ai_client 0.3.0 → 0.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +15 -0
- data/README.md +278 -9
- data/lib/ai_client/chat.rb +64 -7
- data/lib/ai_client/config.yml +11 -17
- data/lib/ai_client/configuration.rb +12 -1
- data/lib/ai_client/llm.rb +13 -2
- data/lib/ai_client/middleware.rb +2 -2
- data/lib/ai_client/models.yml +526 -416
- data/lib/ai_client/open_router_extensions.rb +63 -94
- data/lib/ai_client/tool.rb +4 -7
- data/lib/ai_client/version.rb +4 -1
- data/lib/ai_client.rb +83 -47
- metadata +3 -3
data/lib/ai_client/models.yml
CHANGED
|
@@ -1,4 +1,186 @@
|
|
|
1
1
|
---
|
|
2
|
+
- :id: mistralai/ministral-8b
|
|
3
|
+
:name: Ministral 8B
|
|
4
|
+
:created: 1729123200
|
|
5
|
+
:description: Ministral 8B is an 8B parameter model featuring a unique interleaved
|
|
6
|
+
sliding-window attention pattern for faster, memory-efficient inference. Designed
|
|
7
|
+
for edge use cases, it supports up to 128k context length and excels in knowledge
|
|
8
|
+
and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect
|
|
9
|
+
for low-latency, privacy-first applications.
|
|
10
|
+
:context_length: 128000
|
|
11
|
+
:architecture:
|
|
12
|
+
modality: text->text
|
|
13
|
+
tokenizer: Mistral
|
|
14
|
+
instruct_type:
|
|
15
|
+
:pricing:
|
|
16
|
+
prompt: '0.0000001'
|
|
17
|
+
completion: '0.0000001'
|
|
18
|
+
image: '0'
|
|
19
|
+
request: '0'
|
|
20
|
+
:top_provider:
|
|
21
|
+
context_length: 128000
|
|
22
|
+
max_completion_tokens:
|
|
23
|
+
is_moderated: false
|
|
24
|
+
:per_request_limits:
|
|
25
|
+
prompt_tokens: '201951527'
|
|
26
|
+
completion_tokens: '201951527'
|
|
27
|
+
- :id: mistralai/ministral-3b
|
|
28
|
+
:name: Ministral 3B
|
|
29
|
+
:created: 1729123200
|
|
30
|
+
:description: Ministral 3B is a 3B parameter model optimized for on-device and edge
|
|
31
|
+
computing. It excels in knowledge, commonsense reasoning, and function-calling,
|
|
32
|
+
outperforming larger models like Mistral 7B on most benchmarks. Supporting up
|
|
33
|
+
to 128k context length, it’s ideal for orchestrating agentic workflows and specialist
|
|
34
|
+
tasks with efficient inference.
|
|
35
|
+
:context_length: 128000
|
|
36
|
+
:architecture:
|
|
37
|
+
modality: text->text
|
|
38
|
+
tokenizer: Mistral
|
|
39
|
+
instruct_type:
|
|
40
|
+
:pricing:
|
|
41
|
+
prompt: '0.00000004'
|
|
42
|
+
completion: '0.00000004'
|
|
43
|
+
image: '0'
|
|
44
|
+
request: '0'
|
|
45
|
+
:top_provider:
|
|
46
|
+
context_length: 128000
|
|
47
|
+
max_completion_tokens:
|
|
48
|
+
is_moderated: false
|
|
49
|
+
:per_request_limits:
|
|
50
|
+
prompt_tokens: '504878818'
|
|
51
|
+
completion_tokens: '504878818'
|
|
52
|
+
- :id: qwen/qwen-2.5-7b-instruct
|
|
53
|
+
:name: Qwen2.5 7B Instruct
|
|
54
|
+
:created: 1729036800
|
|
55
|
+
:description: |-
|
|
56
|
+
Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:
|
|
57
|
+
|
|
58
|
+
- Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.
|
|
59
|
+
|
|
60
|
+
- Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.
|
|
61
|
+
|
|
62
|
+
- Long-context Support up to 128K tokens and can generate up to 8K tokens.
|
|
63
|
+
|
|
64
|
+
- Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
|
|
65
|
+
|
|
66
|
+
Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).
|
|
67
|
+
:context_length: 131072
|
|
68
|
+
:architecture:
|
|
69
|
+
modality: text->text
|
|
70
|
+
tokenizer: Qwen
|
|
71
|
+
instruct_type: chatml
|
|
72
|
+
:pricing:
|
|
73
|
+
prompt: '0.00000027'
|
|
74
|
+
completion: '0.00000027'
|
|
75
|
+
image: '0'
|
|
76
|
+
request: '0'
|
|
77
|
+
:top_provider:
|
|
78
|
+
context_length: 32768
|
|
79
|
+
max_completion_tokens:
|
|
80
|
+
is_moderated: false
|
|
81
|
+
:per_request_limits:
|
|
82
|
+
prompt_tokens: '74796862'
|
|
83
|
+
completion_tokens: '74796862'
|
|
84
|
+
- :id: nvidia/llama-3.1-nemotron-70b-instruct
|
|
85
|
+
:name: 'NVIDIA: Llama 3.1 Nemotron 70B Instruct'
|
|
86
|
+
:created: 1728950400
|
|
87
|
+
:description: |-
|
|
88
|
+
NVIDIA's Llama 3.1 Nemotron 70B is a language model designed for generating precise and useful responses. Leveraging [Llama 3.1 70B](/models/meta-llama/llama-3.1-70b-instruct) architecture and Reinforcement Learning from Human Feedback (RLHF), it excels in automatic alignment benchmarks. This model is tailored for applications requiring high accuracy in helpfulness and response generation, suitable for diverse user queries across multiple domains.
|
|
89
|
+
|
|
90
|
+
Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).
|
|
91
|
+
:context_length: 131072
|
|
92
|
+
:architecture:
|
|
93
|
+
modality: text->text
|
|
94
|
+
tokenizer: Llama3
|
|
95
|
+
instruct_type: llama3
|
|
96
|
+
:pricing:
|
|
97
|
+
prompt: '0.00000035'
|
|
98
|
+
completion: '0.0000004'
|
|
99
|
+
image: '0'
|
|
100
|
+
request: '0'
|
|
101
|
+
:top_provider:
|
|
102
|
+
context_length: 131072
|
|
103
|
+
max_completion_tokens:
|
|
104
|
+
is_moderated: false
|
|
105
|
+
:per_request_limits:
|
|
106
|
+
prompt_tokens: '57700436'
|
|
107
|
+
completion_tokens: '50487881'
|
|
108
|
+
- :id: x-ai/grok-2
|
|
109
|
+
:name: 'xAI: Grok 2'
|
|
110
|
+
:created: 1728691200
|
|
111
|
+
:description: |-
|
|
112
|
+
Grok 2 is xAI's frontier language model with state-of-the-art reasoning capabilities, best for complex and multi-step use cases.
|
|
113
|
+
|
|
114
|
+
To use a faster version, see [Grok 2 Mini](/x-ai/grok-2-mini).
|
|
115
|
+
|
|
116
|
+
For more information, see the [launch announcement](https://x.ai/blog/grok-2).
|
|
117
|
+
:context_length: 32768
|
|
118
|
+
:architecture:
|
|
119
|
+
modality: text->text
|
|
120
|
+
tokenizer: Grok
|
|
121
|
+
instruct_type:
|
|
122
|
+
:pricing:
|
|
123
|
+
prompt: '0.000005'
|
|
124
|
+
completion: '0.00001'
|
|
125
|
+
image: '0'
|
|
126
|
+
request: '0'
|
|
127
|
+
:top_provider:
|
|
128
|
+
context_length: 32768
|
|
129
|
+
max_completion_tokens:
|
|
130
|
+
is_moderated: false
|
|
131
|
+
:per_request_limits:
|
|
132
|
+
prompt_tokens: '4039030'
|
|
133
|
+
completion_tokens: '2019515'
|
|
134
|
+
- :id: inflection/inflection-3-pi
|
|
135
|
+
:name: 'Inflection: Inflection 3 Pi'
|
|
136
|
+
:created: 1728604800
|
|
137
|
+
:description: |-
|
|
138
|
+
Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and roleplay.
|
|
139
|
+
|
|
140
|
+
Pi has been trained to mirror your tone and style, if you use more emojis, so will Pi! Try experimenting with various prompts and conversation styles.
|
|
141
|
+
:context_length: 8000
|
|
142
|
+
:architecture:
|
|
143
|
+
modality: text->text
|
|
144
|
+
tokenizer: Other
|
|
145
|
+
instruct_type:
|
|
146
|
+
:pricing:
|
|
147
|
+
prompt: '0.0000025'
|
|
148
|
+
completion: '0.00001'
|
|
149
|
+
image: '0'
|
|
150
|
+
request: '0'
|
|
151
|
+
:top_provider:
|
|
152
|
+
context_length: 8000
|
|
153
|
+
max_completion_tokens:
|
|
154
|
+
is_moderated: false
|
|
155
|
+
:per_request_limits:
|
|
156
|
+
prompt_tokens: '8078061'
|
|
157
|
+
completion_tokens: '2019515'
|
|
158
|
+
- :id: inflection/inflection-3-productivity
|
|
159
|
+
:name: 'Inflection: Inflection 3 Productivity'
|
|
160
|
+
:created: 1728604800
|
|
161
|
+
:description: |-
|
|
162
|
+
Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news.
|
|
163
|
+
|
|
164
|
+
For emotional intelligence similar to Pi, see [Inflect 3 Pi](/inflection/inflection-3-pi)
|
|
165
|
+
|
|
166
|
+
See [Inflection's announcement](https://inflection.ai/blog/enterprise) for more details.
|
|
167
|
+
:context_length: 8000
|
|
168
|
+
:architecture:
|
|
169
|
+
modality: text->text
|
|
170
|
+
tokenizer: Other
|
|
171
|
+
instruct_type:
|
|
172
|
+
:pricing:
|
|
173
|
+
prompt: '0.0000025'
|
|
174
|
+
completion: '0.00001'
|
|
175
|
+
image: '0'
|
|
176
|
+
request: '0'
|
|
177
|
+
:top_provider:
|
|
178
|
+
context_length: 8000
|
|
179
|
+
max_completion_tokens:
|
|
180
|
+
is_moderated: false
|
|
181
|
+
:per_request_limits:
|
|
182
|
+
prompt_tokens: '8078061'
|
|
183
|
+
completion_tokens: '2019515'
|
|
2
184
|
- :id: google/gemini-flash-1.5-8b
|
|
3
185
|
:name: 'Google: Gemini 1.5 Flash-8B'
|
|
4
186
|
:created: 1727913600
|
|
@@ -23,8 +205,8 @@
|
|
|
23
205
|
max_completion_tokens: 8192
|
|
24
206
|
is_moderated: false
|
|
25
207
|
:per_request_limits:
|
|
26
|
-
prompt_tokens: '
|
|
27
|
-
completion_tokens: '
|
|
208
|
+
prompt_tokens: '538537406'
|
|
209
|
+
completion_tokens: '134634351'
|
|
28
210
|
- :id: liquid/lfm-40b
|
|
29
211
|
:name: 'Liquid: LFM 40B MoE'
|
|
30
212
|
:created: 1727654400
|
|
@@ -62,7 +244,7 @@
|
|
|
62
244
|
See the [launch announcement](https://www.liquid.ai/liquid-foundation-models) for benchmarks and more info.
|
|
63
245
|
|
|
64
246
|
_These are free, rate-limited endpoints for [LFM 40B MoE](/liquid/lfm-40b). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
65
|
-
:context_length:
|
|
247
|
+
:context_length: 8192
|
|
66
248
|
:architecture:
|
|
67
249
|
modality: text->text
|
|
68
250
|
tokenizer: Other
|
|
@@ -104,8 +286,8 @@
|
|
|
104
286
|
max_completion_tokens:
|
|
105
287
|
is_moderated: false
|
|
106
288
|
:per_request_limits:
|
|
107
|
-
prompt_tokens: '
|
|
108
|
-
completion_tokens: '
|
|
289
|
+
prompt_tokens: '80780611'
|
|
290
|
+
completion_tokens: '40390305'
|
|
109
291
|
- :id: eva-unit-01/eva-qwen-2.5-14b
|
|
110
292
|
:name: EVA Qwen2.5 14B
|
|
111
293
|
:created: 1727654400
|
|
@@ -128,8 +310,8 @@
|
|
|
128
310
|
max_completion_tokens:
|
|
129
311
|
is_moderated: false
|
|
130
312
|
:per_request_limits:
|
|
131
|
-
prompt_tokens: '
|
|
132
|
-
completion_tokens: '
|
|
313
|
+
prompt_tokens: '80780611'
|
|
314
|
+
completion_tokens: '40390305'
|
|
133
315
|
- :id: anthracite-org/magnum-v2-72b
|
|
134
316
|
:name: Magnum v2 72B
|
|
135
317
|
:created: 1727654400
|
|
@@ -152,8 +334,8 @@
|
|
|
152
334
|
max_completion_tokens:
|
|
153
335
|
is_moderated: false
|
|
154
336
|
:per_request_limits:
|
|
155
|
-
prompt_tokens: '
|
|
156
|
-
completion_tokens: '
|
|
337
|
+
prompt_tokens: '5385374'
|
|
338
|
+
completion_tokens: '4487811'
|
|
157
339
|
- :id: meta-llama/llama-3.2-3b-instruct:free
|
|
158
340
|
:name: 'Meta: Llama 3.2 3B Instruct (free)'
|
|
159
341
|
:created: 1727222400
|
|
@@ -167,7 +349,7 @@
|
|
|
167
349
|
Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).
