1{
2 "name": "Nebius Token Factory",
3 "id": "nebius",
4 "api_key": "$NEBIUS_API_KEY",
5 "api_endpoint": "https://api.tokenfactory.nebius.com/v1",
6 "type": "openai-compat",
7 "default_large_model_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
8 "default_small_model_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B",
9 "models": [
10 {
11 "id": "deepseek-ai/DeepSeek-R1-0528",
12 "name": "DeepSeek-R1-0528",
13 "cost_per_1m_in": 0.8,
14 "cost_per_1m_out": 2.4,
15 "cost_per_1m_in_cached": 0,
16 "cost_per_1m_out_cached": 0,
17 "context_window": 163840,
18 "default_max_tokens": 16384,
19 "can_reason": true,
20 "reasoning_levels": [
21 "low",
22 "medium",
23 "high"
24 ],
25 "default_reasoning_effort": "medium",
26 "supports_attachments": false
27 },
28 {
29 "id": "deepseek-ai/DeepSeek-V3-0324",
30 "name": "DeepSeek-V3-0324",
31 "cost_per_1m_in": 0.5,
32 "cost_per_1m_out": 1.5,
33 "cost_per_1m_in_cached": 0,
34 "cost_per_1m_out_cached": 0,
35 "context_window": 163840,
36 "default_max_tokens": 16384,
37 "can_reason": false,
38 "supports_attachments": false
39 },
40 {
41 "id": "deepseek-ai/DeepSeek-V3.2",
42 "name": "DeepSeek-V3.2",
43 "cost_per_1m_in": 0.3,
44 "cost_per_1m_out": 0.45,
45 "cost_per_1m_in_cached": 0,
46 "cost_per_1m_out_cached": 0,
47 "context_window": 163000,
48 "default_max_tokens": 16300,
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": "deepseek-ai/DeepSeek-V3.2-fast",
60 "name": "DeepSeek-V3.2 (fast)",
61 "cost_per_1m_in": 0.4,
62 "cost_per_1m_out": 2,
63 "cost_per_1m_in_cached": 0,
64 "cost_per_1m_out_cached": 0,
65 "context_window": 8000,
66 "default_max_tokens": 800,
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": "zai-org/GLM-4.5",
78 "name": "GLM-4.5",
79 "cost_per_1m_in": 0.6,
80 "cost_per_1m_out": 2.2,
81 "cost_per_1m_in_cached": 0,
82 "cost_per_1m_out_cached": 0,
83 "context_window": 131072,
84 "default_max_tokens": 13107,
85 "can_reason": true,
86 "reasoning_levels": [
87 "low",
88 "medium",
89 "high"
90 ],
91 "default_reasoning_effort": "medium",
92 "supports_attachments": false
93 },
94 {
95 "id": "zai-org/GLM-4.5-Air",
96 "name": "GLM-4.5-Air",
97 "cost_per_1m_in": 0.2,
98 "cost_per_1m_out": 1.2,
99 "cost_per_1m_in_cached": 0,
100 "cost_per_1m_out_cached": 0,
101 "context_window": 131072,
102 "default_max_tokens": 13107,
103 "can_reason": true,
104 "reasoning_levels": [
105 "low",
106 "medium",
107 "high"
108 ],
109 "default_reasoning_effort": "medium",
110 "supports_attachments": false
111 },
112 {
113 "id": "zai-org/GLM-4.7-FP8",
114 "name": "GLM-4.7",
115 "cost_per_1m_in": 0.4,
116 "cost_per_1m_out": 2,
117 "cost_per_1m_in_cached": 0,
118 "cost_per_1m_out_cached": 0,
119 "context_window": 202752,
120 "default_max_tokens": 20275,
121 "can_reason": true,
122 "reasoning_levels": [
123 "low",
124 "medium",
125 "high"
126 ],
127 "default_reasoning_effort": "medium",
128 "supports_attachments": false
129 },
130 {
131 "id": "zai-org/GLM-5",
132 "name": "GLM-5",
133 "cost_per_1m_in": 1,
134 "cost_per_1m_out": 3.2,
135 "cost_per_1m_in_cached": 0,
136 "cost_per_1m_out_cached": 0,
137 "context_window": 202752,
138 "default_max_tokens": 20275,
