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": 0.55,
 91      "cost_per_1m_out": 3,
 92      "cost_per_1m_in_cached": 0.275,
 93      "cost_per_1m_out_cached": 1.1,
 94      "context_window": 262144,
 95      "default_max_tokens": 26214,
 96      "can_reason": false,
 97      "supports_attachments": false,
 98      "options": {}
 99    },
100    {
101      "id": "openai/gpt-oss-120b",
102      "name": "OpenAI: gpt-oss-120b",
103      "cost_per_1m_in": 0.02,
104      "cost_per_1m_out": 0.1,
105      "cost_per_1m_in_cached": 0.01,
106      "cost_per_1m_out_cached": 0.04,
107      "context_window": 131072,
108      "default_max_tokens": 13107,
109      "can_reason": true,
110      "reasoning_levels": [
111        "low",
112        "medium",
113        "high"
114      ],
115      "default_reasoning_effort": "medium",
116      "supports_attachments": false,
117      "options": {}
118    },
119    {
120      "id": "openai/gpt-oss-20b",
121      "name": "OpenAI: gpt-oss-20b",
122      "cost_per_1m_in": 0.016,
123      "cost_per_1m_out": 0.06,
124      "cost_per_1m_in_cached": 0.008,
125      "cost_per_1m_out_cached": 0.032,
126      "context_window": 64000,
127      "default_max_tokens": 6400,
128      "can_reason": true,
129      "reasoning_levels": [
130        "low",
131        "medium",
132        "high"
133      ],
134      "default_reasoning_effort": "medium",
135      "supports_attachments": false,
136      "options": {}
137    },
138    {
139      "id": "Qwen/Qwen3-Next-80B-A3B-Instruct",
140      "name": "Qwen: Qwen3 Next 80B A3B Instruct",
141      "cost_per_1m_in": 0.06,
142      "cost_per_1m_out": 0.6,
143      "cost_per_1m_in_cached": 0.03,
144      "cost_per_1m_out_cached": 0.12,
145      "context_window": 262144,
146      "default_max_tokens": 26214,
147      "can_reason": false,
148      "supports_attachments": false,
149      "options": {}
150    },
151    {
152      "id": "zai-org/GLM-4.6",
153      "name": "Z.ai: GLM 4.6",
154      "cost_per_1m_in": 0.35,
155      "cost_per_1m_out": 1.5,
156      "cost_per_1m_in_cached": 0.175,
157      "cost_per_1m_out_cached": 0.7,
158      "context_window": 200000,
159      "default_max_tokens": 20000,
160      "can_reason": true,
161      "reasoning_levels": [
162        "low",
163        "medium",
164        "high"
165      ],
166      "default_reasoning_effort": "medium",
167      "supports_attachments": false,
168      "options": {}
169    },
170    {
171      "id": "zai-org/GLM-4.7",
172      "name": "Z.ai: GLM 4.7",
173      "cost_per_1m_in": 0.3,
174      "cost_per_1m_out": 1.4,
175      "cost_per_1m_in_cached": 0.15,
176      "cost_per_1m_out_cached": 0.6,
177      "context_window": 202752,
178      "default_max_tokens": 20275,
179      "can_reason": true,
180      "reasoning_levels": [
181        "low",
182        "medium",
183        "high"
184      ],
185      "default_reasoning_effort": "medium",
186      "supports_attachments": false,
187      "options": {}
188    },
189    {
190      "id": "zai-org/GLM-4.7-Flash",
191      "name": "Z.ai: GLM 4.7 Flash",
192      "cost_per_1m_in": 0.07,
193      "cost_per_1m_out": 0.4,
194      "cost_per_1m_in_cached": 0.035,
195      "cost_per_1m_out_cached": 0.14,
196      "context_window": 200000,
197      "default_max_tokens": 20000,
198      "can_reason": true,
199      "reasoning_levels": [
200        "low",
201        "medium",
202        "high"
203      ],
204      "default_reasoning_effort": "medium",
205      "supports_attachments": false,
206      "options": {}
207    },
208    {
209      "id": "zai-org/GLM-5",
210      "name": "Z.ai: GLM 5",
211      "cost_per_1m_in": 1,
212      "cost_per_1m_out": 3,
213      "cost_per_1m_in_cached": 0.5,
214      "cost_per_1m_out_cached": 0,
215      "context_window": 202752,
216      "default_max_tokens": 20275,
217      "can_reason": true,
218      "reasoning_levels": [
219        "low",
220        "medium",
221        "high"
222      ],
223      "default_reasoning_effort": "medium",
224      "supports_attachments": false,
225      "options": {}
226    }
227  ]
228}