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": "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar",
 12      "name": "Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR",
 13      "cost_per_1m_in": 0.22,
 14      "cost_per_1m_out": 0.95,
 15      "cost_per_1m_in_cached": 0.11,
 16      "cost_per_1m_out_cached": 0.44,
 17      "context_window": 106000,
 18      "default_max_tokens": 10600,
 19      "can_reason": false,
 20      "supports_attachments": false,
 21      "options": {}
 22    },
 23    {
 24      "id": "meta-llama/Llama-3.3-70B-Instruct",
 25      "name": "Meta: Llama 3.3 70B Instruct",
 26      "cost_per_1m_in": 0.1,
 27      "cost_per_1m_out": 0.32,
 28      "cost_per_1m_in_cached": 0.05,
 29      "cost_per_1m_out_cached": 0.2,
 30      "context_window": 128000,
 31      "default_max_tokens": 12800,
 32      "can_reason": true,
 33      "reasoning_levels": [
 34        "low",
 35        "medium",
 36        "high"
 37      ],
 38      "default_reasoning_effort": "medium",
 39      "supports_attachments": false,
 40      "options": {}
 41    },
 42    {
 43      "id": "mistralai/Mistral-Large-Instruct-2411",
 44      "name": "Mistral: Mistral Large Instruct 2411",
 45      "cost_per_1m_in": 2,
 46      "cost_per_1m_out": 6,
 47      "cost_per_1m_in_cached": 1,
 48      "cost_per_1m_out_cached": 4,
 49      "context_window": 128000,
 50      "default_max_tokens": 12800,
 51      "can_reason": false,
 52      "supports_attachments": true,
 53      "options": {}
 54    },
 55    {
 56      "id": "moonshotai/Kimi-K2-Instruct-0905",
 57      "name": "MoonshotAI: Kimi K2 Instruct 0905",
 58      "cost_per_1m_in": 0.39,
 59      "cost_per_1m_out": 1.9,
 60      "cost_per_1m_in_cached": 0.195,
 61      "cost_per_1m_out_cached": 0.78,
 62      "context_window": 262144,
 63      "default_max_tokens": 26214,
 64      "can_reason": false,
 65      "supports_attachments": false,
 66      "options": {}
 67    },
 68    {
 69      "id": "moonshotai/Kimi-K2-Thinking",
 70      "name": "MoonshotAI: Kimi K2 Thinking",
 71      "cost_per_1m_in": 0.32,
 72      "cost_per_1m_out": 0.48,
 73      "cost_per_1m_in_cached": 0.16,
 74      "cost_per_1m_out_cached": 0.64,
 75      "context_window": 262144,
 76      "default_max_tokens": 26214,
 77      "can_reason": true,
 78      "reasoning_levels": [
 79        "low",
 80        "medium",
 81        "high"
 82      ],
 83      "default_reasoning_effort": "medium",
 84      "supports_attachments": false,
 85      "options": {}
 86    },
 87    {
 88      "id": "moonshotai/Kimi-K2.5",
 89      "name": "MoonshotAI: Kimi K2.5",
 90      "cost_per_1m_in": 0.445,
 91      "cost_per_1m_out": 2.22,
 92      "cost_per_1m_in_cached": 0.225,
 93      "cost_per_1m_out_cached": 1.1,
 94      "context_window": 262144,
 95      "default_max_tokens": 26214,
 96      "can_reason": true,
 97      "reasoning_levels": [
 98        "low",
 99        "medium",
100        "high"
101      ],
102      "default_reasoning_effort": "medium",
103      "supports_attachments": false,
104      "options": {}
105    },
106    {
107      "id": "openai/gpt-oss-120b",
108      "name": "OpenAI: gpt-oss-120b",
109      "cost_per_1m_in": 0.02,
110      "cost_per_1m_out": 0.1,
111      "cost_per_1m_in_cached": 0.01,
112      "cost_per_1m_out_cached": 0.04,
113      "context_window": 131072,
114      "default_max_tokens": 13107,
115      "can_reason": true,
116      "reasoning_levels": [
117        "low",
118        "medium",
119        "high"
120      ],
121      "default_reasoning_effort": "medium",
122      "supports_attachments": false,
123      "options": {}
124    },
125    {
126      "id": "openai/gpt-oss-20b",
127      "name": "OpenAI: gpt-oss-20b",
128      "cost_per_1m_in": 0.016,
129      "cost_per_1m_out": 0.06,
130      "cost_per_1m_in_cached": 0.008,
131      "cost_per_1m_out_cached": 0.032,
132      "context_window": 64000,
133      "default_max_tokens": 6400,
134      "can_reason": true,
135      "reasoning_levels": [
136        "low",
137        "medium",
138        "high"
139      ],
140      "default_reasoning_effort": "medium",
141      "supports_attachments": false,
142      "options": {}
143    },
144    {
145      "id": "Qwen/Qwen3-Next-80B-A3B-Instruct",
146      "name": "Qwen: 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      "id": "zai-org/GLM-4.6",
159      "name": "Z.ai: GLM 4.6",
160      "cost_per_1m_in": 0.35,
161      "cost_per_1m_out": 1.5,
162      "cost_per_1m_in_cached": 0.175,
163      "cost_per_1m_out_cached": 0.7,
164      "context_window": 200000,
165      "default_max_tokens": 20000,
166      "can_reason": true,
167      "reasoning_levels": [
168        "low",
169        "medium",
170        "high"
171      ],
172      "default_reasoning_effort": "medium",
173      "supports_attachments": false,
174      "options": {}
175    },
176    {
177      "id": "zai-org/GLM-4.7",
178      "name": "Z.ai: GLM 4.7",
179      "cost_per_1m_in": 0.3,
180      "cost_per_1m_out": 1.4,
181      "cost_per_1m_in_cached": 0.15,
182      "cost_per_1m_out_cached": 0.6,
183      "context_window": 202752,
184      "default_max_tokens": 20275,
185      "can_reason": true,
186      "reasoning_levels": [
187        "low",
188        "medium",
189        "high"
190      ],
191      "default_reasoning_effort": "medium",
192      "supports_attachments": false,
193      "options": {}
194    },
195    {
196      "id": "zai-org/GLM-4.7-Flash",
197      "name": "Z.ai: GLM 4.7 Flash",
198      "cost_per_1m_in": 0.07,
199      "cost_per_1m_out": 0.4,
200      "cost_per_1m_in_cached": 0.035,
201      "cost_per_1m_out_cached": 0.14,
202      "context_window": 200000,
203      "default_max_tokens": 20000,
204      "can_reason": true,
205      "reasoning_levels": [
206        "low",
207        "medium",
208        "high"
209      ],
210      "default_reasoning_effort": "medium",
211      "supports_attachments": false,
212      "options": {}
213    },
214    {
215      "id": "zai-org/GLM-5",
216      "name": "Z.ai: GLM 5",
217      "cost_per_1m_in": 1,
218      "cost_per_1m_out": 3,
219      "cost_per_1m_in_cached": 0.5,
220      "cost_per_1m_out_cached": 0,
221      "context_window": 202752,
222      "default_max_tokens": 20275,
223      "can_reason": true,
224      "reasoning_levels": [
225        "low",
226        "medium",
227        "high"
228      ],
229      "default_reasoning_effort": "medium",
230      "supports_attachments": false,
231      "options": {}
232    }
233  ]
234}