139 "can_reason": true,
140 "reasoning_levels": [
141 "low",
142 "medium",
143 "high"
144 ],
145 "default_reasoning_effort": "medium",
146 "supports_attachments": false
147 },
148 {
149 "id": "NousResearch/Hermes-4-405B",
150 "name": "Hermes-4-405B",
151 "cost_per_1m_in": 1,
152 "cost_per_1m_out": 3,
153 "cost_per_1m_in_cached": 0,
154 "cost_per_1m_out_cached": 0,
155 "context_window": 131072,
156 "default_max_tokens": 13107,
157 "can_reason": true,
158 "reasoning_levels": [
159 "low",
160 "medium",
161 "high"
162 ],
163 "default_reasoning_effort": "medium",
164 "supports_attachments": false
165 },
166 {
167 "id": "NousResearch/Hermes-4-70B",
168 "name": "Hermes-4-70B",
169 "cost_per_1m_in": 0.13,
170 "cost_per_1m_out": 0.4,
171 "cost_per_1m_in_cached": 0,
172 "cost_per_1m_out_cached": 0,
173 "context_window": 131072,
174 "default_max_tokens": 13107,
175 "can_reason": true,
176 "reasoning_levels": [
177 "low",
178 "medium",
179 "high"
180 ],
181 "default_reasoning_effort": "medium",
182 "supports_attachments": false
183 },
184 {
185 "id": "PrimeIntellect/INTELLECT-3",
186 "name": "INTELLECT-3",
187 "cost_per_1m_in": 0.2,
188 "cost_per_1m_out": 1.1,
189 "cost_per_1m_in_cached": 0,
190 "cost_per_1m_out_cached": 0,
191 "context_window": 131072,
192 "default_max_tokens": 13107,
193 "can_reason": true,
194 "reasoning_levels": [
195 "low",
196 "medium",
197 "high"
198 ],
199 "default_reasoning_effort": "medium",
200 "supports_attachments": false
201 },
202 {
203 "id": "moonshotai/Kimi-K2-Instruct",
204 "name": "Kimi-K2-Instruct",
205 "cost_per_1m_in": 0.5,
206 "cost_per_1m_out": 2.4,
207 "cost_per_1m_in_cached": 0,
208 "cost_per_1m_out_cached": 0,
209 "context_window": 131072,
210 "default_max_tokens": 13107,
211 "can_reason": false,
212 "supports_attachments": false
213 },
214 {
215 "id": "moonshotai/Kimi-K2-Thinking",
216 "name": "Kimi-K2-Thinking",
217 "cost_per_1m_in": 0.6,
218 "cost_per_1m_out": 2.5,
219 "cost_per_1m_in_cached": 0,
220 "cost_per_1m_out_cached": 0,
221 "context_window": 262144,
222 "default_max_tokens": 26214,
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": "moonshotai/Kimi-K2.5",
234 "name": "Kimi-K2.5",
235 "cost_per_1m_in": 0.5,
236 "cost_per_1m_out": 2.5,
237 "cost_per_1m_in_cached": 0,
238 "cost_per_1m_out_cached": 0,
239 "context_window": 262144,
240 "default_max_tokens": 26214,
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-fast",
252 "name": "Kimi-K2.5 (fast)",
253 "cost_per_1m_in": 0.5,
254 "cost_per_1m_out": 2.5,
255 "cost_per_1m_in_cached": 0,
256 "cost_per_1m_out_cached": 0,
257 "context_window": 8000,
258 "default_max_tokens": 800,
259 "can_reason": true,
260 "reasoning_levels": [
261 "low",
262 "medium",
263 "high"
264 ],
265 "default_reasoning_effort": "medium",
266 "supports_attachments": false
267 },
268 {
269 "id": "meta-llama/Llama-3.3-70B-Instruct",
270 "name": "Llama-3.3-70B-Instruct",
271 "cost_per_1m_in": 0.13,
272 "cost_per_1m_out": 0.4,
273 "cost_per_1m_in_cached": 0,
274 "cost_per_1m_out_cached": 0,
275 "context_window": 131072,
276 "default_max_tokens": 13107,
277 "can_reason": false,
278 "supports_attachments": false
279 },
280 {
