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": "moonshotai/Kimi-K2.5",
  8  "default_small_model_id": "zai-org/GLM-4.7-Flash",
  9  "models": [
 10    {
 11      "id": "google/gemma-4-26b-a4b-it",
 12      "name": "Google: Gemma 4 26B A4B",
 13      "cost_per_1m_in": 0.145,
 14      "cost_per_1m_out": 0.5,
 15      "cost_per_1m_in_cached": 0.08,
 16      "cost_per_1m_out_cached": 0,
 17      "context_window": 262144,
 18      "default_max_tokens": 26214,
 19      "can_reason": true,
 20      "supports_attachments": false
 21    },
 22    {
 23      "id": "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar",
 24      "name": "Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR",
 25      "cost_per_1m_in": 0.22,
 26      "cost_per_1m_out": 0.95,
 27      "cost_per_1m_in_cached": 0.11,
 28      "cost_per_1m_out_cached": 0.44,
 29      "context_window": 106000,
 30      "default_max_tokens": 10600,
 31      "can_reason": false,
 32      "supports_attachments": false
 33    },
 34    {
 35      "id": "meta-llama/Llama-3.3-70B-Instruct",
 36      "name": "Meta: Llama 3.3 70B Instruct",
 37      "cost_per_1m_in": 0.1,
 38      "cost_per_1m_out": 0.32,
 39      "cost_per_1m_in_cached": 0.05,
 40      "cost_per_1m_out_cached": 0.2,
 41      "context_window": 128000,
 42      "default_max_tokens": 12800,
 43      "can_reason": true,
 44      "supports_attachments": false
 45    },
 46    {
 47      "id": "MiniMaxAI/MiniMax-M2.5",
 48      "name": "MiniMaxAI/MiniMax-M2.5",
 49      "cost_per_1m_in": 0.118,
 50      "cost_per_1m_out": 0.99,
 51      "cost_per_1m_in_cached": 0.1,
 52      "cost_per_1m_out_cached": 0,
 53      "context_window": 196600,
 54      "default_max_tokens": 19660,
 55      "can_reason": false,
 56      "supports_attachments": false
 57    },
 58    {
 59      "id": "mistralai/Mistral-Large-Instruct-2411",
 60      "name": "Mistral: Mistral Large Instruct 2411",
 61      "cost_per_1m_in": 2,
 62      "cost_per_1m_out": 6,
 63      "cost_per_1m_in_cached": 1,
 64      "cost_per_1m_out_cached": 4,
 65      "context_window": 128000,
 66      "default_max_tokens": 12800,
 67      "can_reason": false,
 68      "supports_attachments": true
 69    },
 70    {
 71      "id": "moonshotai/Kimi-K2-Instruct-0905",
 72      "name": "MoonshotAI: Kimi K2 Instruct 0905",
 73      "cost_per_1m_in": 0.39,
 74      "cost_per_1m_out": 1.9,
 75      "cost_per_1m_in_cached": 0.195,
 76      "cost_per_1m_out_cached": 0.78,
 77      "context_window": 262144,
 78      "default_max_tokens": 26214,
 79      "can_reason": false,
 80      "supports_attachments": false
 81    },
 82    {
 83      "id": "moonshotai/Kimi-K2-Thinking",
 84      "name": "MoonshotAI: Kimi K2 Thinking",
 85      "cost_per_1m_in": 0.32,
 86      "cost_per_1m_out": 0.48,
 87      "cost_per_1m_in_cached": 0.16,
 88      "cost_per_1m_out_cached": 0.64,
 89      "context_window": 262144,
 90      "default_max_tokens": 26214,
 91      "can_reason": true,
 92      "supports_attachments": false
 93    },
 94    {
 95      "id": "moonshotai/Kimi-K2.5",
 96      "name": "MoonshotAI: Kimi K2.5",
 97      "cost_per_1m_in": 0.445,
 98      "cost_per_1m_out": 2,
 99      "cost_per_1m_in_cached": 0.225,
100      "cost_per_1m_out_cached": 1.1,
101      "context_window": 262144,
102      "default_max_tokens": 26214,
103      "can_reason": true,
104      "supports_attachments": true
105    },
106    {
107      "id": "moonshotai/Kimi-K2.6",
108      "name": "MoonshotAI: Kimi K2.6",
109      "cost_per_1m_in": 0.8,
110      "cost_per_1m_out": 4,
