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": "deepseek-ai/DeepSeek-V3.2",
 12      "name": "DeepSeek: DeepSeek V3.2",
 13      "cost_per_1m_in": 0.25,
 14      "cost_per_1m_out": 0.38,
 15      "cost_per_1m_in_cached": 0.125,
 16      "cost_per_1m_out_cached": 0.5,
 17      "context_window": 163840,
 18      "default_max_tokens": 16384,
 19      "can_reason": true,
 20      "supports_attachments": false
 21    },
 22    {
 23      "id": "deepseek-ai/DeepSeek-V4-Flash",
 24      "name": "DeepSeek: DeepSeek V4 Flash",
 25      "cost_per_1m_in": 1.55,
 26      "cost_per_1m_out": 2.28,
 27      "cost_per_1m_in_cached": 0.38,
 28      "cost_per_1m_out_cached": 0,
 29      "context_window": 1048576,
 30      "default_max_tokens": 104857,
 31      "can_reason": true,
 32      "supports_attachments": false
 33    },
 34    {
 35      "id": "deepseek-ai/DeepSeek-V4-Pro",
 36      "name": "DeepSeek: DeepSeek V4 Pro",
 37      "cost_per_1m_in": 4.45,
 38      "cost_per_1m_out": 5.5,
 39      "cost_per_1m_in_cached": 0.35,
 40      "cost_per_1m_out_cached": 0,
 41      "context_window": 1048576,
 42      "default_max_tokens": 104857,
 43      "can_reason": true,
 44      "supports_attachments": false
 45    },
 46    {
 47      "id": "google/gemma-4-26b-a4b-it",
 48      "name": "Google: Gemma 4 26B A4B",
 49      "cost_per_1m_in": 0.145,
 50      "cost_per_1m_out": 0.5,
 51      "cost_per_1m_in_cached": 0.08,
 52      "cost_per_1m_out_cached": 0,
 53      "context_window": 32768,
 54      "default_max_tokens": 3276,
 55      "can_reason": true,
 56      "supports_attachments": false
 57    },
 58    {
 59      "id": "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar",
 60      "name": "Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR",
 61      "cost_per_1m_in": 0.22,
 62      "cost_per_1m_out": 0.95,
 63      "cost_per_1m_in_cached": 0.11,
 64      "cost_per_1m_out_cached": 0.44,
 65      "context_window": 106000,
 66      "default_max_tokens": 10600,
 67      "can_reason": false,
 68      "supports_attachments": false
 69    },
 70    {
 71      "id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
 72      "name": "Meta-Llama: Llama 4 Maverick 17B 128E Instruct FP8",
 73      "cost_per_1m_in": 0.15,
 74      "cost_per_1m_out": 0.6,
 75      "cost_per_1m_in_cached": 0.075,
 76      "cost_per_1m_out_cached": 0.3,
 77      "context_window": 430000,
 78      "default_max_tokens": 43000,
 79      "can_reason": true,
 80      "supports_attachments": true
 81    },
 82    {
 83      "id": "meta-llama/Llama-3.3-70B-Instruct",
 84      "name": "Meta: Llama 3.3 70B Instruct",
 85      "cost_per_1m_in": 0.1,
 86      "cost_per_1m_out": 0.32,
 87      "cost_per_1m_in_cached": 0.05,
 88      "cost_per_1m_out_cached": 0.2,
 89      "context_window": 128000,
 90      "default_max_tokens": 12800,
 91      "can_reason": true,
 92      "supports_attachments": false
 93    },
 94    {
 95      "id": "MiniMaxAI/MiniMax-M2.7",
 96      "name": "MiniMax: MiniMax M2.7",
 97      "cost_per_1m_in": 0.3,
 98      "cost_per_1m_out": 1.2,
 99      "cost_per_1m_in_cached": 0.06,
100      "cost_per_1m_out_cached": 0,
101      "context_window": 204800,
102      "default_max_tokens": 20480,
103      "can_reason": false,
104      "supports_attachments": false
105    },
106    {
107      "id": "MiniMaxAI/MiniMax-M2.5",
108      "name": "MiniMaxAI/MiniMax-M2.5",
109      "cost_per_1m_in": 0.2,
110      "cost_per_1m_out": 1.2,
111      "cost_per_1m_in_cached": 0.1,
112      "cost_per_1m_out_cached": 0,
113      "context_window": 196600,
114      "default_max_tokens": 19660,
115      "can_reason": false,
116      "supports_attachments": false
117    },
118    {
119      "id": "mistralai/Mistral-Large-Instruct-2411",
120      "name": "Mistral: 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    },
130    {
131      "id": "moonshotai/Kimi-K2-Instruct-0905",
132      "name": "MoonshotAI: Kimi K2 Instruct 0905",
133      "cost_per_1m_in": 0.39,
134      "cost_per_1m_out": 1.9,
135      "cost_per_1m_in_cached": 0.195,
136      "cost_per_1m_out_cached": 0.78,
137      "context_window": 262144,
138      "default_max_tokens": 26214,
139      "can_reason": false,
140      "supports_attachments": false
141    },
142    {
143      "id": "moonshotai/Kimi-K2-Thinking",
144      "name": "MoonshotAI: Kimi K2 Thinking",
145      "cost_per_1m_in": 0.32,
146      "cost_per_1m_out": 0.48,
147      "cost_per_1m_in_cached": 0.16,
148      "cost_per_1m_out_cached": 0.64,
149      "context_window": 262144,
150      "default_max_tokens": 26214,
