1{
2 "name": "Venice AI",
3 "id": "venice",
4 "api_key": "$VENICE_API_KEY",
5 "api_endpoint": "https://api.venice.ai/api/v1",
6 "type": "openai-compat",
7 "default_large_model_id": "claude-opus-4-6",
8 "default_small_model_id": "qwen3-5-35b-a3b",
9 "models": [
10 {
11 "id": "claude-opus-4-5",
12 "name": "Claude Opus 4.5",
13 "cost_per_1m_in": 6,
14 "cost_per_1m_out": 30,
15 "cost_per_1m_in_cached": 0,
16 "cost_per_1m_out_cached": 0,
17 "context_window": 198000,
18 "default_max_tokens": 32768,
19 "can_reason": true,
20 "reasoning_levels": [
21 "low",
22 "medium",
23 "high"
24 ],
25 "default_reasoning_effort": "medium",
26 "supports_attachments": true,
27 "options": {}
28 },
29 {
30 "id": "claude-opus-4-6",
31 "name": "Claude Opus 4.6",
32 "cost_per_1m_in": 6,
33 "cost_per_1m_out": 30,
34 "cost_per_1m_in_cached": 0,
35 "cost_per_1m_out_cached": 0,
36 "context_window": 1000000,
37 "default_max_tokens": 32768,
38 "can_reason": true,
39 "reasoning_levels": [
40 "low",
41 "medium",
42 "high"
43 ],
44 "default_reasoning_effort": "medium",
45 "supports_attachments": true,
46 "options": {}
47 },
48 {
49 "id": "claude-sonnet-4-5",
50 "name": "Claude Sonnet 4.5",
51 "cost_per_1m_in": 3.75,
52 "cost_per_1m_out": 18.75,
53 "cost_per_1m_in_cached": 0,
54 "cost_per_1m_out_cached": 0,
55 "context_window": 198000,
56 "default_max_tokens": 32768,
57 "can_reason": true,
58 "reasoning_levels": [
59 "low",
60 "medium",
61 "high"
62 ],
63 "default_reasoning_effort": "medium",
64 "supports_attachments": true,
65 "options": {}
66 },
67 {
68 "id": "claude-sonnet-4-6",
69 "name": "Claude Sonnet 4.6",
70 "cost_per_1m_in": 3.6,
71 "cost_per_1m_out": 18,
72 "cost_per_1m_in_cached": 0,
73 "cost_per_1m_out_cached": 0,
74 "context_window": 1000000,
75 "default_max_tokens": 32768,
76 "can_reason": true,
77 "reasoning_levels": [
78 "low",
79 "medium",
80 "high"
81 ],
82 "default_reasoning_effort": "medium",
83 "supports_attachments": true,
84 "options": {}
85 },
86 {
87 "id": "zai-org-glm-4.6",
88 "name": "GLM 4.6",
89 "cost_per_1m_in": 0.85,
90 "cost_per_1m_out": 2.75,
91 "cost_per_1m_in_cached": 0,
92 "cost_per_1m_out_cached": 0,
93 "context_window": 198000,
94 "default_max_tokens": 32768,
95 "can_reason": false,
96 "supports_attachments": false,
97 "options": {}
98 },
99 {
100 "id": "zai-org-glm-4.7",
101 "name": "GLM 4.7",
102 "cost_per_1m_in": 0.55,
103 "cost_per_1m_out": 2.65,
104 "cost_per_1m_in_cached": 0,
105 "cost_per_1m_out_cached": 0,
106 "context_window": 198000,
107 "default_max_tokens": 32768,
108 "can_reason": true,
109 "reasoning_levels": [
110 "low",
111 "medium",
112 "high"
113 ],
114 "default_reasoning_effort": "medium",
115 "supports_attachments": false,
116 "options": {}
117 },
118 {
119 "id": "zai-org-glm-4.7-flash",
120 "name": "GLM 4.7 Flash",
121 "cost_per_1m_in": 0.125,
122 "cost_per_1m_out": 0.5,
123 "cost_per_1m_in_cached": 0,
124 "cost_per_1m_out_cached": 0,
125 "context_window": 128000,
126 "default_max_tokens": 32000,
127 "can_reason": true,
128 "reasoning_levels": [
129 "low",
130 "medium",
131 "high"
132 ],
133 "default_reasoning_effort": "medium",
134 "supports_attachments": false,
135 "options": {}
136 },
137 {
138 "id": "olafangensan-glm-4.7-flash-heretic",
139 "name": "GLM 4.7 Flash Heretic",
140 "cost_per_1m_in": 0.14,
141 "cost_per_1m_out": 0.8,
142 "cost_per_1m_in_cached": 0,
143 "cost_per_1m_out_cached": 0,