|
|
168
350
|
|
|
169
351
|
_These are free, rate-limited endpoints for [Llama 3.2 3B Instruct](/meta-llama/llama-3.2-3b-instruct). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
170
|
-
:context_length:
|
|
352
|
+
:context_length: 4096
|
|
171
353
|
:architecture:
|
|
172
354
|
modality: text->text
|
|
173
355
|
tokenizer: Llama3
|
|
@@ -210,8 +392,8 @@
|
|
|
210
392
|
max_completion_tokens:
|
|
211
393
|
is_moderated: false
|
|
212
394
|
:per_request_limits:
|
|
213
|
-
prompt_tokens: '
|
|
214
|
-
completion_tokens: '
|
|
395
|
+
prompt_tokens: '673171758'
|
|
396
|
+
completion_tokens: '403903055'
|
|
215
397
|
- :id: meta-llama/llama-3.2-1b-instruct:free
|
|
216
398
|
:name: 'Meta: Llama 3.2 1B Instruct (free)'
|
|
217
399
|
:created: 1727222400
|
|
@@ -225,7 +407,7 @@
|
|
|
225
407
|
Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).
|
|
226
408
|
|
|
227
409
|
_These are free, rate-limited endpoints for [Llama 3.2 1B Instruct](/meta-llama/llama-3.2-1b-instruct). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
228
|
-
:context_length:
|
|
410
|
+
:context_length: 4096
|
|
229
411
|
:architecture:
|
|
230
412
|
modality: text->text
|
|
231
413
|
tokenizer: Llama3
|
|
@@ -268,8 +450,8 @@
|
|
|
268
450
|
max_completion_tokens:
|
|
269
451
|
is_moderated: false
|
|
270
452
|
:per_request_limits:
|
|
271
|
-
prompt_tokens: '
|
|
272
|
-
completion_tokens: '
|
|
453
|
+
prompt_tokens: '2019515275'
|
|
454
|
+
completion_tokens: '1009757637'
|
|
273
455
|
- :id: meta-llama/llama-3.2-90b-vision-instruct
|
|
274
456
|
:name: 'Meta: Llama 3.2 90B Vision Instruct'
|
|
275
457
|
:created: 1727222400
|
|
@@ -296,8 +478,8 @@
|
|
|
296
478
|
max_completion_tokens:
|
|
297
479
|
is_moderated: false
|
|
298
480
|
:per_request_limits:
|
|
299
|
-
prompt_tokens: '
|
|
300
|
-
completion_tokens: '
|
|
481
|
+
prompt_tokens: '57700436'
|
|
482
|
+
completion_tokens: '50487881'
|
|
301
483
|
- :id: meta-llama/llama-3.2-11b-vision-instruct:free
|
|
302
484
|
:name: 'Meta: Llama 3.2 11B Vision Instruct (free)'
|
|
303
485
|
:created: 1727222400
|
|
@@ -311,7 +493,7 @@
|
|
|
311
493
|
Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).
|
|
312
494
|
|
|
313
495
|
_These are free, rate-limited endpoints for [Llama 3.2 11B Vision Instruct](/meta-llama/llama-3.2-11b-vision-instruct). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
314
|
-
:context_length:
|
|
496
|
+
:context_length: 8192
|
|
315
497
|
:architecture:
|
|
316
498
|
modality: text+image->text
|
|
317
499
|
tokenizer: Llama3
|
|
@@ -354,8 +536,8 @@
|
|
|
354
536
|
max_completion_tokens:
|
|
355
537
|
is_moderated: false
|
|
356
538
|
:per_request_limits:
|
|
357
|
-
prompt_tokens: '
|
|
358
|
-
completion_tokens: '
|
|
539
|
+
prompt_tokens: '367184595'
|
|
540
|
+
completion_tokens: '367184595'
|
|
359
541
|
- :id: qwen/qwen-2.5-72b-instruct
|
|
360
542
|
:name: Qwen2.5 72B Instruct
|
|
361
543
|
:created: 1726704000
|
|
@@ -373,7 +555,7 @@
|
|
|
373
555
|
Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).
|
|
374
556
|
:context_length: 131072
|
|
375
557
|
:architecture:
|
|
376
|
-
modality: text
|
|
558
|
+
modality: text->text
|
|
377
559
|
tokenizer: Qwen
|
|
378
560
|
instruct_type: chatml
|
|
379
561
|
:pricing:
|
|
@@ -386,8 +568,8 @@
|
|
|
386
568
|
max_completion_tokens:
|
|
387
569
|
is_moderated: false
|
|
388
570
|
:per_request_limits:
|
|
389
|
-
prompt_tokens: '
|
|
390
|
-
completion_tokens: '
|
|
571
|
+
prompt_tokens: '57700436'
|
|
572
|
+
completion_tokens: '50487881'
|
|
391
573
|
- :id: qwen/qwen-2-vl-72b-instruct
|
|
392
574
|
:name: Qwen2-VL 72B Instruct
|
|
393
575
|
:created: 1726617600
|
|
@@ -420,8 +602,8 @@
|
|
|
420
602
|
max_completion_tokens:
|
|
421
603
|
is_moderated: false
|
|
422
604
|
:per_request_limits:
|
|
423
|
-
prompt_tokens: '
|
|
424
|
-
completion_tokens: '
|
|
605
|
+
prompt_tokens: '50487881'
|
|
606
|
+
completion_tokens: '50487881'
|
|
425
607
|
- :id: neversleep/llama-3.1-lumimaid-8b
|
|
426
608
|
:name: Lumimaid v0.2 8B
|
|
427
609
|
:created: 1726358400
|
|
@@ -444,8 +626,8 @@
|
|
|
444
626
|
max_completion_tokens: 2048
|
|
445
627
|
is_moderated: false
|
|
446
628
|
:per_request_limits:
|
|
447
|
-
prompt_tokens: '
|
|
448
|
-
completion_tokens: '
|
|
629
|
+
prompt_tokens: '107707481'
|
|
630
|
+
completion_tokens: '17951246'
|
|
449
631
|
- :id: openai/o1-mini-2024-09-12
|
|
450
632
|
:name: 'OpenAI: o1-mini (2024-09-12)'
|
|
451
633
|
:created: 1726099200
|
|
@@ -470,8 +652,8 @@
|
|
|
470
652
|
max_completion_tokens: 65536
|
|
471
653
|
is_moderated: true
|
|
472
654
|
:per_request_limits:
|
|
473
|
-
prompt_tokens: '
|
|
474
|
-
completion_tokens: '
|
|
655
|
+
prompt_tokens: '6731717'
|
|
656
|
+
completion_tokens: '1682929'
|
|
475
657
|
- :id: openai/o1-mini
|
|
476
658
|
:name: 'OpenAI: o1-mini'
|
|
477
659
|
:created: 1726099200
|
|
@@ -496,8 +678,8 @@
|
|
|
496
678
|
max_completion_tokens: 65536
|
|
497
679
|
is_moderated: true
|
|
498
680
|
:per_request_limits:
|
|
499
|
-
prompt_tokens: '
|
|
500
|
-
completion_tokens: '
|
|
681
|
+
prompt_tokens: '6731717'
|
|
682
|
+
completion_tokens: '1682929'
|
|
501
683
|
- :id: openai/o1-preview-2024-09-12
|
|
502
684
|
:name: 'OpenAI: o1-preview (2024-09-12)'
|
|
503
685
|
:created: 1726099200
|
|
@@ -522,8 +704,8 @@
|
|
|
522
704
|
max_completion_tokens: 32768
|
|
523
705
|
is_moderated: true
|
|
524
706
|
:per_request_limits:
|
|
525
|
-
prompt_tokens: '
|
|
526
|
-
completion_tokens: '
|
|
707
|
+
prompt_tokens: '1346343'
|
|
708
|
+
completion_tokens: '336585'
|
|
527
709
|
- :id: openai/o1-preview
|
|
528
710
|
:name: 'OpenAI: o1-preview'
|
|
529
711
|
:created: 1726099200
|
|
@@ -548,8 +730,8 @@
|
|
|
548
730
|
max_completion_tokens: 32768
|
|
549
731
|
is_moderated: true
|
|
550
732
|
:per_request_limits:
|
|
551
|
-
prompt_tokens: '
|
|
552
|
-
completion_tokens: '
|
|
733
|
+
prompt_tokens: '1346343'
|
|
734
|
+
completion_tokens: '336585'
|
|
553
735
|
- :id: mistralai/pixtral-12b
|
|
554
736
|
:name: 'Mistral: Pixtral 12B'
|
|
555
737
|
:created: 1725926400
|
|
@@ -570,8 +752,8 @@
|
|
|
570
752
|
max_completion_tokens:
|
|
571
753
|
is_moderated: false
|
|
572
754
|
:per_request_limits:
|
|
573
|
-
prompt_tokens: '
|
|
574
|
-
completion_tokens: '
|
|
755
|
+
prompt_tokens: '201951527'
|
|
756
|
+
completion_tokens: '201951527'
|
|
575
757
|
- :id: cohere/command-r-plus-08-2024
|
|
576
758
|
:name: 'Cohere: Command R+ (08-2024)'
|
|
577
759
|
:created: 1724976000
|
|
@@ -596,8 +778,8 @@
|
|
|
596
778
|
max_completion_tokens: 4000
|
|
597
779
|
is_moderated: false
|
|
598
780
|
:per_request_limits:
|
|
599
|
-
prompt_tokens: '
|
|
600
|
-
completion_tokens: '
|
|
781
|
+
prompt_tokens: '8503222'
|
|
782
|
+
completion_tokens: '2125805'
|
|
601
783
|
- :id: cohere/command-r-08-2024
|
|
602
784
|
:name: 'Cohere: Command R (08-2024)'
|
|
603
785
|
:created: 1724976000
|
|
@@ -622,8 +804,8 @@
|
|
|
622
804
|
max_completion_tokens: 4000
|
|
623
805
|
is_moderated: false
|
|
624
806
|
:per_request_limits:
|
|
625
|
-
prompt_tokens: '
|
|
626
|
-
completion_tokens: '
|
|
807
|
+
prompt_tokens: '141720370'
|
|
808
|
+
completion_tokens: '35430092'
|
|
627
809
|
- :id: qwen/qwen-2-vl-7b-instruct
|
|
628
810
|
:name: Qwen2-VL 7B Instruct
|
|
629
811
|
:created: 1724803200
|
|
@@ -656,8 +838,8 @@
|
|
|
656
838
|
max_completion_tokens:
|
|
657
839
|
is_moderated: false
|
|
658
840
|
:per_request_limits:
|
|
659
|
-
prompt_tokens: '
|
|
660
|
-
completion_tokens: '
|
|
841
|
+
prompt_tokens: '201951527'
|
|
842
|
+
completion_tokens: '201951527'
|
|
661
843
|
- :id: google/gemini-flash-1.5-8b-exp
|
|
662
844
|
:name: 'Google: Gemini Flash 8B 1.5 Experimental'
|
|
663
845
|
:created: 1724803200
|
|
@@ -706,8 +888,8 @@
|
|
|
706
888
|
max_completion_tokens:
|
|
707
889
|
is_moderated: false
|
|
708
890
|
:per_request_limits:
|
|
709
|
-
prompt_tokens: '
|
|
710
|
-
completion_tokens: '
|
|
891
|
+
prompt_tokens: '57700436'
|
|
892
|
+
completion_tokens: '50487881'
|
|
711
893
|
- :id: google/gemini-flash-1.5-exp
|
|
712
894
|
:name: 'Google: Gemini Flash 1.5 Experimental'
|
|
713
895
|
:created: 1724803200
|
|
@@ -762,8 +944,8 @@
|
|
|
762
944
|
max_completion_tokens: 4096
|
|
763
945
|
is_moderated: false
|
|
764
946
|
:per_request_limits:
|
|
765
|
-
prompt_tokens: '
|
|
766
|
-
completion_tokens: '
|
|
947
|
+
prompt_tokens: '10097576'
|
|
948
|
+
completion_tokens: '2524394'
|
|
767
949
|
- :id: ai21/jamba-1-5-mini
|
|
768
950
|
:name: 'AI21: Jamba 1.5 Mini'
|
|
769
951
|
:created: 1724371200
|
|
@@ -790,8 +972,8 @@
|
|
|
790
972
|
max_completion_tokens: 4096
|
|
791
973
|
is_moderated: false
|
|
792
974
|
:per_request_limits:
|
|
793
|
-
prompt_tokens: '
|
|
794
|
-
completion_tokens: '
|
|
975
|
+
prompt_tokens: '100975763'
|
|
976
|
+
completion_tokens: '50487881'
|
|
795
977
|
- :id: microsoft/phi-3.5-mini-128k-instruct
|
|
796
978
|
:name: Phi-3.5 Mini 128K Instruct
|
|
797
979
|
:created: 1724198400
|
|
@@ -814,8 +996,8 @@
|
|
|
814
996
|
max_completion_tokens:
|
|
815
997
|
is_moderated: false
|
|
816
998
|
:per_request_limits:
|
|
817
|
-
prompt_tokens: '
|
|
818
|
-
completion_tokens: '
|
|
999
|
+
prompt_tokens: '201951527'
|
|
1000
|
+
completion_tokens: '201951527'
|
|
819
1001
|
- :id: nousresearch/hermes-3-llama-3.1-70b
|
|
820
1002
|
:name: 'Nous: Hermes 3 70B Instruct'
|
|
821
1003
|
:created: 1723939200
|
|
@@ -840,8 +1022,8 @@
|
|
|
840
1022
|
max_completion_tokens:
|
|
841
1023
|
is_moderated: false
|
|
842
1024
|
:per_request_limits:
|
|
843
|
-
prompt_tokens: '
|
|
844
|
-
completion_tokens: '
|
|
1025
|
+
prompt_tokens: '50487881'
|
|
1026
|
+
completion_tokens: '50487881'
|
|
845
1027
|
- :id: nousresearch/hermes-3-llama-3.1-405b:free
|
|
846
1028
|
:name: 'Nous: Hermes 3 405B Instruct (free)'
|
|
847
1029
|
:created: 1723766400
|
|
@@ -855,7 +1037,7 @@
|
|
|
855
1037
|
Hermes 3 is competitive, if not superior, to Llama-3.1 Instruct models at general capabilities, with varying strengths and weaknesses attributable between the two.