281 "id": "meta-llama/Llama-3.3-70B-Instruct-fast",
282 "name": "Llama-3.3-70B-Instruct (fast)",
283 "cost_per_1m_in": 0.25,
284 "cost_per_1m_out": 0.75,
285 "cost_per_1m_in_cached": 0,
286 "cost_per_1m_out_cached": 0,
287 "context_window": 131072,
288 "default_max_tokens": 13107,
289 "can_reason": false,
290 "supports_attachments": false
291 },
292 {
293 "id": "meta-llama/Meta-Llama-3.1-8B-Instruct",
294 "name": "Meta-Llama-3.1-8B-Instruct",
295 "cost_per_1m_in": 0.02,
296 "cost_per_1m_out": 0.06,
297 "cost_per_1m_in_cached": 0,
298 "cost_per_1m_out_cached": 0,
299 "context_window": 131072,
300 "default_max_tokens": 13107,
301 "can_reason": false,
302 "supports_attachments": false
303 },
304 {
305 "id": "meta-llama/Meta-Llama-3.1-8B-Instruct-fast",
306 "name": "Meta-Llama-3.1-8B-Instruct (fast)",
307 "cost_per_1m_in": 0.03,
308 "cost_per_1m_out": 0.09,
309 "cost_per_1m_in_cached": 0,
310 "cost_per_1m_out_cached": 0,
311 "context_window": 131072,
312 "default_max_tokens": 13107,
313 "can_reason": false,
314 "supports_attachments": false
315 },
316 {
317 "id": "MiniMaxAI/MiniMax-M2.1",
318 "name": "MiniMax-M2.1",
319 "cost_per_1m_in": 0.3,
320 "cost_per_1m_out": 1.2,
321 "cost_per_1m_in_cached": 0,
322 "cost_per_1m_out_cached": 0,
323 "context_window": 196608,
324 "default_max_tokens": 19660,
325 "can_reason": true,
326 "reasoning_levels": [
327 "low",
328 "medium",
329 "high"
330 ],
331 "default_reasoning_effort": "medium",
332 "supports_attachments": false
333 },
334 {
335 "id": "MiniMaxAI/MiniMax-M2.5",
336 "name": "MiniMax-M2.5",
337 "cost_per_1m_in": 0.3,
338 "cost_per_1m_out": 1.2,
339 "cost_per_1m_in_cached": 0,
340 "cost_per_1m_out_cached": 0,
341 "context_window": 196608,
342 "default_max_tokens": 19660,
343 "can_reason": true,
344 "reasoning_levels": [
345 "low",
346 "medium",
347 "high"
348 ],
349 "default_reasoning_effort": "medium",
350 "supports_attachments": false
351 },
352 {
353 "id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B",
354 "name": "Nemotron-3-Nano-30B-A3B",
355 "cost_per_1m_in": 0.06,
356 "cost_per_1m_out": 0.24,
357 "cost_per_1m_in_cached": 0,
358 "cost_per_1m_out_cached": 0,
359 "context_window": 262144,
360 "default_max_tokens": 26214,
361 "can_reason": true,
362 "reasoning_levels": [
363 "low",
364 "medium",
365 "high"
366 ],
367 "default_reasoning_effort": "medium",
368 "supports_attachments": false
369 },
370 {
371 "id": "nvidia/nemotron-3-super-120b-a12b",
372 "name": "Nemotron-3-Super-120b-a12b",
373 "cost_per_1m_in": 0.3,
374 "cost_per_1m_out": 0.9,
375 "cost_per_1m_in_cached": 0,
376 "cost_per_1m_out_cached": 0,
377 "context_window": 262144,
378 "default_max_tokens": 26214,
379 "can_reason": true,
380 "reasoning_levels": [
381 "low",
382 "medium",
383 "high"
384 ],
385 "default_reasoning_effort": "medium",
386 "supports_attachments": false
387 },
388 {
389 "id": "Qwen/Qwen3-235B-A22B-Instruct-2507",
390 "name": "Qwen3-235B-A22B-Instruct-2507",
391 "cost_per_1m_in": 0.2,
392 "cost_per_1m_out": 0.6,
393 "cost_per_1m_in_cached": 0,
394 "cost_per_1m_out_cached": 0,
395 "context_window": 262144,
396 "default_max_tokens": 26214,
397 "can_reason": false,