144 "context_window": 200000,
145 "default_max_tokens": 32768,
146 "can_reason": true,
147 "reasoning_levels": [
148 "low",
149 "medium",
150 "high"
151 ],
152 "default_reasoning_effort": "medium",
153 "supports_attachments": false,
154 "options": {}
155 },
156 {
157 "id": "zai-org-glm-5",
158 "name": "GLM 5",
159 "cost_per_1m_in": 1,
160 "cost_per_1m_out": 3.2,
161 "cost_per_1m_in_cached": 0,
162 "cost_per_1m_out_cached": 0,
163 "context_window": 198000,
164 "default_max_tokens": 32768,
165 "can_reason": true,
166 "reasoning_levels": [
167 "low",
168 "medium",
169 "high"
170 ],
171 "default_reasoning_effort": "medium",
172 "supports_attachments": false,
173 "options": {}
174 },
175 {
176 "id": "openai-gpt-4o-2024-11-20",
177 "name": "GPT-4o",
178 "cost_per_1m_in": 3.125,
179 "cost_per_1m_out": 12.5,
180 "cost_per_1m_in_cached": 0,
181 "cost_per_1m_out_cached": 0,
182 "context_window": 128000,
183 "default_max_tokens": 32000,
184 "can_reason": false,
185 "supports_attachments": true,
186 "options": {}
187 },
188 {
189 "id": "openai-gpt-4o-mini-2024-07-18",
190 "name": "GPT-4o Mini",
191 "cost_per_1m_in": 0.1875,
192 "cost_per_1m_out": 0.75,
193 "cost_per_1m_in_cached": 0,
194 "cost_per_1m_out_cached": 0,
195 "context_window": 128000,
196 "default_max_tokens": 32000,
197 "can_reason": false,
198 "supports_attachments": true,
199 "options": {}
200 },
201 {
202 "id": "openai-gpt-52",
203 "name": "GPT-5.2",
204 "cost_per_1m_in": 2.19,
205 "cost_per_1m_out": 17.5,
206 "cost_per_1m_in_cached": 0,
207 "cost_per_1m_out_cached": 0,
208 "context_window": 256000,
209 "default_max_tokens": 32768,
210 "can_reason": true,
211 "reasoning_levels": [
212 "low",
213 "medium",
214 "high"
215 ],
216 "default_reasoning_effort": "medium",
217 "supports_attachments": false,
218 "options": {}
219 },
220 {
221 "id": "openai-gpt-52-codex",
222 "name": "GPT-5.2 Codex",
223 "cost_per_1m_in": 2.19,
224 "cost_per_1m_out": 17.5,
225 "cost_per_1m_in_cached": 0,
226 "cost_per_1m_out_cached": 0,
227 "context_window": 256000,
228 "default_max_tokens": 32768,
229 "can_reason": true,
230 "reasoning_levels": [
231 "low",
232 "medium",
233 "high"
234 ],
235 "default_reasoning_effort": "medium",
236 "supports_attachments": true,
237 "options": {}
238 },
239 {
240 "id": "openai-gpt-53-codex",
241 "name": "GPT-5.3 Codex",
242 "cost_per_1m_in": 2.19,
243 "cost_per_1m_out": 17.5,
244 "cost_per_1m_in_cached": 0,
245 "cost_per_1m_out_cached": 0,
246 "context_window": 400000,
247 "default_max_tokens": 32768,
248 "can_reason": true,
249 "reasoning_levels": [
250 "low",
251 "medium",
252 "high"
253 ],
254 "default_reasoning_effort": "medium",
255 "supports_attachments": true,
256 "options": {}
257 },
258 {
259 "id": "openai-gpt-54",
260 "name": "GPT-5.4",
261 "cost_per_1m_in": 3.13,
262 "cost_per_1m_out": 18.8,
263 "cost_per_1m_in_cached": 0,
264 "cost_per_1m_out_cached": 0,
265 "context_window": 1000000,
266 "default_max_tokens": 32768,
267 "can_reason": true,
268 "reasoning_levels": [
269 "low",
270 "medium",
271 "high"
272 ],
273 "default_reasoning_effort": "medium",
274 "supports_attachments": true,
275 "options": {}
276 },
277 {
278 "id": "openai-gpt-54-pro",
279 "name": "GPT-5.4 Pro",
280 "cost_per_1m_in": 37.5,
281 "cost_per_1m_out": 225,
282 "cost_per_1m_in_cached": 0,
283 "cost_per_1m_out_cached": 0,
284 "context_window": 1000000,
285 "default_max_tokens": 32768,