|
|
856
1038
|
|
|
857
1039
|
_These are free, rate-limited endpoints for [Hermes 3 405B Instruct](/nousresearch/hermes-3-llama-3.1-405b). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
858
|
-
:context_length:
|
|
1040
|
+
:context_length: 8192
|
|
859
1041
|
:architecture:
|
|
860
1042
|
modality: text->text
|
|
861
1043
|
tokenizer: Llama3
|
|
@@ -889,17 +1071,17 @@
|
|
|
889
1071
|
tokenizer: Llama3
|
|
890
1072
|
instruct_type: chatml
|
|
891
1073
|
:pricing:
|
|
892
|
-
prompt: '0.
|
|
893
|
-
completion: '0.
|
|
1074
|
+
prompt: '0.00000179'
|
|
1075
|
+
completion: '0.00000249'
|
|
894
1076
|
image: '0'
|
|
895
1077
|
request: '0'
|
|
896
1078
|
:top_provider:
|
|
897
|
-
context_length:
|
|
1079
|
+
context_length: 131072
|
|
898
1080
|
max_completion_tokens:
|
|
899
1081
|
is_moderated: false
|
|
900
1082
|
:per_request_limits:
|
|
901
|
-
prompt_tokens: '
|
|
902
|
-
completion_tokens: '
|
|
1083
|
+
prompt_tokens: '11282208'
|
|
1084
|
+
completion_tokens: '8110503'
|
|
903
1085
|
- :id: nousresearch/hermes-3-llama-3.1-405b:extended
|
|
904
1086
|
:name: 'Nous: Hermes 3 405B Instruct (extended)'
|
|
905
1087
|
:created: 1723766400
|
|
@@ -928,8 +1110,8 @@
|
|
|
928
1110
|
max_completion_tokens:
|
|
929
1111
|
is_moderated: false
|
|
930
1112
|
:per_request_limits:
|
|
931
|
-
prompt_tokens: '
|
|
932
|
-
completion_tokens: '
|
|
1113
|
+
prompt_tokens: '4487811'
|
|
1114
|
+
completion_tokens: '4487811'
|
|
933
1115
|
- :id: perplexity/llama-3.1-sonar-huge-128k-online
|
|
934
1116
|
:name: 'Perplexity: Llama 3.1 Sonar 405B Online'
|
|
935
1117
|
:created: 1723593600
|
|
@@ -951,8 +1133,8 @@
|
|
|
951
1133
|
max_completion_tokens:
|
|
952
1134
|
is_moderated: false
|
|
953
1135
|
:per_request_limits:
|
|
954
|
-
prompt_tokens: '
|
|
955
|
-
completion_tokens: '
|
|
1136
|
+
prompt_tokens: '4039030'
|
|
1137
|
+
completion_tokens: '4039030'
|
|
956
1138
|
- :id: openai/chatgpt-4o-latest
|
|
957
1139
|
:name: 'OpenAI: ChatGPT-4o'
|
|
958
1140
|
:created: 1723593600
|
|
@@ -975,8 +1157,8 @@
|
|
|
975
1157
|
max_completion_tokens: 16384
|
|
976
1158
|
is_moderated: true
|
|
977
1159
|
:per_request_limits:
|
|
978
|
-
prompt_tokens: '
|
|
979
|
-
completion_tokens: '
|
|
1160
|
+
prompt_tokens: '4039030'
|
|
1161
|
+
completion_tokens: '1346343'
|
|
980
1162
|
- :id: sao10k/l3-lunaris-8b
|
|
981
1163
|
:name: Llama 3 8B Lunaris
|
|
982
1164
|
:created: 1723507200
|
|
@@ -1001,8 +1183,8 @@
|
|
|
1001
1183
|
max_completion_tokens:
|
|
1002
1184
|
is_moderated: false
|
|
1003
1185
|
:per_request_limits:
|
|
1004
|
-
prompt_tokens: '
|
|
1005
|
-
completion_tokens: '
|
|
1186
|
+
prompt_tokens: '10097576'
|
|
1187
|
+
completion_tokens: '10097576'
|
|
1006
1188
|
- :id: aetherwiing/mn-starcannon-12b
|
|
1007
1189
|
:name: Mistral Nemo 12B Starcannon
|
|
1008
1190
|
:created: 1723507200
|
|
@@ -1025,8 +1207,8 @@
|
|
|
1025
1207
|
max_completion_tokens:
|
|
1026
1208
|
is_moderated: false
|
|
1027
1209
|
:per_request_limits:
|
|
1028
|
-
prompt_tokens: '
|
|
1029
|
-
completion_tokens: '
|
|
1210
|
+
prompt_tokens: '10097576'
|
|
1211
|
+
completion_tokens: '10097576'
|
|
1030
1212
|
- :id: openai/gpt-4o-2024-08-06
|
|
1031
1213
|
:name: 'OpenAI: GPT-4o (2024-08-06)'
|
|
1032
1214
|
:created: 1722902400
|
|
@@ -1051,8 +1233,8 @@
|
|
|
1051
1233
|
max_completion_tokens: 16384
|
|
1052
1234
|
is_moderated: true
|
|
1053
1235
|
:per_request_limits:
|
|
1054
|
-
prompt_tokens: '
|
|
1055
|
-
completion_tokens: '
|
|
1236
|
+
prompt_tokens: '8078061'
|
|
1237
|
+
completion_tokens: '2019515'
|
|
1056
1238
|
- :id: meta-llama/llama-3.1-405b
|
|
1057
1239
|
:name: 'Meta: Llama 3.1 405B (base)'
|
|
1058
1240
|
:created: 1722556800
|
|
@@ -1077,8 +1259,8 @@
|
|
|
1077
1259
|
max_completion_tokens:
|
|
1078
1260
|
is_moderated: false
|
|
1079
1261
|
:per_request_limits:
|
|
1080
|
-
prompt_tokens: '
|
|
1081
|
-
completion_tokens: '
|
|
1262
|
+
prompt_tokens: '10097576'
|
|
1263
|
+
completion_tokens: '10097576'
|
|
1082
1264
|
- :id: nothingiisreal/mn-celeste-12b
|
|
1083
1265
|
:name: Mistral Nemo 12B Celeste
|
|
1084
1266
|
:created: 1722556800
|
|
@@ -1103,8 +1285,8 @@
|
|
|
1103
1285
|
max_completion_tokens:
|
|
1104
1286
|
is_moderated: false
|
|
1105
1287
|
:per_request_limits:
|
|
1106
|
-
prompt_tokens: '
|
|
1107
|
-
completion_tokens: '
|
|
1288
|
+
prompt_tokens: '13463435'
|
|
1289
|
+
completion_tokens: '13463435'
|
|
1108
1290
|
- :id: google/gemini-pro-1.5-exp
|
|
1109
1291
|
:name: 'Google: Gemini Pro 1.5 Experimental'
|
|
1110
1292
|
:created: 1722470400
|
|
@@ -1155,8 +1337,8 @@
|
|
|
1155
1337
|
max_completion_tokens:
|
|
1156
1338
|
is_moderated: false
|
|
1157
1339
|
:per_request_limits:
|
|
1158
|
-
prompt_tokens: '
|
|
1159
|
-
completion_tokens: '
|
|
1340
|
+
prompt_tokens: '20195152'
|
|
1341
|
+
completion_tokens: '20195152'
|
|
1160
1342
|
- :id: perplexity/llama-3.1-sonar-large-128k-chat
|
|
1161
1343
|
:name: 'Perplexity: Llama 3.1 Sonar 70B'
|
|
1162
1344
|
:created: 1722470400
|
|
@@ -1179,8 +1361,8 @@
|
|
|
1179
1361
|
max_completion_tokens:
|
|
1180
1362
|
is_moderated: false
|
|
1181
1363
|
:per_request_limits:
|
|
1182
|
-
prompt_tokens: '
|
|
1183
|
-
completion_tokens: '
|
|
1364
|
+
prompt_tokens: '20195152'
|
|
1365
|
+
completion_tokens: '20195152'
|
|
1184
1366
|
- :id: perplexity/llama-3.1-sonar-small-128k-online
|
|
1185
1367
|
:name: 'Perplexity: Llama 3.1 Sonar 8B Online'
|
|
1186
1368
|
:created: 1722470400
|
|
@@ -1203,8 +1385,8 @@
|
|
|
1203
1385
|
max_completion_tokens:
|
|
1204
1386
|
is_moderated: false
|
|
1205
1387
|
:per_request_limits:
|
|
1206
|
-
prompt_tokens: '
|
|
1207
|
-
completion_tokens: '
|
|
1388
|
+
prompt_tokens: '100975763'
|
|
1389
|
+
completion_tokens: '100975763'
|
|
1208
1390
|
- :id: perplexity/llama-3.1-sonar-small-128k-chat
|
|
1209
1391
|
:name: 'Perplexity: Llama 3.1 Sonar 8B'
|
|
1210
1392
|
:created: 1722470400
|
|
@@ -1227,8 +1409,8 @@
|
|
|
1227
1409
|
max_completion_tokens:
|
|
1228
1410
|
is_moderated: false
|
|
1229
1411
|
:per_request_limits:
|
|
1230
|
-
prompt_tokens: '
|
|
1231
|
-
completion_tokens: '
|
|
1412
|
+
prompt_tokens: '100975763'
|
|
1413
|
+
completion_tokens: '100975763'
|
|
1232
1414
|
- :id: meta-llama/llama-3.1-70b-instruct:free
|
|
1233
1415
|
:name: 'Meta: Llama 3.1 70B Instruct (free)'
|
|
1234
1416
|
:created: 1721692800
|
|
@@ -1240,7 +1422,7 @@
|
|
|
1240
1422
|
Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).
|
|
1241
1423
|
|
|
1242
1424
|
_These are free, rate-limited endpoints for [Llama 3.1 70B Instruct](/meta-llama/llama-3.1-70b-instruct). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
1243
|
-
:context_length:
|
|
1425
|
+
:context_length: 8192
|
|
1244
1426
|
:architecture:
|
|
1245
1427
|
modality: text->text
|
|
1246
1428
|
tokenizer: Llama3
|
|
@@ -1272,17 +1454,17 @@
|
|
|
1272
1454
|
tokenizer: Llama3
|
|
1273
1455
|
instruct_type: llama3
|
|
1274
1456
|
:pricing:
|
|
1275
|
-
prompt: '0.
|
|
1276
|
-
completion: '0.
|
|
1457
|
+
prompt: '0.00000035'
|
|
1458
|
+
completion: '0.0000004'
|
|
1277
1459
|
image: '0'
|
|
1278
1460
|
request: '0'
|
|
1279
1461
|
:top_provider:
|
|
1280
|
-
context_length:
|
|
1462
|
+
context_length: 100000
|
|
1281
1463
|
max_completion_tokens:
|
|
1282
1464
|
is_moderated: false
|
|
1283
1465
|
:per_request_limits:
|
|
1284
|
-
prompt_tokens: '
|
|
1285
|
-
completion_tokens: '
|
|
1466
|
+
prompt_tokens: '57700436'
|
|
1467
|
+
completion_tokens: '50487881'
|
|
1286
1468
|
- :id: meta-llama/llama-3.1-8b-instruct:free
|
|
1287
1469
|
:name: 'Meta: Llama 3.1 8B Instruct (free)'
|
|
1288
1470
|
:created: 1721692800
|
|
@@ -1294,7 +1476,7 @@
|
|
|
1294
1476
|
Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).
|
|
1295
1477
|
|
|
1296
1478
|
_These are free, rate-limited endpoints for [Llama 3.1 8B Instruct](/meta-llama/llama-3.1-8b-instruct). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
1297
|
-
:context_length:
|
|
1479
|
+
:context_length: 8192
|
|
1298
1480
|
:architecture:
|
|
1299
1481
|
modality: text->text
|
|
1300
1482
|
tokenizer: Llama3
|
|
@@ -1335,8 +1517,8 @@
|
|
|
1335
1517
|
max_completion_tokens:
|
|
1336
1518
|
is_moderated: false
|
|
1337
1519
|
:per_request_limits:
|
|
1338
|
-
prompt_tokens: '
|
|
1339
|
-
completion_tokens: '
|
|
1520
|
+
prompt_tokens: '367184595'
|
|
1521
|
+
completion_tokens: '367184595'
|
|
1340
1522
|
- :id: meta-llama/llama-3.1-405b-instruct:free
|
|
1341
1523
|
:name: 'Meta: Llama 3.1 405B Instruct (free)'
|
|
1342
1524
|
:created: 1721692800
|
|
@@ -1350,7 +1532,7 @@
|
|
|
1350
1532
|
Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).