398 "supports_attachments": false
399 },
400 {
401 "id": "Qwen/Qwen3-235B-A22B-Thinking-2507",
402 "name": "Qwen3-235B-A22B-Thinking-2507",
403 "cost_per_1m_in": 0.2,
404 "cost_per_1m_out": 0.8,
405 "cost_per_1m_in_cached": 0,
406 "cost_per_1m_out_cached": 0,
407 "context_window": 262144,
408 "default_max_tokens": 26214,
409 "can_reason": true,
410 "reasoning_levels": [
411 "low",
412 "medium",
413 "high"
414 ],
415 "default_reasoning_effort": "medium",
416 "supports_attachments": false
417 },
418 {
419 "id": "Qwen/Qwen3-235B-A22B-Thinking-2507-fast",
420 "name": "Qwen3-235B-A22B-Thinking-2507 (fast)",
421 "cost_per_1m_in": 0.5,
422 "cost_per_1m_out": 2,
423 "cost_per_1m_in_cached": 0,
424 "cost_per_1m_out_cached": 0,
425 "context_window": 8000,
426 "default_max_tokens": 800,
427 "can_reason": true,
428 "reasoning_levels": [
429 "low",
430 "medium",
431 "high"
432 ],
433 "default_reasoning_effort": "medium",
434 "supports_attachments": false
435 },
436 {
437 "id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
438 "name": "Qwen3-30B-A3B-Instruct-2507",
439 "cost_per_1m_in": 0.1,
440 "cost_per_1m_out": 0.3,
441 "cost_per_1m_in_cached": 0,
442 "cost_per_1m_out_cached": 0,
443 "context_window": 262144,
444 "default_max_tokens": 26214,
445 "can_reason": false,
446 "supports_attachments": false
447 },
448 {
449 "id": "Qwen/Qwen3-30B-A3B-Thinking-2507",
450 "name": "Qwen3-30B-A3B-Thinking-2507",
451 "cost_per_1m_in": 0.1,
452 "cost_per_1m_out": 0.3,
453 "cost_per_1m_in_cached": 0,
454 "cost_per_1m_out_cached": 0,
455 "context_window": 262144,
456 "default_max_tokens": 26214,
457 "can_reason": true,
458 "reasoning_levels": [
459 "low",
460 "medium",
461 "high"
462 ],
463 "default_reasoning_effort": "medium",
464 "supports_attachments": false
465 },
466 {
467 "id": "Qwen/Qwen3-32B",
468 "name": "Qwen3-32B",
469 "cost_per_1m_in": 0.1,
470 "cost_per_1m_out": 0.3,
471 "cost_per_1m_in_cached": 0,
472 "cost_per_1m_out_cached": 0,
473 "context_window": 40960,
474 "default_max_tokens": 4096,
475 "can_reason": true,
476 "reasoning_levels": [
477 "low",
478 "medium",
479 "high"
480 ],
481 "default_reasoning_effort": "medium",
482 "supports_attachments": false
483 },
484 {
485 "id": "Qwen/Qwen3-32B-fast",
486 "name": "Qwen3-32B (fast)",
487 "cost_per_1m_in": 0.2,
488 "cost_per_1m_out": 0.6,
489 "cost_per_1m_in_cached": 0,
490 "cost_per_1m_out_cached": 0,
491 "context_window": 40960,
492 "default_max_tokens": 4096,
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 "id": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
504 "name": "Qwen3-Coder-30B-A3B-Instruct",
505 "cost_per_1m_in": 0.1,
506 "cost_per_1m_out": 0.3,
507 "cost_per_1m_in_cached": 0,
508 "cost_per_1m_out_cached": 0,
509 "context_window": 262144,
510 "default_max_tokens": 26214,
511 "can_reason": false,
512 "supports_attachments": false
513 },
514 {
515 "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
516 "name": "Qwen3-Coder-480B-A35B-Instruct",
517 "cost_per_1m_in": 0.4,
518 "cost_per_1m_out": 1.8,
519 "cost_per_1m_in_cached": 0,
520 "cost_per_1m_out_cached": 0,
521 "context_window": 262144,
522 "default_max_tokens": 26214,