286 "can_reason": true,
287 "reasoning_levels": [
288 "low",
289 "medium",
290 "high"
291 ],
292 "default_reasoning_effort": "medium",
293 "supports_attachments": true,
294 "options": {}
295 },
296 {
297 "id": "gemini-3-flash-preview",
298 "name": "Gemini 3 Flash Preview",
299 "cost_per_1m_in": 0.7,
300 "cost_per_1m_out": 3.75,
301 "cost_per_1m_in_cached": 0,
302 "cost_per_1m_out_cached": 0,
303 "context_window": 256000,
304 "default_max_tokens": 32768,
305 "can_reason": true,
306 "reasoning_levels": [
307 "low",
308 "medium",
309 "high"
310 ],
311 "default_reasoning_effort": "medium",
312 "supports_attachments": true,
313 "options": {}
314 },
315 {
316 "id": "gemini-3-pro-preview",
317 "name": "Gemini 3 Pro Preview",
318 "cost_per_1m_in": 2.5,
319 "cost_per_1m_out": 15,
320 "cost_per_1m_in_cached": 0,
321 "cost_per_1m_out_cached": 0,
322 "context_window": 198000,
323 "default_max_tokens": 32768,
324 "can_reason": true,
325 "reasoning_levels": [
326 "low",
327 "medium",
328 "high"
329 ],
330 "default_reasoning_effort": "medium",
331 "supports_attachments": true,
332 "options": {}
333 },
334 {
335 "id": "gemini-3-1-pro-preview",
336 "name": "Gemini 3.1 Pro Preview",
337 "cost_per_1m_in": 2.5,
338 "cost_per_1m_out": 15,
339 "cost_per_1m_in_cached": 0,
340 "cost_per_1m_out_cached": 0,
341 "context_window": 1000000,
342 "default_max_tokens": 32768,
343 "can_reason": true,
344 "reasoning_levels": [
345 "low",
346 "medium",
347 "high"
348 ],
349 "default_reasoning_effort": "medium",
350 "supports_attachments": true,
351 "options": {}
352 },
353 {
354 "id": "google-gemma-3-27b-it",
355 "name": "Google Gemma 3 27B Instruct",
356 "cost_per_1m_in": 0.12,
357 "cost_per_1m_out": 0.2,
358 "cost_per_1m_in_cached": 0,
359 "cost_per_1m_out_cached": 0,
360 "context_window": 198000,
361 "default_max_tokens": 32768,
362 "can_reason": false,
363 "supports_attachments": true,
364 "options": {}
365 },
366 {
367 "id": "grok-41-fast",
368 "name": "Grok 4.1 Fast",
369 "cost_per_1m_in": 0.25,
370 "cost_per_1m_out": 0.625,
371 "cost_per_1m_in_cached": 0,
372 "cost_per_1m_out_cached": 0,
373 "context_window": 1000000,
374 "default_max_tokens": 32768,
375 "can_reason": true,
376 "reasoning_levels": [
377 "low",
378 "medium",
379 "high"
380 ],
381 "default_reasoning_effort": "medium",
382 "supports_attachments": true,
383 "options": {}
384 },
385 {
386 "id": "grok-code-fast-1",
387 "name": "Grok Code Fast 1",
388 "cost_per_1m_in": 0.25,
389 "cost_per_1m_out": 1.87,
390 "cost_per_1m_in_cached": 0,
391 "cost_per_1m_out_cached": 0,
392 "context_window": 256000,
393 "default_max_tokens": 32768,
394 "can_reason": true,
395 "reasoning_levels": [
396 "low",
397 "medium",
398 "high"
399 ],
400 "default_reasoning_effort": "medium",
401 "supports_attachments": false,
402 "options": {}
403 },
404 {
405 "id": "kimi-k2-thinking",
406 "name": "Kimi K2 Thinking",
407 "cost_per_1m_in": 0.75,
408 "cost_per_1m_out": 3.2,
409 "cost_per_1m_in_cached": 0,
410 "cost_per_1m_out_cached": 0,
411 "context_window": 256000,
412 "default_max_tokens": 32768,
413 "can_reason": true,
414 "reasoning_levels": [
415 "low",
416 "medium",
417 "high"
418 ],
419 "default_reasoning_effort": "medium",
420 "supports_attachments": false,
421 "options": {}
422 },
423 {
424 "id": "kimi-k2-5",
425 "name": "Kimi K2.5",
426 "cost_per_1m_in": 0.75,
427 "cost_per_1m_out": 3.75,