|
|
1351
1533
|
|
|
1352
1534
|
_These are free, rate-limited endpoints for [Llama 3.1 405B Instruct](/meta-llama/llama-3.1-405b-instruct). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
1353
|
-
:context_length:
|
|
1535
|
+
:context_length: 8000
|
|
1354
1536
|
:architecture:
|
|
1355
1537
|
modality: text->text
|
|
1356
1538
|
tokenizer: Llama3
|
|
@@ -1361,8 +1543,8 @@
|
|
|
1361
1543
|
image: '0'
|
|
1362
1544
|
request: '0'
|
|
1363
1545
|
:top_provider:
|
|
1364
|
-
context_length:
|
|
1365
|
-
max_completion_tokens:
|
|
1546
|
+
context_length: 8000
|
|
1547
|
+
max_completion_tokens: 4000
|
|
1366
1548
|
is_moderated: false
|
|
1367
1549
|
:per_request_limits:
|
|
1368
1550
|
prompt_tokens: Infinity
|
|
@@ -1393,8 +1575,8 @@
|
|
|
1393
1575
|
max_completion_tokens:
|
|
1394
1576
|
is_moderated: false
|
|
1395
1577
|
:per_request_limits:
|
|
1396
|
-
prompt_tokens: '
|
|
1397
|
-
completion_tokens: '
|
|
1578
|
+
prompt_tokens: '11282208'
|
|
1579
|
+
completion_tokens: '11282208'
|
|
1398
1580
|
- :id: mistralai/codestral-mamba
|
|
1399
1581
|
:name: 'Mistral: Codestral Mamba'
|
|
1400
1582
|
:created: 1721347200
|
|
@@ -1421,8 +1603,8 @@
|
|
|
1421
1603
|
max_completion_tokens:
|
|
1422
1604
|
is_moderated: false
|
|
1423
1605
|
:per_request_limits:
|
|
1424
|
-
prompt_tokens: '
|
|
1425
|
-
completion_tokens: '
|
|
1606
|
+
prompt_tokens: '80780611'
|
|
1607
|
+
completion_tokens: '80780611'
|
|
1426
1608
|
- :id: mistralai/mistral-nemo
|
|
1427
1609
|
:name: 'Mistral: Mistral Nemo'
|
|
1428
1610
|
:created: 1721347200
|
|
@@ -1447,8 +1629,8 @@
|
|
|
1447
1629
|
max_completion_tokens:
|
|
1448
1630
|
is_moderated: false
|
|
1449
1631
|
:per_request_limits:
|
|
1450
|
-
prompt_tokens: '
|
|
1451
|
-
completion_tokens: '
|
|
1632
|
+
prompt_tokens: '155347328'
|
|
1633
|
+
completion_tokens: '155347328'
|
|
1452
1634
|
- :id: openai/gpt-4o-mini-2024-07-18
|
|
1453
1635
|
:name: 'OpenAI: GPT-4o-mini (2024-07-18)'
|
|
1454
1636
|
:created: 1721260800
|
|
@@ -1475,8 +1657,8 @@
|
|
|
1475
1657
|
max_completion_tokens: 16384
|
|
1476
1658
|
is_moderated: true
|
|
1477
1659
|
:per_request_limits:
|
|
1478
|
-
prompt_tokens: '
|
|
1479
|
-
completion_tokens: '
|
|
1660
|
+
prompt_tokens: '134634351'
|
|
1661
|
+
completion_tokens: '33658587'
|
|
1480
1662
|
- :id: openai/gpt-4o-mini
|
|
1481
1663
|
:name: 'OpenAI: GPT-4o-mini'
|
|
1482
1664
|
:created: 1721260800
|
|
@@ -1503,8 +1685,8 @@
|
|
|
1503
1685
|
max_completion_tokens: 16384
|
|
1504
1686
|
is_moderated: true
|
|
1505
1687
|
:per_request_limits:
|
|
1506
|
-
prompt_tokens: '
|
|
1507
|
-
completion_tokens: '
|
|
1688
|
+
prompt_tokens: '134634351'
|
|
1689
|
+
completion_tokens: '33658587'
|
|
1508
1690
|
- :id: qwen/qwen-2-7b-instruct:free
|
|
1509
1691
|
:name: Qwen 2 7B Instruct (free)
|
|
1510
1692
|
:created: 1721088000
|
|
@@ -1518,7 +1700,7 @@
|
|
|
1518
1700
|
Usage of this model is subject to [Tongyi Qianwen LICENSE AGREEMENT](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).
|
|
1519
1701
|
|
|
1520
1702
|
_These are free, rate-limited endpoints for [Qwen 2 7B Instruct](/qwen/qwen-2-7b-instruct). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
1521
|
-
:context_length:
|
|
1703
|
+
:context_length: 8192
|
|
1522
1704
|
:architecture:
|
|
1523
1705
|
modality: text->text
|
|
1524
1706
|
tokenizer: Qwen
|
|
@@ -1561,8 +1743,8 @@
|
|
|
1561
1743
|
max_completion_tokens:
|
|
1562
1744
|
is_moderated: false
|
|
1563
1745
|
:per_request_limits:
|
|
1564
|
-
prompt_tokens: '
|
|
1565
|
-
completion_tokens: '
|
|
1746
|
+
prompt_tokens: '373984310'
|
|
1747
|
+
completion_tokens: '373984310'
|
|
1566
1748
|
- :id: google/gemma-2-27b-it
|
|
1567
1749
|
:name: 'Google: Gemma 2 27B'
|
|
1568
1750
|
:created: 1720828800
|
|
@@ -1587,8 +1769,8 @@
|
|
|
1587
1769
|
max_completion_tokens:
|
|
1588
1770
|
is_moderated: false
|
|
1589
1771
|
:per_request_limits:
|
|
1590
|
-
prompt_tokens: '
|
|
1591
|
-
completion_tokens: '
|
|
1772
|
+
prompt_tokens: '74796862'
|
|
1773
|
+
completion_tokens: '74796862'
|
|
1592
1774
|
- :id: alpindale/magnum-72b
|
|
1593
1775
|
:name: Magnum 72B
|
|
1594
1776
|
:created: 1720656000
|
|
@@ -1611,8 +1793,8 @@
|
|
|
1611
1793
|
max_completion_tokens: 1024
|
|
1612
1794
|
is_moderated: false
|
|
1613
1795
|
:per_request_limits:
|
|
1614
|
-
prompt_tokens: '
|
|
1615
|
-
completion_tokens: '
|
|
1796
|
+
prompt_tokens: '5385374'
|
|
1797
|
+
completion_tokens: '4487811'
|
|
1616
1798
|
- :id: nousresearch/hermes-2-theta-llama-3-8b
|
|
1617
1799
|
:name: 'Nous: Hermes 2 Theta 8B'
|
|
1618
1800
|
:created: 1720656000
|
|
@@ -1635,8 +1817,8 @@
|
|
|
1635
1817
|
max_completion_tokens: 2048
|
|
1636
1818
|
is_moderated: false
|
|
1637
1819
|
:per_request_limits:
|
|
1638
|
-
prompt_tokens: '
|
|
1639
|
-
completion_tokens: '
|
|
1820
|
+
prompt_tokens: '107707481'
|
|
1821
|
+
completion_tokens: '17951246'
|
|
1640
1822
|
- :id: google/gemma-2-9b-it:free
|
|
1641
1823
|
:name: 'Google: Gemma 2 9B (free)'
|
|
1642
1824
|
:created: 1719532800
|
|
@@ -1648,7 +1830,7 @@
|
|
|
1648
1830
|
See the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
|
|
1649
1831
|
|
|
1650
1832
|
_These are free, rate-limited endpoints for [Gemma 2 9B](/google/gemma-2-9b-it). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
1651
|
-
:context_length:
|
|
1833
|
+
:context_length: 4096
|
|
1652
1834
|
:architecture:
|
|
1653
1835
|
modality: text->text
|
|
1654
1836
|
tokenizer: Gemini
|
|
@@ -1689,8 +1871,8 @@
|
|
|
1689
1871
|
max_completion_tokens:
|
|
1690
1872
|
is_moderated: false
|
|
1691
1873
|
:per_request_limits:
|
|
1692
|
-
prompt_tokens: '
|
|
1693
|
-
completion_tokens: '
|
|
1874
|
+
prompt_tokens: '336585879'
|
|
1875
|
+
completion_tokens: '336585879'
|
|
1694
1876
|
- :id: ai21/jamba-instruct
|
|
1695
1877
|
:name: 'AI21: Jamba Instruct'
|
|
1696
1878
|
:created: 1719273600
|
|
@@ -1718,8 +1900,8 @@
|
|
|
1718
1900
|
max_completion_tokens: 4096
|
|
1719
1901
|
is_moderated: false
|
|
1720
1902
|
:per_request_limits:
|
|
1721
|
-
prompt_tokens: '
|
|
1722
|
-
completion_tokens: '
|
|
1903
|
+
prompt_tokens: '40390305'
|
|
1904
|
+
completion_tokens: '28850218'
|
|
1723
1905
|
- :id: anthropic/claude-3.5-sonnet
|
|
1724
1906
|
:name: 'Anthropic: Claude 3.5 Sonnet'
|
|
1725
1907
|
:created: 1718841600
|
|
@@ -1747,8 +1929,8 @@
|
|
|
1747
1929
|
max_completion_tokens: 8192
|
|
1748
1930
|
is_moderated: true
|
|
1749
1931
|
:per_request_limits:
|
|
1750
|
-
prompt_tokens: '
|
|
1751
|
-
completion_tokens: '
|
|
1932
|
+
prompt_tokens: '6731717'
|
|
1933
|
+
completion_tokens: '1346343'
|
|
1752
1934
|
- :id: anthropic/claude-3.5-sonnet:beta
|
|
1753
1935
|
:name: 'Anthropic: Claude 3.5 Sonnet (self-moderated)'
|
|
1754
1936
|
:created: 1718841600
|
|
@@ -1778,8 +1960,8 @@
|
|
|
1778
1960
|
max_completion_tokens: 8192
|
|
1779
1961
|
is_moderated: false
|
|
1780
1962
|
:per_request_limits:
|
|
1781
|
-
prompt_tokens: '
|
|
1782
|
-
completion_tokens: '
|
|
1963
|
+
prompt_tokens: '6731717'
|
|
1964
|
+
completion_tokens: '1346343'
|
|
1783
1965
|
- :id: sao10k/l3-euryale-70b
|
|
1784
1966
|
:name: Llama 3 Euryale 70B v2.1
|
|
1785
1967
|
:created: 1718668800
|
|
@@ -1806,8 +1988,8 @@
|
|
|
1806
1988
|
max_completion_tokens:
|
|
1807
1989
|
is_moderated: false
|
|
1808
1990
|
:per_request_limits:
|
|
1809
|
-
prompt_tokens: '
|
|
1810
|
-
completion_tokens: '
|
|
1991
|
+
prompt_tokens: '57700436'
|
|
1992
|
+
completion_tokens: '50487881'
|
|
1811
1993
|
- :id: cognitivecomputations/dolphin-mixtral-8x22b
|
|
1812
1994
|
:name: "Dolphin 2.9.2 Mixtral 8x22B \U0001F42C"
|
|
1813
1995
|
:created: 1717804800
|
|
@@ -1834,8 +2016,8 @@
|
|
|
1834
2016
|
max_completion_tokens:
|
|
1835
2017
|
is_moderated: false
|
|
1836
2018
|
:per_request_limits:
|
|
1837
|
-
prompt_tokens: '
|
|
1838
|
-
completion_tokens: '
|
|
2019
|
+
prompt_tokens: '22439058'
|
|
2020
|
+
completion_tokens: '22439058'
|
|
1839
2021
|
- :id: qwen/qwen-2-72b-instruct
|
|
1840
2022
|
:name: Qwen 2 72B Instruct
|
|
1841
2023
|
:created: 1717718400
|
|
@@ -1862,8 +2044,8 @@
|
|
|
1862
2044
|
max_completion_tokens:
|
|
1863
2045
|
is_moderated: false
|
|
1864
2046
|
:per_request_limits:
|
|
1865
|
-
prompt_tokens: '
|
|
1866
|
-
completion_tokens: '
|
|
2047
|
+
prompt_tokens: '59397508'
|
|
2048
|
+
completion_tokens: '51782442'
|
|
1867
2049
|
- :id: nousresearch/hermes-2-pro-llama-3-8b
|
|
1868
2050
|
:name: 'NousResearch: Hermes 2 Pro - Llama-3 8B'
|
|
1869
2051
|
:created: 1716768000
|
|
@@ -1885,8 +2067,8 @@
|
|
|
1885
2067
|
max_completion_tokens:
|
|
1886
2068
|
is_moderated: false
|
|
1887
2069
|
:per_request_limits:
|
|
1888
|
-
prompt_tokens: '
|
|
1889
|
-
completion_tokens: '
|
|
2070
|
+
prompt_tokens: '144251091'
|
|
2071
|
+
completion_tokens: '144251091'
|
|
1890
2072
|
- :id: mistralai/mistral-7b-instruct-v0.3
|
|
1891
2073
|
:name: 'Mistral: Mistral 7B Instruct v0.3'
|
|
1892
2074
|
:created: 1716768000
|
|
@@ -1915,8 +2097,8 @@
|
|
|
1915
2097
|
max_completion_tokens:
|
|
1916
2098
|
is_moderated: false
|
|
1917
2099
|
:per_request_limits:
|
|
1918
|
-
prompt_tokens: '
|
|
1919
|
-
completion_tokens: '
|
|
2100
|
+
prompt_tokens: '367184595'
|
|
2101
|
+
completion_tokens: '367184595'
|
|
1920
2102
|
- :id: mistralai/mistral-7b-instruct:free
|
|
1921
2103
|
:name: 'Mistral: Mistral 7B Instruct (free)'
|
|
1922
2104
|
:created: 1716768000
|
|
@@ -1926,7 +2108,7 @@
|
|
|
1926
2108
|
*Mistral 7B Instruct has multiple version variants, and this is intended to be the latest version.*
|
|
1927
2109
|
|
|
1928
2110
|
_These are free, rate-limited endpoints for [Mistral 7B Instruct](/mistralai/mistral-7b-instruct). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
1929
|
-
:context_length:
|
|
2111
|
+
:context_length: 8192
|
|
1930
2112
|
:architecture:
|
|
1931
2113
|
modality: text->text
|
|
1932
2114
|
tokenizer: Mistral
|
|
@@ -1965,8 +2147,8 @@
|
|
|
1965
2147
|
max_completion_tokens:
|
|
1966
2148
|
is_moderated: false
|
|
1967
2149
|
:per_request_limits:
|
|
1968
|
-
prompt_tokens: '
|
|
1969
|
-
completion_tokens: '
|
|
2150
|
+
prompt_tokens: '367184595'
|
|
2151
|
+
completion_tokens: '367184595'
|
|
1970
2152
|
- :id: mistralai/mistral-7b-instruct:nitro
|
|
1971
2153
|
:name: 'Mistral: Mistral 7B Instruct (nitro)'
|
|
1972
2154
|
:created: 1716768000
|
|
@@ -1991,8 +2173,8 @@
|
|
|
1991
2173
|
max_completion_tokens:
|
|
1992
2174
|
is_moderated: false
|
|
1993
2175
|
:per_request_limits:
|
|
1994
|
-
prompt_tokens: '
|
|
1995
|
-
completion_tokens: '
|
|
2176
|
+
prompt_tokens: '288502182'
|
|
2177
|
+
completion_tokens: '288502182'
|
|
1996
2178
|
- :id: microsoft/phi-3-mini-128k-instruct:free
|
|
1997
2179
|
:name: Phi-3 Mini 128K Instruct (free)
|
|
1998
2180
|
:created: 1716681600
|
|
@@ -2002,7 +2184,7 @@
|
|
|
2002
2184
|
At time of release, Phi-3 Medium demonstrated state-of-the-art performance among lightweight models. This model is static, trained on an offline dataset with an October 2023 cutoff date.
