1{
2 "name": "Chutes",
3 "id": "chutes",
4 "api_key": "$CHUTES_API_KEY",
5 "api_endpoint": "https://llm.chutes.ai/v1",
6 "type": "openai-compat",
7 "default_large_model_id": "zai-org/GLM-5-TEE",
8 "default_small_model_id": "zai-org/GLM-5-Turbo",
9 "models": [
10 {
11 "id": "NousResearch/DeepHermes-3-Mistral-24B-Preview",
12 "name": "DeepHermes-3-Mistral-24B-Preview",
13 "cost_per_1m_in": 0.0245,
14 "cost_per_1m_out": 0.0978,
15 "cost_per_1m_in_cached": 0.01225,
16 "cost_per_1m_out_cached": 0,
17 "context_window": 32768,
18 "default_max_tokens": 32768,
19 "can_reason": false,
20 "supports_attachments": false
21 },
22 {
23 "id": "deepseek-ai/DeepSeek-R1-0528-TEE",
24 "name": "DeepSeek-R1-0528-TEE",
25 "cost_per_1m_in": 0.45,
26 "cost_per_1m_out": 2.15,
27 "cost_per_1m_in_cached": 0.225,
28 "cost_per_1m_out_cached": 0,
29 "context_window": 163840,
30 "default_max_tokens": 65536,
31 "can_reason": true,
32 "reasoning_levels": [
33 "low",
34 "medium",
35 "high"
36 ],
37 "default_reasoning_effort": "medium",
38 "supports_attachments": false
39 },
40 {
41 "id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
42 "name": "DeepSeek-R1-Distill-Llama-70B",
43 "cost_per_1m_in": 0.0272,
44 "cost_per_1m_out": 0.1087,
45 "cost_per_1m_in_cached": 0.0136,
46 "cost_per_1m_out_cached": 0,
47 "context_window": 131072,
48 "default_max_tokens": 131072,
49 "can_reason": true,
50 "reasoning_levels": [
51 "low",
52 "medium",
53 "high"
54 ],
55 "default_reasoning_effort": "medium",
56 "supports_attachments": false
57 },
58 {
59 "id": "tngtech/DeepSeek-TNG-R1T2-Chimera-TEE",
60 "name": "DeepSeek-TNG-R1T2-Chimera-TEE",
61 "cost_per_1m_in": 0.3,
62 "cost_per_1m_out": 1.1,
63 "cost_per_1m_in_cached": 0.15,
64 "cost_per_1m_out_cached": 0,
65 "context_window": 163840,
66 "default_max_tokens": 163840,
67 "can_reason": true,
68 "reasoning_levels": [
69 "low",
70 "medium",
71 "high"
72 ],
73 "default_reasoning_effort": "medium",
74 "supports_attachments": false
75 },
76 {
77 "id": "deepseek-ai/DeepSeek-V3-0324-TEE",
78 "name": "DeepSeek-V3-0324-TEE",
79 "cost_per_1m_in": 0.25,
80 "cost_per_1m_out": 1,
81 "cost_per_1m_in_cached": 0.125,
82 "cost_per_1m_out_cached": 0,
83 "context_window": 163840,
84 "default_max_tokens": 65536,
85 "can_reason": false,
86 "supports_attachments": false
87 },
88 {
89 "id": "deepseek-ai/DeepSeek-V3.1-TEE",
90 "name": "DeepSeek-V3.1-TEE",
91 "cost_per_1m_in": 0.27,
92 "cost_per_1m_out": 1,
93 "cost_per_1m_in_cached": 0.135,
94 "cost_per_1m_out_cached": 0,
95 "context_window": 163840,
96 "default_max_tokens": 65536,
97 "can_reason": true,
98 "reasoning_levels": [
99 "low",
100 "medium",
101 "high"
102 ],
103 "default_reasoning_effort": "medium",
104 "supports_attachments": false
105 },
106 {
107 "id": "deepseek-ai/DeepSeek-V3.2-TEE",
108 "name": "DeepSeek-V3.2-TEE",
109 "cost_per_1m_in": 0.28,
110 "cost_per_1m_out": 0.42,
111 "cost_per_1m_in_cached": 0.14,
112 "cost_per_1m_out_cached": 0,
113 "context_window": 131072,
114 "default_max_tokens": 65536,
115 "can_reason": true,
116 "reasoning_levels": [
117 "low",
118 "medium",
119 "high"
120 ],