523 "can_reason": false,
524 "supports_attachments": false
525 },
526 {
527 "id": "Qwen/Qwen3-Next-80B-A3B-Thinking",
528 "name": "Qwen3-Next-80B-A3B-Thinking",
529 "cost_per_1m_in": 0.15,
530 "cost_per_1m_out": 1.2,
531 "cost_per_1m_in_cached": 0,
532 "cost_per_1m_out_cached": 0,
533 "context_window": 128000,
534 "default_max_tokens": 12800,
535 "can_reason": true,
536 "reasoning_levels": [
537 "low",
538 "medium",
539 "high"
540 ],
541 "default_reasoning_effort": "medium",
542 "supports_attachments": false
543 },
544 {
545 "id": "Qwen/Qwen3-Next-80B-A3B-Thinking-fast",
546 "name": "Qwen3-Next-80B-A3B-Thinking (fast)",
547 "cost_per_1m_in": 0.15,
548 "cost_per_1m_out": 1.2,
549 "cost_per_1m_in_cached": 0,
550 "cost_per_1m_out_cached": 0,
551 "context_window": 8000,
552 "default_max_tokens": 800,
553 "can_reason": true,
554 "reasoning_levels": [
555 "low",
556 "medium",
557 "high"
558 ],
559 "default_reasoning_effort": "medium",
560 "supports_attachments": false
561 },
562 {
563 "id": "Qwen/Qwen3.5-397B-A17B",
564 "name": "Qwen3.5-397B-A17B",
565 "cost_per_1m_in": 0.6,
566 "cost_per_1m_out": 3.6,
567 "cost_per_1m_in_cached": 0,
568 "cost_per_1m_out_cached": 0,
569 "context_window": 262144,
570 "default_max_tokens": 26214,
571 "can_reason": true,
572 "reasoning_levels": [
573 "low",
574 "medium",
575 "high"
576 ],
577 "default_reasoning_effort": "medium",
578 "supports_attachments": false
579 },
580 {
581 "id": "Qwen/Qwen3.5-397B-A17B-fast",
582 "name": "Qwen3.5-397B-A17B (fast)",
583 "cost_per_1m_in": 0.6,
584 "cost_per_1m_out": 3.6,
585 "cost_per_1m_in_cached": 0,
586 "cost_per_1m_out_cached": 0,
587 "context_window": 8000,
588 "default_max_tokens": 800,
589 "can_reason": true,
590 "reasoning_levels": [
591 "low",
592 "medium",
593 "high"
594 ],
595 "default_reasoning_effort": "medium",
596 "supports_attachments": false
597 },
598 {
599 "id": "openai/gpt-oss-120b",
600 "name": "gpt-oss-120b",
601 "cost_per_1m_in": 0.15,
602 "cost_per_1m_out": 0.6,
603 "cost_per_1m_in_cached": 0,
604 "cost_per_1m_out_cached": 0,
605 "context_window": 131072,
606 "default_max_tokens": 13107,
607 "can_reason": true,
608 "reasoning_levels": [
609 "low",
610 "medium",
611 "high"
612 ],
613 "default_reasoning_effort": "medium",
614 "supports_attachments": false
615 },
616 {
617 "id": "openai/gpt-oss-120b-fast",
618 "name": "gpt-oss-120b (fast)",
619 "cost_per_1m_in": 0.1,
620 "cost_per_1m_out": 0.5,
621 "cost_per_1m_in_cached": 0,
622 "cost_per_1m_out_cached": 0,
623 "context_window": 8000,
624 "default_max_tokens": 800,
625 "can_reason": true,
626 "reasoning_levels": [
627 "low",
628 "medium",
629 "high"
630 ],
631 "default_reasoning_effort": "medium",
632 "supports_attachments": false
633 },
634 {
635 "id": "openai/gpt-oss-20b",
636 "name": "gpt-oss-20b",
637 "cost_per_1m_in": 0.05,
638 "cost_per_1m_out": 0.2,
639 "cost_per_1m_in_cached": 0,
640 "cost_per_1m_out_cached": 0,
641 "context_window": 131072,
642 "default_max_tokens": 13107,
643 "can_reason": true,
644 "reasoning_levels": [
645 "low",
646 "medium",
647 "high"
648 ],
649 "default_reasoning_effort": "medium",
650 "supports_attachments": false
651 }
652 ]
653}