|
|
2003
2185
|
|
|
2004
2186
|
_These are free, rate-limited endpoints for [Phi-3 Mini 128K Instruct](/microsoft/phi-3-mini-128k-instruct). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
2005
|
-
:context_length:
|
|
2187
|
+
:context_length: 8192
|
|
2006
2188
|
:architecture:
|
|
2007
2189
|
modality: text->text
|
|
2008
2190
|
tokenizer: Other
|
|
@@ -2041,8 +2223,8 @@
|
|
|
2041
2223
|
max_completion_tokens:
|
|
2042
2224
|
is_moderated: false
|
|
2043
2225
|
:per_request_limits:
|
|
2044
|
-
prompt_tokens: '
|
|
2045
|
-
completion_tokens: '
|
|
2226
|
+
prompt_tokens: '201951527'
|
|
2227
|
+
completion_tokens: '201951527'
|
|
2046
2228
|
- :id: microsoft/phi-3-medium-128k-instruct:free
|
|
2047
2229
|
:name: Phi-3 Medium 128K Instruct (free)
|
|
2048
2230
|
:created: 1716508800
|
|
@@ -2054,7 +2236,7 @@
|
|
|
2054
2236
|
For 4k context length, try [Phi-3 Medium 4K](/microsoft/phi-3-medium-4k-instruct).
|
|
2055
2237
|
|
|
2056
2238
|
_These are free, rate-limited endpoints for [Phi-3 Medium 128K Instruct](/microsoft/phi-3-medium-128k-instruct). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
2057
|
-
:context_length:
|
|
2239
|
+
:context_length: 8192
|
|
2058
2240
|
:architecture:
|
|
2059
2241
|
modality: text->text
|
|
2060
2242
|
tokenizer: Other
|
|
@@ -2095,8 +2277,8 @@
|
|
|
2095
2277
|
max_completion_tokens:
|
|
2096
2278
|
is_moderated: false
|
|
2097
2279
|
:per_request_limits:
|
|
2098
|
-
prompt_tokens: '
|
|
2099
|
-
completion_tokens: '
|
|
2280
|
+
prompt_tokens: '20195152'
|
|
2281
|
+
completion_tokens: '20195152'
|
|
2100
2282
|
- :id: neversleep/llama-3-lumimaid-70b
|
|
2101
2283
|
:name: Llama 3 Lumimaid 70B
|
|
2102
2284
|
:created: 1715817600
|
|
@@ -2121,8 +2303,8 @@
|
|
|
2121
2303
|
max_completion_tokens: 2048
|
|
2122
2304
|
is_moderated: false
|
|
2123
2305
|
:per_request_limits:
|
|
2124
|
-
prompt_tokens: '
|
|
2125
|
-
completion_tokens: '
|
|
2306
|
+
prompt_tokens: '5983748'
|
|
2307
|
+
completion_tokens: '4487811'
|
|
2126
2308
|
- :id: google/gemini-flash-1.5
|
|
2127
2309
|
:name: 'Google: Gemini Flash 1.5'
|
|
2128
2310
|
:created: 1715644800
|
|
@@ -2149,8 +2331,8 @@
|
|
|
2149
2331
|
max_completion_tokens: 8192
|
|
2150
2332
|
is_moderated: false
|
|
2151
2333
|
:per_request_limits:
|
|
2152
|
-
prompt_tokens: '
|
|
2153
|
-
completion_tokens: '
|
|
2334
|
+
prompt_tokens: '269268703'
|
|
2335
|
+
completion_tokens: '67317175'
|
|
2154
2336
|
- :id: deepseek/deepseek-chat
|
|
2155
2337
|
:name: DeepSeek V2.5
|
|
2156
2338
|
:created: 1715644800
|
|
@@ -2177,8 +2359,8 @@
|
|
|
2177
2359
|
max_completion_tokens: 4096
|
|
2178
2360
|
is_moderated: false
|
|
2179
2361
|
:per_request_limits:
|
|
2180
|
-
prompt_tokens: '
|
|
2181
|
-
completion_tokens: '
|
|
2362
|
+
prompt_tokens: '144251091'
|
|
2363
|
+
completion_tokens: '72125545'
|
|
2182
2364
|
- :id: perplexity/llama-3-sonar-large-32k-online
|
|
2183
2365
|
:name: 'Perplexity: Llama3 Sonar 70B Online'
|
|
2184
2366
|
:created: 1715644800
|
|
@@ -2201,8 +2383,8 @@
|
|
|
2201
2383
|
max_completion_tokens:
|
|
2202
2384
|
is_moderated: false
|
|
2203
2385
|
:per_request_limits:
|
|
2204
|
-
prompt_tokens: '
|
|
2205
|
-
completion_tokens: '
|
|
2386
|
+
prompt_tokens: '20195152'
|
|
2387
|
+
completion_tokens: '20195152'
|
|
2206
2388
|
- :id: perplexity/llama-3-sonar-large-32k-chat
|
|
2207
2389
|
:name: 'Perplexity: Llama3 Sonar 70B'
|
|
2208
2390
|
:created: 1715644800
|
|
@@ -2225,32 +2407,8 @@
|
|
|
2225
2407
|
max_completion_tokens:
|
|
2226
2408
|
is_moderated: false
|
|
2227
2409
|
:per_request_limits:
|
|
2228
|
-
prompt_tokens: '
|
|
2229
|
-
completion_tokens: '
|
|
2230
|
-
- :id: perplexity/llama-3-sonar-small-32k-online
|
|
2231
|
-
:name: 'Perplexity: Llama3 Sonar 8B Online'
|
|
2232
|
-
:created: 1715644800
|
|
2233
|
-
:description: |-
|
|
2234
|
-
Llama3 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance.
|
|
2235
|
-
|
|
2236
|
-
This is the online version of the [offline chat model](/perplexity/llama-3-sonar-small-32k-chat). It is focused on delivering helpful, up-to-date, and factual responses. #online
|
|
2237
|
-
:context_length: 28000
|
|
2238
|
-
:architecture:
|
|
2239
|
-
modality: text->text
|
|
2240
|
-
tokenizer: Llama3
|
|
2241
|
-
instruct_type:
|
|
2242
|
-
:pricing:
|
|
2243
|
-
prompt: '0.0000002'
|
|
2244
|
-
completion: '0.0000002'
|
|
2245
|
-
image: '0'
|
|
2246
|
-
request: '0.005'
|
|
2247
|
-
:top_provider:
|
|
2248
|
-
context_length: 28000
|
|
2249
|
-
max_completion_tokens:
|
|
2250
|
-
is_moderated: false
|
|
2251
|
-
:per_request_limits:
|
|
2252
|
-
prompt_tokens: '100989083'
|
|
2253
|
-
completion_tokens: '100989083'
|
|
2410
|
+
prompt_tokens: '20195152'
|
|
2411
|
+
completion_tokens: '20195152'
|
|
2254
2412
|
- :id: perplexity/llama-3-sonar-small-32k-chat
|
|
2255
2413
|
:name: 'Perplexity: Llama3 Sonar 8B'
|
|
2256
2414
|
:created: 1715644800
|
|
@@ -2273,8 +2431,8 @@
|
|
|
2273
2431
|
max_completion_tokens:
|
|
2274
2432
|
is_moderated: false
|
|
2275
2433
|
:per_request_limits:
|
|
2276
|
-
prompt_tokens: '
|
|
2277
|
-
completion_tokens: '
|
|
2434
|
+
prompt_tokens: '100975763'
|
|
2435
|
+
completion_tokens: '100975763'
|
|
2278
2436
|
- :id: meta-llama/llama-guard-2-8b
|
|
2279
2437
|
:name: 'Meta: LlamaGuard 2 8B'
|
|
2280
2438
|
:created: 1715558400
|
|
@@ -2303,8 +2461,8 @@
|
|
|
2303
2461
|
max_completion_tokens:
|
|
2304
2462
|
is_moderated: false
|
|
2305
2463
|
:per_request_limits:
|
|
2306
|
-
prompt_tokens: '
|
|
2307
|
-
completion_tokens: '
|
|
2464
|
+
prompt_tokens: '112195293'
|
|
2465
|
+
completion_tokens: '112195293'
|
|
2308
2466
|
- :id: openai/gpt-4o-2024-05-13
|
|
2309
2467
|
:name: 'OpenAI: GPT-4o (2024-05-13)'
|
|
2310
2468
|
:created: 1715558400
|
|
@@ -2327,8 +2485,8 @@
|
|
|
2327
2485
|
max_completion_tokens: 4096
|
|
2328
2486
|
is_moderated: true
|
|
2329
2487
|
:per_request_limits:
|
|
2330
|
-
prompt_tokens: '
|
|
2331
|
-
completion_tokens: '
|
|
2488
|
+
prompt_tokens: '4039030'
|
|
2489
|
+
completion_tokens: '1346343'
|
|
2332
2490
|
- :id: openai/gpt-4o
|
|
2333
2491
|
:name: 'OpenAI: GPT-4o'
|
|
2334
2492
|
:created: 1715558400
|
|
@@ -2351,8 +2509,8 @@
|
|
|
2351
2509
|
max_completion_tokens: 4096
|
|
2352
2510
|
is_moderated: true
|
|
2353
2511
|
:per_request_limits:
|
|
2354
|
-
prompt_tokens: '
|
|
2355
|
-
completion_tokens: '
|
|
2512
|
+
prompt_tokens: '8078061'
|
|
2513
|
+
completion_tokens: '2019515'
|
|
2356
2514
|
- :id: openai/gpt-4o:extended
|
|
2357
2515
|
:name: 'OpenAI: GPT-4o (extended)'
|
|
2358
2516
|
:created: 1715558400
|
|
@@ -2375,8 +2533,8 @@
|
|
|
2375
2533
|
max_completion_tokens: 64000
|
|
2376
2534
|
is_moderated: false
|
|
2377
2535
|
:per_request_limits:
|
|
2378
|
-
prompt_tokens: '
|
|
2379
|
-
completion_tokens: '
|
|
2536
|
+
prompt_tokens: '3365858'
|
|
2537
|
+
completion_tokens: '1121952'
|
|
2380
2538
|
- :id: qwen/qwen-72b-chat
|
|
2381
2539
|
:name: Qwen 1.5 72B Chat
|
|
2382
2540
|
:created: 1715212800
|
|
@@ -2405,8 +2563,8 @@
|
|
|
2405
2563
|
max_completion_tokens:
|
|
2406
2564
|
is_moderated: false
|
|
2407
2565
|
:per_request_limits:
|
|
2408
|
-
prompt_tokens: '
|
|
2409
|
-
completion_tokens: '
|
|
2566
|
+
prompt_tokens: '24932287'
|
|
2567
|
+
completion_tokens: '24932287'
|
|
2410
2568
|
- :id: qwen/qwen-110b-chat
|
|
2411
2569
|
:name: Qwen 1.5 110B Chat
|
|
2412
2570
|
:created: 1715212800
|
|
@@ -2435,8 +2593,8 @@
|
|
|
2435
2593
|
max_completion_tokens:
|
|
2436
2594
|
is_moderated: false
|
|
2437
2595
|
:per_request_limits:
|
|
2438
|
-
prompt_tokens: '
|
|
2439
|
-
completion_tokens: '
|
|
2596
|
+
prompt_tokens: '12466143'
|
|
2597
|
+
completion_tokens: '12466143'
|
|
2440
2598
|
- :id: neversleep/llama-3-lumimaid-8b
|
|
2441
2599
|
:name: Llama 3 Lumimaid 8B
|
|
2442
2600
|
:created: 1714780800
|
|
@@ -2461,8 +2619,8 @@
|
|
|
2461
2619
|
max_completion_tokens:
|
|
2462
2620
|
is_moderated: false
|
|
2463
2621
|
:per_request_limits:
|
|
2464
|
-
prompt_tokens: '
|
|
2465
|
-
completion_tokens: '
|
|
2622
|
+
prompt_tokens: '107707481'
|
|
2623
|
+
completion_tokens: '17951246'
|
|
2466
2624
|
- :id: neversleep/llama-3-lumimaid-8b:extended
|
|
2467
2625
|
:name: Llama 3 Lumimaid 8B (extended)
|
|
2468
2626
|
:created: 1714780800
|
|
@@ -2489,8 +2647,8 @@
|
|
|
2489
2647
|
max_completion_tokens: 2048
|
|
2490
2648
|
is_moderated: false
|
|
2491
2649
|
:per_request_limits:
|
|
2492
|
-
prompt_tokens: '
|
|
2493
|
-
completion_tokens: '
|
|
2650
|
+
prompt_tokens: '107707481'
|
|
2651
|
+
completion_tokens: '17951246'
|
|
2494
2652
|
- :id: sao10k/fimbulvetr-11b-v2
|
|
2495
2653
|
:name: Fimbulvetr 11B v2
|
|
2496
2654
|
:created: 1713657600
|
|
@@ -2513,8 +2671,8 @@
|
|
|
2513
2671
|
max_completion_tokens: 2048
|
|
2514
2672
|
is_moderated: false
|
|
2515
2673
|
:per_request_limits:
|
|
2516
|
-
prompt_tokens: '
|
|
2517
|
-
completion_tokens: '
|
|
2674
|
+
prompt_tokens: '53853740'
|
|
2675
|
+
completion_tokens: '13463435'
|
|
2518
2676
|
- :id: meta-llama/llama-3-70b-instruct