121 "default_reasoning_effort": "medium",
122 "supports_attachments": false
123 },
124 {
125 "id": "zai-org/GLM-4.6V",
126 "name": "GLM-4.6V",
127 "cost_per_1m_in": 0.3,
128 "cost_per_1m_out": 0.9,
129 "cost_per_1m_in_cached": 0.15,
130 "cost_per_1m_out_cached": 0,
131 "context_window": 131072,
132 "default_max_tokens": 65536,
133 "can_reason": true,
134 "reasoning_levels": [
135 "low",
136 "medium",
137 "high"
138 ],
139 "default_reasoning_effort": "medium",
140 "supports_attachments": true
141 },
142 {
143 "id": "zai-org/GLM-4.7-FP8",
144 "name": "GLM-4.7-FP8",
145 "cost_per_1m_in": 0.2989,
146 "cost_per_1m_out": 1.1957,
147 "cost_per_1m_in_cached": 0.14945,
148 "cost_per_1m_out_cached": 0,
149 "context_window": 202752,
150 "default_max_tokens": 65535,
151 "can_reason": true,
152 "reasoning_levels": [
153 "low",
154 "medium",
155 "high"
156 ],
157 "default_reasoning_effort": "medium",
158 "supports_attachments": false
159 },
160 {
161 "id": "zai-org/GLM-4.7-TEE",
162 "name": "GLM-4.7-TEE",
163 "cost_per_1m_in": 0.39,
164 "cost_per_1m_out": 1.75,
165 "cost_per_1m_in_cached": 0.195,
166 "cost_per_1m_out_cached": 0,
167 "context_window": 202752,
168 "default_max_tokens": 65535,
169 "can_reason": true,
170 "reasoning_levels": [
171 "low",
172 "medium",
173 "high"
174 ],
175 "default_reasoning_effort": "medium",
176 "supports_attachments": false
177 },
178 {
179 "id": "zai-org/GLM-5-TEE",
180 "name": "GLM-5-TEE",
181 "cost_per_1m_in": 0.95,
182 "cost_per_1m_out": 2.55,
183 "cost_per_1m_in_cached": 0.475,
184 "cost_per_1m_out_cached": 0,
185 "context_window": 202752,
186 "default_max_tokens": 65535,
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": "zai-org/GLM-5-Turbo",
198 "name": "GLM-5-Turbo",
199 "cost_per_1m_in": 0.4891,
200 "cost_per_1m_out": 1.9565,
201 "cost_per_1m_in_cached": 0.24455,
202 "cost_per_1m_out_cached": 0,
203 "context_window": 202752,
204 "default_max_tokens": 65535,
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": "zai-org/GLM-5.1-TEE",
216 "name": "GLM-5.1-TEE",
217 "cost_per_1m_in": 1.05,
218 "cost_per_1m_out": 3.5,
219 "cost_per_1m_in_cached": 0.525,
220 "cost_per_1m_out_cached": 0,
221 "context_window": 202752,
222 "default_max_tokens": 65535,
223 "can_reason": true,
224 "reasoning_levels": [
225 "low",
226 "medium",
227 "high"
228 ],
229 "default_reasoning_effort": "medium",
230 "supports_attachments": false
231 },
232 {
233 "id": "NousResearch/Hermes-4-14B",
234 "name": "Hermes-4-14B",
235 "cost_per_1m_in": 0.0136,
236 "cost_per_1m_out": 0.0543,
237 "cost_per_1m_in_cached": 0.0068,
238 "cost_per_1m_out_cached": 0,
239 "context_window": 40960,
240 "default_max_tokens": 40960,
241 "can_reason": true,
242 "reasoning_levels": [
243 "low",
244 "medium",
245 "high"
246 ],
247 "default_reasoning_effort": "medium",
248 "supports_attachments": false
249 },
250 {
251 "id": "moonshotai/Kimi-K2.5-TEE",
252 "name": "Kimi-K2.5-TEE",
253 "cost_per_1m_in": 0.44,
254 "cost_per_1m_out": 2,
255 "cost_per_1m_in_cached": 0.22,
256 "cost_per_1m_out_cached": 0,
257 "context_window": 262144,
258 "default_max_tokens": 65535,
259 "can_reason": true,