428 "cost_per_1m_in_cached": 0,
429 "cost_per_1m_out_cached": 0,
430 "context_window": 256000,
431 "default_max_tokens": 32768,
432 "can_reason": true,
433 "reasoning_levels": [
434 "low",
435 "medium",
436 "high"
437 ],
438 "default_reasoning_effort": "medium",
439 "supports_attachments": true,
440 "options": {}
441 },
442 {
443 "id": "llama-3.2-3b",
444 "name": "Llama 3.2 3B",
445 "cost_per_1m_in": 0.15,
446 "cost_per_1m_out": 0.6,
447 "cost_per_1m_in_cached": 0,
448 "cost_per_1m_out_cached": 0,
449 "context_window": 128000,
450 "default_max_tokens": 32000,
451 "can_reason": false,
452 "supports_attachments": false,
453 "options": {}
454 },
455 {
456 "id": "llama-3.3-70b",
457 "name": "Llama 3.3 70B",
458 "cost_per_1m_in": 0.7,
459 "cost_per_1m_out": 2.8,
460 "cost_per_1m_in_cached": 0,
461 "cost_per_1m_out_cached": 0,
462 "context_window": 128000,
463 "default_max_tokens": 32000,
464 "can_reason": false,
465 "supports_attachments": false,
466 "options": {}
467 },
468 {
469 "id": "minimax-m21",
470 "name": "MiniMax M2.1",
471 "cost_per_1m_in": 0.4,
472 "cost_per_1m_out": 1.6,
473 "cost_per_1m_in_cached": 0,
474 "cost_per_1m_out_cached": 0,
475 "context_window": 198000,
476 "default_max_tokens": 32768,
477 "can_reason": true,
478 "reasoning_levels": [
479 "low",
480 "medium",
481 "high"
482 ],
483 "default_reasoning_effort": "medium",
484 "supports_attachments": false,
485 "options": {}
486 },
487 {
488 "id": "minimax-m25",
489 "name": "MiniMax M2.5",
490 "cost_per_1m_in": 0.4,
491 "cost_per_1m_out": 1.6,
492 "cost_per_1m_in_cached": 0,
493 "cost_per_1m_out_cached": 0,
494 "context_window": 198000,
495 "default_max_tokens": 32768,
496 "can_reason": true,
497 "reasoning_levels": [
498 "low",
499 "medium",
500 "high"
501 ],
502 "default_reasoning_effort": "medium",
503 "supports_attachments": false,
504 "options": {}
505 },
506 {
507 "id": "mistral-small-3-2-24b-instruct",
508 "name": "Mistral Small 3.2 24B Instruct",
509 "cost_per_1m_in": 0.09375,
510 "cost_per_1m_out": 0.25,
511 "cost_per_1m_in_cached": 0,
512 "cost_per_1m_out_cached": 0,
513 "context_window": 256000,
514 "default_max_tokens": 32768,
515 "can_reason": false,
516 "supports_attachments": false,
517 "options": {}
518 },
519 {
520 "id": "nvidia-nemotron-3-nano-30b-a3b",
521 "name": "NVIDIA Nemotron 3 Nano 30B",
522 "cost_per_1m_in": 0.075,
523 "cost_per_1m_out": 0.3,
524 "cost_per_1m_in_cached": 0,
525 "cost_per_1m_out_cached": 0,
526 "context_window": 128000,
527 "default_max_tokens": 32000,
528 "can_reason": false,
529 "supports_attachments": false,
530 "options": {}
531 },
532 {
533 "id": "openai-gpt-oss-120b",
534 "name": "OpenAI GPT OSS 120B",
535 "cost_per_1m_in": 0.07,
536 "cost_per_1m_out": 0.3,
537 "cost_per_1m_in_cached": 0,
538 "cost_per_1m_out_cached": 0,
539 "context_window": 128000,
540 "default_max_tokens": 32000,
541 "can_reason": false,
542 "supports_attachments": false,
543 "options": {}
544 },
545 {
546 "id": "qwen3-235b-a22b-instruct-2507",
547 "name": "Qwen 3 235B A22B Instruct 2507",
548 "cost_per_1m_in": 0.15,
549 "cost_per_1m_out": 0.75,
550 "cost_per_1m_in_cached": 0,
551 "cost_per_1m_out_cached": 0,
552 "context_window": 128000,
553 "default_max_tokens": 32000,
554 "can_reason": false,
555 "supports_attachments": false,
556 "options": {}
557 },
558 {
559 "id": "qwen3-235b-a22b-thinking-2507",
560 "name": "Qwen 3 235B A22B Thinking 2507",