|
|
2519
2677
|
:name: 'Meta: Llama 3 70B Instruct'
|
|
2520
2678
|
:created: 1713398400
|
|
@@ -2539,8 +2697,8 @@
|
|
|
2539
2697
|
max_completion_tokens:
|
|
2540
2698
|
is_moderated: false
|
|
2541
2699
|
:per_request_limits:
|
|
2542
|
-
prompt_tokens: '
|
|
2543
|
-
completion_tokens: '
|
|
2700
|
+
prompt_tokens: '57700436'
|
|
2701
|
+
completion_tokens: '50487881'
|
|
2544
2702
|
- :id: meta-llama/llama-3-70b-instruct:nitro
|
|
2545
2703
|
:name: 'Meta: Llama 3 70B Instruct (nitro)'
|
|
2546
2704
|
:created: 1713398400
|
|
@@ -2567,8 +2725,8 @@
|
|
|
2567
2725
|
max_completion_tokens:
|
|
2568
2726
|
is_moderated: false
|
|
2569
2727
|
:per_request_limits:
|
|
2570
|
-
prompt_tokens: '
|
|
2571
|
-
completion_tokens: '
|
|
2728
|
+
prompt_tokens: '25498930'
|
|
2729
|
+
completion_tokens: '25498930'
|
|
2572
2730
|
- :id: meta-llama/llama-3-8b-instruct:free
|
|
2573
2731
|
:name: 'Meta: Llama 3 8B Instruct (free)'
|
|
2574
2732
|
:created: 1713398400
|
|
@@ -2621,8 +2779,8 @@
|
|
|
2621
2779
|
max_completion_tokens:
|
|
2622
2780
|
is_moderated: false
|
|
2623
2781
|
:per_request_limits:
|
|
2624
|
-
prompt_tokens: '
|
|
2625
|
-
completion_tokens: '
|
|
2782
|
+
prompt_tokens: '367184595'
|
|
2783
|
+
completion_tokens: '367184595'
|
|
2626
2784
|
- :id: meta-llama/llama-3-8b-instruct:nitro
|
|
2627
2785
|
:name: 'Meta: Llama 3 8B Instruct (nitro)'
|
|
2628
2786
|
:created: 1713398400
|
|
@@ -2649,8 +2807,8 @@
|
|
|
2649
2807
|
max_completion_tokens:
|
|
2650
2808
|
is_moderated: false
|
|
2651
2809
|
:per_request_limits:
|
|
2652
|
-
prompt_tokens: '
|
|
2653
|
-
completion_tokens: '
|
|
2810
|
+
prompt_tokens: '124661436'
|
|
2811
|
+
completion_tokens: '124661436'
|
|
2654
2812
|
- :id: meta-llama/llama-3-8b-instruct:extended
|
|
2655
2813
|
:name: 'Meta: Llama 3 8B Instruct (extended)'
|
|
2656
2814
|
:created: 1713398400
|
|
@@ -2677,8 +2835,8 @@
|
|
|
2677
2835
|
max_completion_tokens: 2048
|
|
2678
2836
|
is_moderated: false
|
|
2679
2837
|
:per_request_limits:
|
|
2680
|
-
prompt_tokens: '
|
|
2681
|
-
completion_tokens: '
|
|
2838
|
+
prompt_tokens: '107707481'
|
|
2839
|
+
completion_tokens: '17951246'
|
|
2682
2840
|
- :id: mistralai/mixtral-8x22b-instruct
|
|
2683
2841
|
:name: 'Mistral: Mixtral 8x22B Instruct'
|
|
2684
2842
|
:created: 1713312000
|
|
@@ -2705,8 +2863,8 @@
|
|
|
2705
2863
|
max_completion_tokens:
|
|
2706
2864
|
is_moderated: false
|
|
2707
2865
|
:per_request_limits:
|
|
2708
|
-
prompt_tokens: '
|
|
2709
|
-
completion_tokens: '
|
|
2866
|
+
prompt_tokens: '22439058'
|
|
2867
|
+
completion_tokens: '22439058'
|
|
2710
2868
|
- :id: microsoft/wizardlm-2-7b
|
|
2711
2869
|
:name: WizardLM-2 7B
|
|
2712
2870
|
:created: 1713225600
|
|
@@ -2733,8 +2891,8 @@
|
|
|
2733
2891
|
max_completion_tokens:
|
|
2734
2892
|
is_moderated: false
|
|
2735
2893
|
:per_request_limits:
|
|
2736
|
-
prompt_tokens: '
|
|
2737
|
-
completion_tokens: '
|
|
2894
|
+
prompt_tokens: '367184595'
|
|
2895
|
+
completion_tokens: '367184595'
|
|
2738
2896
|
- :id: microsoft/wizardlm-2-8x22b
|
|
2739
2897
|
:name: WizardLM-2 8x22B
|
|
2740
2898
|
:created: 1713225600
|
|
@@ -2761,8 +2919,8 @@
|
|
|
2761
2919
|
max_completion_tokens:
|
|
2762
2920
|
is_moderated: false
|
|
2763
2921
|
:per_request_limits:
|
|
2764
|
-
prompt_tokens: '
|
|
2765
|
-
completion_tokens: '
|
|
2922
|
+
prompt_tokens: '40390305'
|
|
2923
|
+
completion_tokens: '40390305'
|
|
2766
2924
|
- :id: google/gemini-pro-1.5
|
|
2767
2925
|
:name: 'Google: Gemini Pro 1.5'
|
|
2768
2926
|
:created: 1712620800
|
|
@@ -2791,15 +2949,15 @@
|
|
|
2791
2949
|
:pricing:
|
|
2792
2950
|
prompt: '0.00000125'
|
|
2793
2951
|
completion: '0.000005'
|
|
2794
|
-
image: '0.
|
|
2952
|
+
image: '0.0006575'
|
|
2795
2953
|
request: '0'
|
|
2796
2954
|
:top_provider:
|
|
2797
2955
|
context_length: 2000000
|
|
2798
2956
|
max_completion_tokens: 8192
|
|
2799
2957
|
is_moderated: false
|
|
2800
2958
|
:per_request_limits:
|
|
2801
|
-
prompt_tokens: '
|
|
2802
|
-
completion_tokens: '
|
|
2959
|
+
prompt_tokens: '16156122'
|
|
2960
|
+
completion_tokens: '4039030'
|
|
2803
2961
|
- :id: openai/gpt-4-turbo
|
|
2804
2962
|
:name: 'OpenAI: GPT-4 Turbo'
|
|
2805
2963
|
:created: 1712620800
|
|
@@ -2822,8 +2980,8 @@
|
|
|
2822
2980
|
max_completion_tokens: 4096
|
|
2823
2981
|
is_moderated: true
|
|
2824
2982
|
:per_request_limits:
|
|
2825
|
-
prompt_tokens: '
|
|
2826
|
-
completion_tokens: '
|
|
2983
|
+
prompt_tokens: '2019515'
|
|
2984
|
+
completion_tokens: '673171'
|
|
2827
2985
|
- :id: cohere/command-r-plus
|
|
2828
2986
|
:name: 'Cohere: Command R+'
|
|
2829
2987
|
:created: 1712188800
|
|
@@ -2848,8 +3006,8 @@
|
|
|
2848
3006
|
max_completion_tokens: 4000
|
|
2849
3007
|
is_moderated: false
|
|
2850
3008
|
:per_request_limits:
|
|
2851
|
-
prompt_tokens: '
|
|
2852
|
-
completion_tokens: '
|
|
3009
|
+
prompt_tokens: '7086018'
|
|
3010
|
+
completion_tokens: '1417203'
|
|
2853
3011
|
- :id: cohere/command-r-plus-04-2024
|
|
2854
3012
|
:name: 'Cohere: Command R+ (04-2024)'
|
|
2855
3013
|
:created: 1712016000
|
|
@@ -2874,8 +3032,8 @@
|
|
|
2874
3032
|
max_completion_tokens: 4000
|
|
2875
3033
|
is_moderated: false
|
|
2876
3034
|
:per_request_limits:
|
|
2877
|
-
prompt_tokens: '
|
|
2878
|
-
completion_tokens: '
|
|
3035
|
+
prompt_tokens: '7086018'
|
|
3036
|
+
completion_tokens: '1417203'
|
|
2879
3037
|
- :id: databricks/dbrx-instruct
|
|
2880
3038
|
:name: 'Databricks: DBRX 132B Instruct'
|
|
2881
3039
|
:created: 1711670400
|
|
@@ -2902,8 +3060,8 @@
|
|
|
2902
3060
|
max_completion_tokens:
|
|
2903
3061
|
is_moderated: false
|
|
2904
3062
|
:per_request_limits:
|
|
2905
|
-
prompt_tokens: '
|
|
2906
|
-
completion_tokens: '
|
|
3063
|
+
prompt_tokens: '18699215'
|
|
3064
|
+
completion_tokens: '18699215'
|
|
2907
3065
|
- :id: sophosympatheia/midnight-rose-70b
|
|
2908
3066
|
:name: Midnight Rose 70B
|
|
2909
3067
|
:created: 1711065600
|
|
@@ -2926,8 +3084,8 @@
|
|
|
2926
3084
|
max_completion_tokens:
|
|
2927
3085
|
is_moderated: false
|
|
2928
3086
|
:per_request_limits:
|
|
2929
|
-
prompt_tokens: '
|
|
2930
|
-
completion_tokens: '
|
|
3087
|
+
prompt_tokens: '25243940'
|
|
3088
|
+
completion_tokens: '25243940'
|
|
2931
3089
|
- :id: cohere/command-r
|
|
2932
3090
|
:name: 'Cohere: Command R'
|
|
2933
3091
|
:created: 1710374400
|
|
@@ -2952,8 +3110,8 @@
|
|
|
2952
3110
|
max_completion_tokens: 4000
|
|
2953
3111
|
is_moderated: false
|
|
2954
3112
|
:per_request_limits:
|
|
2955
|
-
prompt_tokens: '
|
|
2956
|
-
completion_tokens: '
|
|
3113
|
+
prompt_tokens: '42516111'
|
|
3114
|
+
completion_tokens: '14172037'
|
|
2957
3115
|
- :id: cohere/command
|
|
2958
3116
|
:name: 'Cohere: Command'
|
|
2959
3117
|
:created: 1710374400
|
|
@@ -2976,8 +3134,8 @@
|
|
|
2976
3134
|
max_completion_tokens: 4000
|
|
2977
3135
|
is_moderated: false
|
|
2978
3136
|
:per_request_limits:
|
|
2979
|
-
prompt_tokens: '
|
|
2980
|
-
completion_tokens: '
|
|
3137
|
+
prompt_tokens: '21258055'
|
|
3138
|
+
completion_tokens: '10629027'
|
|
2981
3139
|
- :id: anthropic/claude-3-haiku
|
|
2982
3140
|
:name: 'Anthropic: Claude 3 Haiku'
|
|
2983
3141
|
:created: 1710288000
|
|
@@ -3003,8 +3161,8 @@
|
|
|
3003
3161
|
max_completion_tokens: 4096
|
|
3004
3162
|
is_moderated: true
|
|
3005
3163
|
:per_request_limits:
|
|
3006
|
-
prompt_tokens: '
|
|
3007
|
-
completion_tokens: '
|
|
3164
|
+
prompt_tokens: '80780611'
|
|
3165
|
+
completion_tokens: '16156122'
|
|
3008
3166
|
- :id: anthropic/claude-3-haiku:beta
|
|
3009
3167
|
:name: 'Anthropic: Claude 3 Haiku (self-moderated)'
|
|
3010
3168
|
:created: 1710288000
|
|
@@ -3032,8 +3190,8 @@
|
|
|
3032
3190
|
max_completion_tokens: 4096
|
|
3033
3191
|
is_moderated: false
|
|
3034
3192
|
:per_request_limits:
|
|
3035
|
-
prompt_tokens: '
|
|
3036
|
-
completion_tokens: '
|
|
3193
|
+
prompt_tokens: '80780611'
|
|
3194
|
+
completion_tokens: '16156122'
|
|
3037
3195
|
- :id: anthropic/claude-3-sonnet
|
|
3038
3196
|
:name: 'Anthropic: Claude 3 Sonnet'
|
|
3039
3197
|
:created: 1709596800
|
|
@@ -3058,8 +3216,8 @@
|
|
|
3058
3216
|
max_completion_tokens: 4096
|
|
3059
3217
|
is_moderated: true
|
|
3060
3218
|
:per_request_limits:
|
|
3061
|
-
prompt_tokens: '
|
|
3062
|
-
completion_tokens: '
|
|
3219
|
+
prompt_tokens: '6731717'
|
|
3220
|
+
completion_tokens: '1346343'
|
|
3063
3221
|
- :id: anthropic/claude-3-sonnet:beta
|
|
3064
3222
|
:name: 'Anthropic: Claude 3 Sonnet (self-moderated)'
|
|
3065
3223
|
:created: 1709596800
|
|
@@ -3086,8 +3244,8 @@
|
|
|
3086
3244
|
max_completion_tokens: 4096
|
|
3087
3245
|
is_moderated: false
|
|
3088
3246
|
:per_request_limits:
|
|
3089
|
-
prompt_tokens: '
|
|
3090
|
-
completion_tokens: '
|
|
3247
|
+
prompt_tokens: '6731717'
|
|
3248
|
+
completion_tokens: '1346343'
|
|
3091
3249
|
- :id: anthropic/claude-3-opus
|
|
3092
3250
|
:name: 'Anthropic: Claude 3 Opus'
|
|
3093
3251
|
:created: 1709596800
|
|
@@ -3112,8 +3270,8 @@
|
|
|
3112
3270
|
max_completion_tokens: 4096
|
|
3113
3271
|
is_moderated: true