260 "reasoning_levels": [
261 "low",
262 "medium",
263 "high"
264 ],
265 "default_reasoning_effort": "medium",
266 "supports_attachments": true
267 },
268 {
269 "id": "moonshotai/Kimi-K2.6-TEE",
270 "name": "Kimi-K2.6-TEE",
271 "cost_per_1m_in": 0.95,
272 "cost_per_1m_out": 4,
273 "cost_per_1m_in_cached": 0.475,
274 "cost_per_1m_out_cached": 0,
275 "context_window": 262144,
276 "default_max_tokens": 65535,
277 "can_reason": true,
278 "reasoning_levels": [
279 "low",
280 "medium",
281 "high"
282 ],
283 "default_reasoning_effort": "medium",
284 "supports_attachments": true
285 },
286 {
287 "id": "XiaomiMiMo/MiMo-V2-Flash-TEE",
288 "name": "MiMo-V2-Flash-TEE",
289 "cost_per_1m_in": 0.09,
290 "cost_per_1m_out": 0.29,
291 "cost_per_1m_in_cached": 0.045,
292 "cost_per_1m_out_cached": 0,
293 "context_window": 262144,
294 "default_max_tokens": 65536,
295 "can_reason": false,
296 "supports_attachments": false
297 },
298 {
299 "id": "MiniMaxAI/MiniMax-M2.5-TEE",
300 "name": "MiniMax-M2.5-TEE",
301 "cost_per_1m_in": 0.15,
302 "cost_per_1m_out": 1.2,
303 "cost_per_1m_in_cached": 0.075,
304 "cost_per_1m_out_cached": 0,
305 "context_window": 196608,
306 "default_max_tokens": 65536,
307 "can_reason": true,
308 "reasoning_levels": [
309 "low",
310 "medium",
311 "high"
312 ],
313 "default_reasoning_effort": "medium",
314 "supports_attachments": false
315 },
316 {
317 "id": "Qwen/Qwen2.5-72B-Instruct",
318 "name": "Qwen2.5-72B-Instruct",
319 "cost_per_1m_in": 0.2989,
320 "cost_per_1m_out": 1.1957,
321 "cost_per_1m_in_cached": 0.14945,
322 "cost_per_1m_out_cached": 0,
323 "context_window": 32768,
324 "default_max_tokens": 32768,
325 "can_reason": false,
326 "supports_attachments": false
327 },
328 {
329 "id": "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE",
330 "name": "Qwen3-235B-A22B-Instruct-2507-TEE",
331 "cost_per_1m_in": 0.1,
332 "cost_per_1m_out": 0.6,
333 "cost_per_1m_in_cached": 0.05,
334 "cost_per_1m_out_cached": 0,
335 "context_window": 262144,
336 "default_max_tokens": 65536,
337 "can_reason": false,
338 "supports_attachments": false
339 },
340 {
341 "id": "Qwen/Qwen3-235B-A22B-Thinking-2507",
342 "name": "Qwen3-235B-A22B-Thinking-2507",
343 "cost_per_1m_in": 0.11,
344 "cost_per_1m_out": 0.6,
345 "cost_per_1m_in_cached": 0.055,
346 "cost_per_1m_out_cached": 0,
347 "context_window": 262144,
348 "default_max_tokens": 262144,
349 "can_reason": true,
350 "reasoning_levels": [
351 "low",
352 "medium",
353 "high"
354 ],
355 "default_reasoning_effort": "medium",
356 "supports_attachments": false
357 },
358 {
359 "id": "Qwen/Qwen3-30B-A3B",
360 "name": "Qwen3-30B-A3B",
361 "cost_per_1m_in": 0.06,
362 "cost_per_1m_out": 0.22,
363 "cost_per_1m_in_cached": 0.03,
364 "cost_per_1m_out_cached": 0,
365 "context_window": 40960,
366 "default_max_tokens": 40960,
367 "can_reason": true,
368 "reasoning_levels": [
369 "low",
370 "medium",
371 "high"
372 ],
373 "default_reasoning_effort": "medium",
374 "supports_attachments": false
375 },
376 {
377 "id": "Qwen/Qwen3-32B-TEE",
378 "name": "Qwen3-32B-TEE",
379 "cost_per_1m_in": 0.08,
380 "cost_per_1m_out": 0.24,
