m_out_cached": 0.14,
 55      "context_window": 200000,
 56      "default_max_tokens": 20000,
 57      "can_reason": true,
 58      "reasoning_levels": [
 59        "low",
 60        "medium",
 61        "high"
 62      ],
 63      "default_reasoning_effort": "medium",
 64      "supports_attachments": false,
 65      "options": {}
 66    },
 67    {
 68      "id": "moonshotai/Kimi-K2-Instruct-0905",
 69      "name": "Kimi K2 Instruct 0905",
 70      "cost_per_1m_in": 0.39,
 71      "cost_per_1m_out": 1.9,
 72      "cost_per_1m_in_cached": 0.195,
 73      "cost_per_1m_out_cached": 0.78,
 74      "context_window": 262144,
 75      "default_max_tokens": 26214,
 76      "can_reason": false,
 77      "supports_attachments": false,
 78      "options": {}
 79    },
 80    {
 81      "id": "moonshotai/Kimi-K2-Thinking",
 82      "name": "Kimi K2 Thinking",
 83      "cost_per_1m_in": 0.32,
 84      "cost_per_1m_out": 0.48,
 85      "cost_per_1m_in_cached": 0.16,
 86      "cost_per_1m_out_cached": 0.64,
 87      "context_window": 262144,
 88      "default_max_tokens": 26214,
 89      "can_reason": true,
 90      "reasoning_levels": [
 91        "low",
 92        "medium",
 93        "high"
 94      ],
 95      "default_reasoning_effort": "medium",
 96      "supports_attachments": false,
 97      "options": {}
 98    },
 99    {
100      "id": "meta-llama/Llama-3.3-70B-Instruct",
101      "name": "Llama 3.3 70B Instruct",
102      "cost_per_1m_in": 0.09999999999999999,
103      "cost_per_1m_out": 0.32,
104      "cost_per_1m_in_cached": 0.049999999999999996,
105      "cost_per_1m_out_cached": 0.19999999999999998,
106      "context_window": 128000,
107      "default_max_tokens": 12800,
108      "can_reason": true,
109      "reasoning_levels": [
110        "low",
111        "medium",
112        "high"
113      ],
114      "default_reasoning_effort": "medium",
115      "supports_attachments": false,
116      "options": {}
117    },
118    {
119      "id": "mistralai/Mistral-Large-Instruct-2411",
120      "name": "Mistral Large Instruct 2411",
121      "cost_per_1m_in": 2,
122      "cost_per_1m_out": 6,
123      "cost_per_1m_in_cached": 1,
124      "cost_per_1m_out_cached": 4,
125      "context_window": 128000,
126      "default_max_tokens": 12800,
127      "can_reason": false,
128      "supports_attachments": true,
129      "options": {}
130    },
131    {
132      "id": "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar",
133      "name": "Qwen3 Coder 480B A35B Instruct int4 mixed ar",
134      "cost_per_1m_in": 0.22,
135      "cost_per_1m_out": 0.95,
136      "cost_per_1m_in_cached": 0.11,
137      "cost_per_1m_out_cached": 0.44,
138      "context_window": 106000,
139      "default_max_tokens": 10600,
140      "can_reason": false,
141      "supports_attachments": false,
142      "options": {}
143    },
144    {
145      "id": "Qwen/Qwen3-Next-80B-A3B-Instruct",
146      "name": "Qwen3 Next 80B A3B Instruct",
147      "cost_per_1m_in": 0.06,
148      "cost_per_1m_out": 0.6,
149      "cost_per_1m_in_cached": 0.03,
150      "cost_per_1m_out_cached": 0.12,
151      "context_window": 262144,
152      "default_max_tokens": 26214,
153      "can_reason": false,
154      "supports_attachments": false,
155      "options": {}
156    }
157  ]
158}