|
|
3114
3272
|
:per_request_limits:
|
|
3115
|
-
prompt_tokens: '
|
|
3116
|
-
completion_tokens: '
|
|
3273
|
+
prompt_tokens: '1346343'
|
|
3274
|
+
completion_tokens: '269268'
|
|
3117
3275
|
- :id: anthropic/claude-3-opus:beta
|
|
3118
3276
|
:name: 'Anthropic: Claude 3 Opus (self-moderated)'
|
|
3119
3277
|
:created: 1709596800
|
|
@@ -3140,8 +3298,8 @@
|
|
|
3140
3298
|
max_completion_tokens: 4096
|
|
3141
3299
|
is_moderated: false
|
|
3142
3300
|
:per_request_limits:
|
|
3143
|
-
prompt_tokens: '
|
|
3144
|
-
completion_tokens: '
|
|
3301
|
+
prompt_tokens: '1346343'
|
|
3302
|
+
completion_tokens: '269268'
|
|
3145
3303
|
- :id: cohere/command-r-03-2024
|
|
3146
3304
|
:name: 'Cohere: Command R (03-2024)'
|
|
3147
3305
|
:created: 1709341200
|
|
@@ -3166,8 +3324,8 @@
|
|
|
3166
3324
|
max_completion_tokens: 4000
|
|
3167
3325
|
is_moderated: false
|
|
3168
3326
|
:per_request_limits:
|
|
3169
|
-
prompt_tokens: '
|
|
3170
|
-
completion_tokens: '
|
|
3327
|
+
prompt_tokens: '42516111'
|
|
3328
|
+
completion_tokens: '14172037'
|
|
3171
3329
|
- :id: mistralai/mistral-large
|
|
3172
3330
|
:name: Mistral Large
|
|
3173
3331
|
:created: 1708905600
|
|
@@ -3190,8 +3348,8 @@
|
|
|
3190
3348
|
max_completion_tokens:
|
|
3191
3349
|
is_moderated: false
|
|
3192
3350
|
:per_request_limits:
|
|
3193
|
-
prompt_tokens: '
|
|
3194
|
-
completion_tokens: '
|
|
3351
|
+
prompt_tokens: '10097576'
|
|
3352
|
+
completion_tokens: '3365858'
|
|
3195
3353
|
- :id: openai/gpt-4-turbo-preview
|
|
3196
3354
|
:name: 'OpenAI: GPT-4 Turbo Preview'
|
|
3197
3355
|
:created: 1706140800
|
|
@@ -3214,8 +3372,8 @@
|
|
|
3214
3372
|
max_completion_tokens: 4096
|
|
3215
3373
|
is_moderated: true
|
|
3216
3374
|
:per_request_limits:
|
|
3217
|
-
prompt_tokens: '
|
|
3218
|
-
completion_tokens: '
|
|
3375
|
+
prompt_tokens: '2019515'
|
|
3376
|
+
completion_tokens: '673171'
|
|
3219
3377
|
- :id: openai/gpt-3.5-turbo-0613
|
|
3220
3378
|
:name: 'OpenAI: GPT-3.5 Turbo (older v0613)'
|
|
3221
3379
|
:created: 1706140800
|
|
@@ -3238,8 +3396,8 @@
|
|
|
3238
3396
|
max_completion_tokens: 4096
|
|
3239
3397
|
is_moderated: true
|
|
3240
3398
|
:per_request_limits:
|
|
3241
|
-
prompt_tokens: '
|
|
3242
|
-
completion_tokens: '
|
|
3399
|
+
prompt_tokens: '20195152'
|
|
3400
|
+
completion_tokens: '10097576'
|
|
3243
3401
|
- :id: nousresearch/nous-hermes-2-mixtral-8x7b-dpo
|
|
3244
3402
|
:name: 'Nous: Hermes 2 Mixtral 8x7B DPO'
|
|
3245
3403
|
:created: 1705363200
|
|
@@ -3264,8 +3422,8 @@
|
|
|
3264
3422
|
max_completion_tokens:
|
|
3265
3423
|
is_moderated: false
|
|
3266
3424
|
:per_request_limits:
|
|
3267
|
-
prompt_tokens: '
|
|
3268
|
-
completion_tokens: '
|
|
3425
|
+
prompt_tokens: '37398431'
|
|
3426
|
+
completion_tokens: '37398431'
|
|
3269
3427
|
- :id: mistralai/mistral-medium
|
|
3270
3428
|
:name: Mistral Medium
|
|
3271
3429
|
:created: 1704844800
|
|
@@ -3287,8 +3445,8 @@
|
|
|
3287
3445
|
max_completion_tokens:
|
|
3288
3446
|
is_moderated: false
|
|
3289
3447
|
:per_request_limits:
|
|
3290
|
-
prompt_tokens: '
|
|
3291
|
-
completion_tokens: '
|
|
3448
|
+
prompt_tokens: '7343691'
|
|
3449
|
+
completion_tokens: '2493228'
|
|
3292
3450
|
- :id: mistralai/mistral-small
|
|
3293
3451
|
:name: Mistral Small
|
|
3294
3452
|
:created: 1704844800
|
|
@@ -3309,8 +3467,8 @@
|
|
|
3309
3467
|
max_completion_tokens:
|
|
3310
3468
|
is_moderated: false
|
|
3311
3469
|
:per_request_limits:
|
|
3312
|
-
prompt_tokens: '
|
|
3313
|
-
completion_tokens: '
|
|
3470
|
+
prompt_tokens: '100975763'
|
|
3471
|
+
completion_tokens: '33658587'
|
|
3314
3472
|
- :id: mistralai/mistral-tiny
|
|
3315
3473
|
:name: Mistral Tiny
|
|
3316
3474
|
:created: 1704844800
|
|
@@ -3333,32 +3491,8 @@
|
|
|
3333
3491
|
max_completion_tokens:
|
|
3334
3492
|
is_moderated: false
|
|
3335
3493
|
:per_request_limits:
|
|
3336
|
-
prompt_tokens: '
|
|
3337
|
-
completion_tokens: '
|
|
3338
|
-
- :id: nousresearch/nous-hermes-yi-34b
|
|
3339
|
-
:name: 'Nous: Hermes 2 Yi 34B'
|
|
3340
|
-
:created: 1704153600
|
|
3341
|
-
:description: |-
|
|
3342
|
-
Nous Hermes 2 Yi 34B was trained on 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from open datasets across the AI landscape.
|
|
3343
|
-
|
|
3344
|
-
Nous-Hermes 2 on Yi 34B outperforms all Nous-Hermes & Open-Hermes models of the past, achieving new heights in all benchmarks for a Nous Research LLM as well as surpassing many popular finetunes.
|
|
3345
|
-
:context_length: 4096
|
|
3346
|
-
:architecture:
|
|
3347
|
-
modality: text->text
|
|
3348
|
-
tokenizer: Yi
|
|
3349
|
-
instruct_type: chatml
|
|
3350
|
-
:pricing:
|
|
3351
|
-
prompt: '0.00000072'
|
|
3352
|
-
completion: '0.00000072'
|
|
3353
|
-
image: '0'
|
|
3354
|
-
request: '0'
|
|
3355
|
-
:top_provider:
|
|
3356
|
-
context_length: 4096
|
|
3357
|
-
max_completion_tokens:
|
|
3358
|
-
is_moderated: false
|
|
3359
|
-
:per_request_limits:
|
|
3360
|
-
prompt_tokens: '28052523'
|
|
3361
|
-
completion_tokens: '28052523'
|
|
3494
|
+
prompt_tokens: '80780611'
|
|
3495
|
+
completion_tokens: '80780611'
|
|
3362
3496
|
- :id: mistralai/mistral-7b-instruct-v0.2
|
|
3363
3497
|
:name: 'Mistral: Mistral 7B Instruct v0.2'
|
|
3364
3498
|
:created: 1703721600
|
|
@@ -3385,8 +3519,8 @@
|
|
|
3385
3519
|
max_completion_tokens:
|
|
3386
3520
|
is_moderated: false
|
|
3387
3521
|
:per_request_limits:
|
|
3388
|
-
prompt_tokens: '
|
|
3389
|
-
completion_tokens: '
|
|
3522
|
+
prompt_tokens: '112195293'
|
|
3523
|
+
completion_tokens: '112195293'
|
|
3390
3524
|
- :id: cognitivecomputations/dolphin-mixtral-8x7b
|
|
3391
3525
|
:name: "Dolphin 2.6 Mixtral 8x7B \U0001F42C"
|
|
3392
3526
|
:created: 1703116800
|
|
@@ -3411,8 +3545,8 @@
|
|
|
3411
3545
|
max_completion_tokens:
|
|
3412
3546
|
is_moderated: false
|
|
3413
3547
|
:per_request_limits:
|
|
3414
|
-
prompt_tokens: '
|
|
3415
|
-
completion_tokens: '
|
|
3548
|
+
prompt_tokens: '40390305'
|
|
3549
|
+
completion_tokens: '40390305'
|
|
3416
3550
|
- :id: google/gemini-pro
|
|
3417
3551
|
:name: 'Google: Gemini Pro 1.0'
|
|
3418
3552
|
:created: 1702425600
|
|
@@ -3437,8 +3571,8 @@
|
|
|
3437
3571
|
max_completion_tokens: 8192
|
|
3438
3572
|
is_moderated: false
|
|
3439
3573
|
:per_request_limits:
|
|
3440
|
-
prompt_tokens: '
|
|
3441
|
-
completion_tokens: '
|
|
3574
|
+
prompt_tokens: '40390305'
|
|
3575
|
+
completion_tokens: '13463435'
|
|
3442
3576
|
- :id: google/gemini-pro-vision
|
|
3443
3577
|
:name: 'Google: Gemini Pro Vision 1.0'
|
|
3444
3578
|
:created: 1702425600
|
|
@@ -3465,8 +3599,8 @@
|
|
|
3465
3599
|
max_completion_tokens: 2048
|
|
3466
3600
|
is_moderated: false
|
|
3467
3601
|
:per_request_limits:
|
|
3468
|
-
prompt_tokens: '
|
|
3469
|
-
completion_tokens: '
|
|
3602
|
+
prompt_tokens: '40390305'
|
|
3603
|
+
completion_tokens: '13463435'
|
|
3470
3604
|
- :id: mistralai/mixtral-8x7b-instruct
|
|
3471
3605
|
:name: Mixtral 8x7B Instruct
|
|
3472
3606
|
:created: 1702166400
|
|
@@ -3489,8 +3623,8 @@
|
|
|
3489
3623
|
max_completion_tokens:
|
|
3490
3624
|
is_moderated: false
|
|
3491
3625
|
:per_request_limits:
|
|
3492
|
-
prompt_tokens: '
|
|
3493
|
-
completion_tokens: '
|
|
3626
|
+
prompt_tokens: '84146469'
|
|
3627
|
+
completion_tokens: '84146469'
|
|
3494
3628
|
- :id: mistralai/mixtral-8x7b-instruct:nitro
|
|
3495
3629
|
:name: Mixtral 8x7B Instruct (nitro)
|
|
3496
3630
|
:created: 1702166400
|
|
@@ -3515,8 +3649,8 @@
|
|
|
3515
3649
|
max_completion_tokens:
|
|
3516
3650
|
is_moderated: false
|
|
3517
3651
|
:per_request_limits:
|
|
3518
|
-
prompt_tokens: '
|
|
3519
|
-
completion_tokens: '
|
|
3652
|
+
prompt_tokens: '37398431'
|
|
3653
|
+
completion_tokens: '37398431'
|
|
3520
3654
|
- :id: mistralai/mixtral-8x7b
|
|
3521
3655
|
:name: Mixtral 8x7B (base)
|
|
3522
3656
|
:created: 1702166400
|
|
@@ -3539,8 +3673,8 @@
|
|
|
3539
3673
|
max_completion_tokens:
|
|
3540
3674
|
is_moderated: false
|
|
3541
3675
|
:per_request_limits:
|
|
3542
|
-
prompt_tokens: '
|
|
3543
|
-
completion_tokens: '
|
|
3676
|
+
prompt_tokens: '37398431'
|
|
3677
|
+
completion_tokens: '37398431'
|
|
3544
3678
|
- :id: gryphe/mythomist-7b:free
|
|
3545
3679
|
:name: MythoMist 7B (free)
|
|
3546
3680
|
:created: 1701907200
|
|
@@ -3552,7 +3686,7 @@
|
|
|
3552
3686
|
#merge
|
|
3553
3687
|
|
|
3554
3688
|
_These are free, rate-limited endpoints for [MythoMist 7B](/gryphe/mythomist-7b). Outputs may be cached. Read about rate limits [here](/docs/limits)._
|
|
3555
|
-
:context_length:
|
|
3689
|
+
:context_length: 8192
|
|
3556
3690
|
:architecture:
|
|
3557
3691
|
modality: text->text
|
|
3558
3692
|
tokenizer: Mistral
|
|
@@ -3593,8 +3727,8 @@
|
|
|
3593
3727
|
max_completion_tokens: 2048
|
|
3594
3728
|
is_moderated: false
|
|
3595
3729
|
:per_request_limits:
|
|
3596
|
-
prompt_tokens: '
|
|
3597
|
-
completion_tokens: '
|
|
3730
|
+
prompt_tokens: '53853740'
|
|
3731
|
+
completion_tokens: '53853740'
|
|
3598
3732
|
- :id: openchat/openchat-7b:free
|
|
3599
3733
|
:name: OpenChat 3.5 7B (free)
|
|
3600
3734
|