111      "cost_per_1m_in_cached": 0.25,
112      "cost_per_1m_out_cached": 0,
113      "context_window": 262144,
114      "default_max_tokens": 26214,
115      "can_reason": true,
116      "supports_attachments": true
117    },
118    {
119      "id": "openai/gpt-oss-120b",
120      "name": "OpenAI: gpt-oss-120b",
121      "cost_per_1m_in": 0.1,
122      "cost_per_1m_out": 0.4,
123      "cost_per_1m_in_cached": 0.01,
124      "cost_per_1m_out_cached": 0.04,
125      "context_window": 131072,
126      "default_max_tokens": 13107,
127      "can_reason": true,
128      "reasoning_levels": [
129        "low",
130        "medium",
131        "high"
132      ],
133      "default_reasoning_effort": "medium",
134      "supports_attachments": false
135    },
136    {
137      "id": "openai/gpt-oss-20b",
138      "name": "OpenAI: gpt-oss-20b",
139      "cost_per_1m_in": 0.016,
140      "cost_per_1m_out": 0.06,
141      "cost_per_1m_in_cached": 0.008,
142      "cost_per_1m_out_cached": 0.032,
143      "context_window": 64000,
144      "default_max_tokens": 6400,
145      "can_reason": true,
146      "reasoning_levels": [
147        "low",
148        "medium",
149        "high"
150      ],
151      "default_reasoning_effort": "medium",
152      "supports_attachments": false
153    },
154    {
155      "id": "Qwen/Qwen3-Next-80B-A3B-Instruct",
156      "name": "Qwen: Qwen3 Next 80B A3B Instruct",
157      "cost_per_1m_in": 0.06,
158      "cost_per_1m_out": 0.6,
159      "cost_per_1m_in_cached": 0.03,
160      "cost_per_1m_out_cached": 0.12,
161      "context_window": 262144,
162      "default_max_tokens": 26214,
163      "can_reason": false,
164      "supports_attachments": false
165    },
166    {
167      "id": "zai-org/GLM-4.6",
168      "name": "Z.ai: GLM 4.6",
169      "cost_per_1m_in": 0.35,
170      "cost_per_1m_out": 1.5,
171      "cost_per_1m_in_cached": 0.175,
172      "cost_per_1m_out_cached": 0.7,
173      "context_window": 200000,
174      "default_max_tokens": 20000,
175      "can_reason": true,
176      "supports_attachments": false
177    },
178    {
179      "id": "zai-org/GLM-4.7",
180      "name": "Z.ai: GLM 4.7",
181      "cost_per_1m_in": 0.3,
182      "cost_per_1m_out": 1.4,
183      "cost_per_1m_in_cached": 0.15,
184      "cost_per_1m_out_cached": 0.6,
185      "context_window": 202752,
186      "default_max_tokens": 20275,
187      "can_reason": true,
188      "supports_attachments": false
189    },
190    {
191      "id": "zai-org/GLM-4.7-Flash",
192      "name": "Z.ai: GLM 4.7 Flash",
193      "cost_per_1m_in": 0.07,
194      "cost_per_1m_out": 0.4,
195      "cost_per_1m_in_cached": 0.035,
196      "cost_per_1m_out_cached": 0.14,
197      "context_window": 200000,
198      "default_max_tokens": 20000,
199      "can_reason": true,
200      "supports_attachments": false
201    },
202    {
203      "id": "zai-org/GLM-5",
204      "name": "Z.ai: GLM 5",
205      "cost_per_1m_in": 1,
206      "cost_per_1m_out": 3,
207      "cost_per_1m_in_cached": 0.5,
208      "cost_per_1m_out_cached": 0,
209      "context_window": 202752,
210      "default_max_tokens": 20275,
211      "can_reason": true,
212      "supports_attachments": false
213    },
214    {
215      "id": "zai-org/GLM-5.1",
216      "name": "Z.ai: GLM 5.1",
217      "cost_per_1m_in": 1.06,
218      "cost_per_1m_out": 4.4,
219      "cost_per_1m_in_cached": 0.26,
220      "cost_per_1m_out_cached": 0,
221      "context_window": 202752,
222      "default_max_tokens": 20275,
223      "can_reason": true,
224      "supports_attachments": false
225    }
226  ]
227}