381 "cost_per_1m_in_cached": 0.04,
382 "cost_per_1m_out_cached": 0,
383 "context_window": 40960,
384 "default_max_tokens": 40960,
385 "can_reason": true,
386 "reasoning_levels": [
387 "low",
388 "medium",
389 "high"
390 ],
391 "default_reasoning_effort": "medium",
392 "supports_attachments": false
393 },
394 {
395 "id": "Qwen/Qwen3-Coder-Next-TEE",
396 "name": "Qwen3-Coder-Next-TEE",
397 "cost_per_1m_in": 0.12,
398 "cost_per_1m_out": 0.75,
399 "cost_per_1m_in_cached": 0.06,
400 "cost_per_1m_out_cached": 0,
401 "context_window": 262144,
402 "default_max_tokens": 65536,
403 "can_reason": false,
404 "supports_attachments": false
405 },
406 {
407 "id": "Qwen/Qwen3-Next-80B-A3B-Instruct",
408 "name": "Qwen3-Next-80B-A3B-Instruct",
409 "cost_per_1m_in": 0.1,
410 "cost_per_1m_out": 0.8,
411 "cost_per_1m_in_cached": 0.05,
412 "cost_per_1m_out_cached": 0,
413 "context_window": 262144,
414 "default_max_tokens": 262144,
415 "can_reason": false,
416 "supports_attachments": false
417 },
418 {
419 "id": "Qwen/Qwen3.5-397B-A17B-TEE",
420 "name": "Qwen3.5-397B-A17B-TEE",
421 "cost_per_1m_in": 0.39,
422 "cost_per_1m_out": 2.34,
423 "cost_per_1m_in_cached": 0.195,
424 "cost_per_1m_out_cached": 0,
425 "context_window": 262144,
426 "default_max_tokens": 65536,
427 "can_reason": true,
428 "reasoning_levels": [
429 "low",
430 "medium",
431 "high"
432 ],
433 "default_reasoning_effort": "medium",
434 "supports_attachments": true
435 },
436 {
437 "id": "Qwen/Qwen3.6-27B-TEE",
438 "name": "Qwen3.6-27B-TEE",
439 "cost_per_1m_in": 0.5,
440 "cost_per_1m_out": 2,
441 "cost_per_1m_in_cached": 0.25,
442 "cost_per_1m_out_cached": 0,
443 "context_window": 262144,
444 "default_max_tokens": 65536,
445 "can_reason": true,
446 "reasoning_levels": [
447 "low",
448 "medium",
449 "high"
450 ],
451 "default_reasoning_effort": "medium",
452 "supports_attachments": true
453 },
454 {
455 "id": "unsloth/gemma-3-27b-it",
456 "name": "gemma-3-27b-it",
457 "cost_per_1m_in": 0.0272,
458 "cost_per_1m_out": 0.1087,
459 "cost_per_1m_in_cached": 0.0136,
460 "cost_per_1m_out_cached": 0,
461 "context_window": 128000,
462 "default_max_tokens": 65536,
463 "can_reason": false,
464 "supports_attachments": true
465 },
466 {
467 "id": "google/gemma-4-31B-turbo-TEE",
468 "name": "gemma-4-31B-turbo-TEE",
469 "cost_per_1m_in": 0.13,
470 "cost_per_1m_out": 0.38,
471 "cost_per_1m_in_cached": 0.065,
472 "cost_per_1m_out_cached": 0,
473 "context_window": 131072,
474 "default_max_tokens": 65536,
475 "can_reason": true,
476 "reasoning_levels": [
477 "low",
478 "medium",
479 "high"
480 ],
481 "default_reasoning_effort": "medium",
482 "supports_attachments": true
483 },
484 {
485 "id": "openai/gpt-oss-120b-TEE",
486 "name": "gpt-oss-120b-TEE",
487 "cost_per_1m_in": 0.09,
488 "cost_per_1m_out": 0.36,
489 "cost_per_1m_in_cached": 0.045,
490 "cost_per_1m_out_cached": 0,
491 "context_window": 131072,
492 "default_max_tokens": 65536,
493 "can_reason": true,
494 "reasoning_levels": [
495 "low",
496 "medium",
497 "high"
498 ],
499 "default_reasoning_effort": "medium",
500 "supports_attachments": false
501 }
502 ]
503}