151      "can_reason": true,
152      "supports_attachments": false
153    },
154    {
155      "id": "moonshotai/Kimi-K2.5",
156      "name": "MoonshotAI: Kimi K2.5",
157      "cost_per_1m_in": 0.445,
158      "cost_per_1m_out": 2,
159      "cost_per_1m_in_cached": 0.225,
160      "cost_per_1m_out_cached": 1.1,
161      "context_window": 262144,
162      "default_max_tokens": 26214,
163      "can_reason": true,
164      "supports_attachments": true
165    },
166    {
167      "id": "moonshotai/Kimi-K2.6",
168      "name": "MoonshotAI: Kimi K2.6",
169      "cost_per_1m_in": 0.74,
170      "cost_per_1m_out": 3.5,
171      "cost_per_1m_in_cached": 0.25,
172      "cost_per_1m_out_cached": 0,
173      "context_window": 32768,
174      "default_max_tokens": 3276,
175      "can_reason": true,
176      "supports_attachments": true
177    },
178    {
179      "id": "openai/gpt-oss-120b",
180      "name": "OpenAI: gpt-oss-120b",
181      "cost_per_1m_in": 0.1,
182      "cost_per_1m_out": 0.4,
183      "cost_per_1m_in_cached": 0.01,
184      "cost_per_1m_out_cached": 0.04,
185      "context_window": 131072,
186      "default_max_tokens": 13107,
187      "can_reason": true,
188      "reasoning_levels": [
189        "low",
190        "medium",
191        "high"
192      ],
193      "default_reasoning_effort": "medium",
194      "supports_attachments": false
195    },
196    {
197      "id": "openai/gpt-oss-20b",
198      "name": "OpenAI: gpt-oss-20b",
199      "cost_per_1m_in": 0.016,
200      "cost_per_1m_out": 0.06,
201      "cost_per_1m_in_cached": 0.008,
202      "cost_per_1m_out_cached": 0.032,
203      "context_window": 64000,
204      "default_max_tokens": 6400,
205      "can_reason": true,
206      "reasoning_levels": [
207        "low",
208        "medium",
209        "high"
210      ],
211      "default_reasoning_effort": "medium",
212      "supports_attachments": false
213    },
214    {
215      "id": "Qwen/Qwen2.5-VL-32B-Instruct",
216      "name": "Qwen: Qwen2.5 VL 32B Instruct",
217      "cost_per_1m_in": 0.05,
218      "cost_per_1m_out": 0.22,
219      "cost_per_1m_in_cached": 0.025,
220      "cost_per_1m_out_cached": 0.1,
221      "context_window": 32000,
222      "default_max_tokens": 3200,
223      "can_reason": false,
224      "supports_attachments": true
225    },
226    {
227      "id": "Qwen/Qwen3-Next-80B-A3B-Instruct",
228      "name": "Qwen: Qwen3 Next 80B A3B Instruct",
229      "cost_per_1m_in": 0.06,
230      "cost_per_1m_out": 0.6,
231      "cost_per_1m_in_cached": 0.03,
232      "cost_per_1m_out_cached": 0.12,
233      "context_window": 262144,
234      "default_max_tokens": 26214,
235      "can_reason": false,
236      "supports_attachments": false
237    },
238    {
239      "id": "zai-org/GLM-4.6",
240      "name": "Z.ai: GLM 4.6",
241      "cost_per_1m_in": 0.35,
242      "cost_per_1m_out": 1.5,
243      "cost_per_1m_in_cached": 0.175,
244      "cost_per_1m_out_cached": 0.7,
245      "context_window": 200000,
246      "default_max_tokens": 20000,
247      "can_reason": true,
248      "supports_attachments": false
249    },
250    {
251      "id": "zai-org/GLM-4.7",
252      "name": "Z.ai: GLM 4.7",
253      "cost_per_1m_in": 0.5,
254      "cost_per_1m_out": 2,
255      "cost_per_1m_in_cached": 0.35,
256      "cost_per_1m_out_cached": 0.6,
257      "context_window": 202752,
258      "default_max_tokens": 20275,
259      "can_reason": true,
260      "supports_attachments": false
261    },
262    {
263      "id": "zai-org/GLM-4.7-Flash",
264      "name": "Z.ai: GLM 4.7 Flash",
265      "cost_per_1m_in": 0.07,
266      "cost_per_1m_out": 0.4,
267      "cost_per_1m_in_cached": 0.035,
268      "cost_per_1m_out_cached": 0.14,
269      "context_window": 200000,
270      "default_max_tokens": 20000,
271      "can_reason": true,
272      "supports_attachments": false
273    },
274    {
275      "id": "zai-org/GLM-5",
276      "name": "Z.ai: GLM 5",
277      "cost_per_1m_in": 1,
278      "cost_per_1m_out": 3,
279      "cost_per_1m_in_cached": 0.5,
280      "cost_per_1m_out_cached": 0,
281      "context_window": 202752,
282      "default_max_tokens": 20275,
283      "can_reason": true,
284      "supports_attachments": false
285    },
286    {
287      "id": "zai-org/GLM-5.1",
288      "name": "Z.ai: GLM 5.1",
289      "cost_per_1m_in": 1.5,
290      "cost_per_1m_out": 4.4,
291      "cost_per_1m_in_cached": 0.26,
292      "cost_per_1m_out_cached": 0,
293      "context_window": 202752,
294      "default_max_tokens": 20275,
295      "can_reason": true,
296      "supports_attachments": false
297    }
298  ]
299}