561 "cost_per_1m_in": 0.45,
562 "cost_per_1m_out": 3.5,
563 "cost_per_1m_in_cached": 0,
564 "cost_per_1m_out_cached": 0,
565 "context_window": 128000,
566 "default_max_tokens": 32000,
567 "can_reason": true,
568 "reasoning_levels": [
569 "low",
570 "medium",
571 "high"
572 ],
573 "default_reasoning_effort": "medium",
574 "supports_attachments": false,
575 "options": {}
576 },
577 {
578 "id": "qwen3-coder-480b-a35b-instruct-turbo",
579 "name": "Qwen 3 Coder 480B Turbo",
580 "cost_per_1m_in": 0.35,
581 "cost_per_1m_out": 1.5,
582 "cost_per_1m_in_cached": 0,
583 "cost_per_1m_out_cached": 0,
584 "context_window": 256000,
585 "default_max_tokens": 32768,
586 "can_reason": false,
587 "supports_attachments": false,
588 "options": {}
589 },
590 {
591 "id": "qwen3-coder-480b-a35b-instruct",
592 "name": "Qwen 3 Coder 480b",
593 "cost_per_1m_in": 0.75,
594 "cost_per_1m_out": 3,
595 "cost_per_1m_in_cached": 0,
596 "cost_per_1m_out_cached": 0,
597 "context_window": 256000,
598 "default_max_tokens": 32768,
599 "can_reason": false,
600 "supports_attachments": false,
601 "options": {}
602 },
603 {
604 "id": "qwen3-next-80b",
605 "name": "Qwen 3 Next 80b",
606 "cost_per_1m_in": 0.35,
607 "cost_per_1m_out": 1.9,
608 "cost_per_1m_in_cached": 0,
609 "cost_per_1m_out_cached": 0,
610 "context_window": 256000,
611 "default_max_tokens": 32768,
612 "can_reason": false,
613 "supports_attachments": false,
614 "options": {}
615 },
616 {
617 "id": "qwen3-5-35b-a3b",
618 "name": "Qwen 3.5 35B A3B",
619 "cost_per_1m_in": 0.3125,
620 "cost_per_1m_out": 1.25,
621 "cost_per_1m_in_cached": 0,
622 "cost_per_1m_out_cached": 0,
623 "context_window": 256000,
624 "default_max_tokens": 32768,
625 "can_reason": true,
626 "reasoning_levels": [
627 "low",
628 "medium",
629 "high"
630 ],
631 "default_reasoning_effort": "medium",
632 "supports_attachments": true,
633 "options": {
634 "temperature": 1,
635 "top_p": 0.95
636 }
637 },
638 {
639 "id": "qwen3-vl-235b-a22b",
640 "name": "Qwen3 VL 235B",
641 "cost_per_1m_in": 0.25,
642 "cost_per_1m_out": 1.5,
643 "cost_per_1m_in_cached": 0,
644 "cost_per_1m_out_cached": 0,
645 "context_window": 256000,
646 "default_max_tokens": 32768,
647 "can_reason": false,
648 "supports_attachments": true,
649 "options": {}
650 },
651 {
652 "id": "mistral-31-24b",
653 "name": "Venice Medium",
654 "cost_per_1m_in": 0.5,
655 "cost_per_1m_out": 2,
656 "cost_per_1m_in_cached": 0,
657 "cost_per_1m_out_cached": 0,
658 "context_window": 128000,
659 "default_max_tokens": 32000,
660 "can_reason": false,
661 "supports_attachments": true,
662 "options": {}
663 },
664 {
665 "id": "venice-uncensored-role-play",
666 "name": "Venice Role Play Uncensored",
667 "cost_per_1m_in": 0.5,
668 "cost_per_1m_out": 2,
669 "cost_per_1m_in_cached": 0,
670 "cost_per_1m_out_cached": 0,
671 "context_window": 128000,
672 "default_max_tokens": 32000,
673 "can_reason": false,
674 "supports_attachments": false,
675 "options": {}
676 },
677 {
678 "id": "qwen3-4b",
679 "name": "Venice Small",
680 "cost_per_1m_in": 0.05,
681 "cost_per_1m_out": 0.15,
682 "cost_per_1m_in_cached": 0,
683 "cost_per_1m_out_cached": 0,
684 "context_window": 32000,
685 "default_max_tokens": 8000,
686 "can_reason": true,
687 "reasoning_levels": [
688 "low",
689 "medium",
690 "high"
691 ],
692 "default_reasoning_effort": "medium",
693 "supports_attachments": false,
694 "options": {}
695 }
696 ]
697}