:created: 1701129600
|
|
@@ -3649,8 +3783,8 @@
|
|
|
3649
3783
|
max_completion_tokens:
|
|
3650
3784
|
is_moderated: false
|
|
3651
3785
|
:per_request_limits:
|
|
3652
|
-
prompt_tokens: '
|
|
3653
|
-
completion_tokens: '
|
|
3786
|
+
prompt_tokens: '367184595'
|
|
3787
|
+
completion_tokens: '367184595'
|
|
3654
3788
|
- :id: neversleep/noromaid-20b
|
|
3655
3789
|
:name: Noromaid 20B
|
|
3656
3790
|
:created: 1700956800
|
|
@@ -3673,8 +3807,8 @@
|
|
|
3673
3807
|
max_completion_tokens: 2048
|
|
3674
3808
|
is_moderated: false
|
|
3675
3809
|
:per_request_limits:
|
|
3676
|
-
prompt_tokens: '
|
|
3677
|
-
completion_tokens: '
|
|
3810
|
+
prompt_tokens: '13463435'
|
|
3811
|
+
completion_tokens: '8975623'
|
|
3678
3812
|
- :id: anthropic/claude-instant-1.1
|
|
3679
3813
|
:name: 'Anthropic: Claude Instant v1.1'
|
|
3680
3814
|
:created: 1700611200
|
|
@@ -3695,8 +3829,8 @@
|
|
|
3695
3829
|
max_completion_tokens: 2048
|
|
3696
3830
|
is_moderated: true
|
|
3697
3831
|
:per_request_limits:
|
|
3698
|
-
prompt_tokens: '
|
|
3699
|
-
completion_tokens: '
|
|
3832
|
+
prompt_tokens: '25243940'
|
|
3833
|
+
completion_tokens: '8414646'
|
|
3700
3834
|
- :id: anthropic/claude-2.1
|
|
3701
3835
|
:name: 'Anthropic: Claude v2.1'
|
|
3702
3836
|
:created: 1700611200
|
|
@@ -3718,8 +3852,8 @@
|
|
|
3718
3852
|
max_completion_tokens: 4096
|
|
3719
3853
|
is_moderated: true
|
|
3720
3854
|
:per_request_limits:
|
|
3721
|
-
prompt_tokens: '
|
|
3722
|
-
completion_tokens: '
|
|
3855
|
+
prompt_tokens: '2524394'
|
|
3856
|
+
completion_tokens: '841464'
|
|
3723
3857
|
- :id: anthropic/claude-2.1:beta
|
|
3724
3858
|
:name: 'Anthropic: Claude v2.1 (self-moderated)'
|
|
3725
3859
|
:created: 1700611200
|
|
@@ -3742,8 +3876,8 @@
|
|
|
3742
3876
|
max_completion_tokens: 4096
|
|
3743
3877
|
is_moderated: false
|
|
3744
3878
|
:per_request_limits:
|
|
3745
|
-
prompt_tokens: '
|
|
3746
|
-
completion_tokens: '
|
|
3879
|
+
prompt_tokens: '2524394'
|
|
3880
|
+
completion_tokens: '841464'
|
|
3747
3881
|
- :id: anthropic/claude-2
|
|
3748
3882
|
:name: 'Anthropic: Claude v2'
|
|
3749
3883
|
:created: 1700611200
|
|
@@ -3765,8 +3899,8 @@
|
|
|
3765
3899
|
max_completion_tokens: 4096
|
|
3766
3900
|
is_moderated: true
|
|
3767
3901
|
:per_request_limits:
|
|
3768
|
-
prompt_tokens: '
|
|
3769
|
-
completion_tokens: '
|
|
3902
|
+
prompt_tokens: '2524394'
|
|
3903
|
+
completion_tokens: '841464'
|
|
3770
3904
|
- :id: anthropic/claude-2:beta
|
|
3771
3905
|
:name: 'Anthropic: Claude v2 (self-moderated)'
|
|
3772
3906
|
:created: 1700611200
|
|
@@ -3789,8 +3923,8 @@
|
|
|
3789
3923
|
max_completion_tokens: 4096
|
|
3790
3924
|
is_moderated: false
|
|
3791
3925
|
:per_request_limits:
|
|
3792
|
-
prompt_tokens: '
|
|
3793
|
-
completion_tokens: '
|
|
3926
|
+
prompt_tokens: '2524394'
|
|
3927
|
+
completion_tokens: '841464'
|
|
3794
3928
|
- :id: teknium/openhermes-2.5-mistral-7b
|
|
3795
3929
|
:name: OpenHermes 2.5 Mistral 7B
|
|
3796
3930
|
:created: 1700438400
|
|
@@ -3812,8 +3946,8 @@
|
|
|
3812
3946
|
max_completion_tokens:
|
|
3813
3947
|
is_moderated: false
|
|
3814
3948
|
:per_request_limits:
|
|
3815
|
-
prompt_tokens: '
|
|
3816
|
-
completion_tokens: '
|
|
3949
|
+
prompt_tokens: '118795016'
|
|
3950
|
+
completion_tokens: '118795016'
|
|
3817
3951
|
- :id: openai/gpt-4-vision-preview
|
|
3818
3952
|
:name: 'OpenAI: GPT-4 Vision'
|
|
3819
3953
|
:created: 1699833600
|
|
@@ -3838,8 +3972,8 @@
|
|
|
3838
3972
|
max_completion_tokens: 4096
|
|
3839
3973
|
is_moderated: true
|
|
3840
3974
|
:per_request_limits:
|
|
3841
|
-
prompt_tokens: '
|
|
3842
|
-
completion_tokens: '
|
|
3975
|
+
prompt_tokens: '2019515'
|
|
3976
|
+
completion_tokens: '673171'
|
|
3843
3977
|
- :id: lizpreciatior/lzlv-70b-fp16-hf
|
|
3844
3978
|
:name: lzlv 70B
|
|
3845
3979
|
:created: 1699747200
|
|
@@ -3863,8 +3997,8 @@
|
|
|
3863
3997
|
max_completion_tokens:
|
|
3864
3998
|
is_moderated: false
|
|
3865
3999
|
:per_request_limits:
|
|
3866
|
-
prompt_tokens: '
|
|
3867
|
-
completion_tokens: '
|
|
4000
|
+
prompt_tokens: '57700436'
|
|
4001
|
+
completion_tokens: '50487881'
|
|
3868
4002
|
- :id: alpindale/goliath-120b
|
|
3869
4003
|
:name: Goliath 120B
|
|
3870
4004
|
:created: 1699574400
|
|
@@ -3891,8 +4025,8 @@
|
|
|
3891
4025
|
max_completion_tokens: 400
|
|
3892
4026
|
is_moderated: false
|
|
3893
4027
|
:per_request_limits:
|
|
3894
|
-
prompt_tokens: '
|
|
3895
|
-
completion_tokens: '
|
|
4028
|
+
prompt_tokens: '2154149'
|
|
4029
|
+
completion_tokens: '2154149'
|
|
3896
4030
|
- :id: undi95/toppy-m-7b:free
|
|
3897
4031
|
:name: Toppy M 7B (free)
|
|
3898
4032
|
:created: 1699574400
|
|
@@ -3953,8 +4087,8 @@
|
|
|
3953
4087
|
max_completion_tokens:
|
|
3954
4088
|
is_moderated: false
|
|
3955
4089
|
:per_request_limits:
|
|
3956
|
-
prompt_tokens: '
|
|
3957
|
-
completion_tokens: '
|
|
4090
|
+
prompt_tokens: '288502182'
|
|
4091
|
+
completion_tokens: '288502182'
|
|
3958
4092
|
- :id: undi95/toppy-m-7b:nitro
|
|
3959
4093
|
:name: Toppy M 7B (nitro)
|
|
3960
4094
|
:created: 1699574400
|
|
@@ -3985,8 +4119,8 @@
|
|
|
3985
4119
|
max_completion_tokens:
|
|
3986
4120
|
is_moderated: false
|
|
3987
4121
|
:per_request_limits:
|
|
3988
|
-
prompt_tokens: '
|
|
3989
|
-
completion_tokens: '
|
|
4122
|
+
prompt_tokens: '288502182'
|
|
4123
|
+
completion_tokens: '288502182'
|
|
3990
4124
|
- :id: openrouter/auto
|
|
3991
4125
|
:name: Auto (best for prompt)
|
|
3992
4126
|
:created: 1699401600
|
|
@@ -4031,8 +4165,8 @@
|
|
|
4031
4165
|
max_completion_tokens: 4096
|
|
4032
4166
|
is_moderated: true
|
|
4033
4167
|
:per_request_limits:
|
|
4034
|
-
prompt_tokens: '
|
|
4035
|
-
completion_tokens: '
|
|
4168
|
+
prompt_tokens: '2019515'
|
|
4169
|
+
completion_tokens: '673171'
|
|
4036
4170
|
- :id: openai/gpt-3.5-turbo-1106
|
|
4037
4171
|
:name: 'OpenAI: GPT-3.5 Turbo 16k (older v1106)'
|
|
4038
4172
|
:created: 1699228800
|
|
@@ -4054,8 +4188,8 @@
|
|
|
4054
4188
|
max_completion_tokens: 4096
|
|
4055
4189
|
is_moderated: true
|
|
4056
4190
|
:per_request_limits:
|
|
4057
|
-
prompt_tokens: '
|
|
4058
|
-
completion_tokens: '
|
|
4191
|
+
prompt_tokens: '20195152'
|
|
4192
|
+
completion_tokens: '10097576'
|
|
4059
4193
|
- :id: google/palm-2-codechat-bison-32k
|
|
4060
4194
|
:name: 'Google: PaLM 2 Code Chat 32k'
|
|
4061
4195
|
:created: 1698969600
|
|
@@ -4076,8 +4210,8 @@
|
|
|
4076
4210
|
max_completion_tokens: 8192
|
|
4077
4211
|
is_moderated: false
|
|
4078
4212
|
:per_request_limits:
|
|
4079
|
-
prompt_tokens: '
|
|
4080
|
-
completion_tokens: '
|
|
4213
|
+
prompt_tokens: '20195152'
|
|
4214
|
+
completion_tokens: '10097576'
|
|
4081
4215
|
- :id: google/palm-2-chat-bison-32k
|
|
4082
4216
|
:name: 'Google: PaLM 2 Chat 32k'
|
|
4083
4217
|
:created: 1698969600
|
|
@@ -4098,8 +4232,8 @@
|
|
|
4098
4232
|
max_completion_tokens: 8192
|
|
4099
4233
|
is_moderated: false
|
|
4100
4234
|
:per_request_limits:
|
|
4101
|
-
prompt_tokens: '
|
|
4102
|
-
completion_tokens: '
|
|
4235
|
+
prompt_tokens: '20195152'
|
|
4236
|
+
completion_tokens: '10097576'
|
|
4103
4237
|
- :id: jondurbin/airoboros-l2-70b
|
|
4104
4238
|
:name: Airoboros 70B
|
|
4105
4239
|
:created: 1698537600
|
|
@@ -4122,8 +4256,8 @@
|
|
|
4122
4256
|
max_completion_tokens:
|
|
4123
4257
|
is_moderated: false
|
|
4124
4258
|
:per_request_limits:
|
|
4125
|
-
prompt_tokens: '
|
|
4126
|
-
completion_tokens: '
|
|
4259
|
+
prompt_tokens: '40390305'
|
|
4260
|
+
completion_tokens: '40390305'
|
|
4127
4261
|
- :id: xwin-lm/xwin-lm-70b
|
|
4128
4262
|
:name: Xwin 70B
|
|
4129
4263
|
:created: 1697328000
|
|
@@ -4146,8 +4280,8 @@
|
|
|
4146
4280
|
max_completion_tokens: 400
|
|
4147
4281
|
is_moderated: false
|
|
4148
4282
|
:per_request_limits:
|
|
4149
|
-
prompt_tokens: '
|
|
4150
|
-
completion_tokens: '
|
|
4283
|
+
prompt_tokens: '5385374'
|
|
4284
|
+
completion_tokens: '5385374'
|
|
4151
4285
|
- :id: mistralai/mistral-7b-instruct-v0.1
|
|
4152
4286
|
:name: 'Mistral: Mistral 7B Instruct v0.1'
|
|
4153
4287
|
:created: 1695859200
|
|
@@ -4168,8 +4302,8 @@
|
|
|
4168
4302
|
max_completion_tokens:
|
|
4169
4303
|
is_moderated: false
|
|
4170
4304
|
:per_request_limits:
|
|
4171
|
-
prompt_tokens: '
|
|
4172
|
-
completion_tokens: '
|
|
4305
|
+
prompt_tokens: '112195293'
|
|
4306
|
+
completion_tokens: '112195293'
|
|
4173
4307
|
- :id: openai/gpt-3.5-turbo-instruct
|
|
4174
4308
|
:name: 'OpenAI: GPT-3.5 Turbo Instruct'
|
|
4175
4309
|
:created: 1695859200
|
|
@@ -4190,8 +4324,8 @@
|
|
|
4190
4324
|
max_completion_tokens: 4096
|
|
4191
4325
|
is_moderated: true
|
|
4192
4326
|
:per_request_limits:
|
|
4193
|
-
prompt_tokens: '
|
|
4194
|
-
completion_tokens: '
|
|
4327
|
+
prompt_tokens: '13463435'
|
|
4328
|
+
completion_tokens: '10097576'
|
|
4195
4329
|
- :id: pygmalionai/mythalion-13b
|
|
4196
4330
|
:name: 'Pygmalion: Mythalion 13B'
|
|
4197
4331
|
:created: 1693612800
|
|
@@ -4211,8 +4345,8 @@
|
|
|
4211
4345
|
max_completion_tokens: 400
|
|
4212
4346
|
is_moderated: false
|
|
4213
4347
|
:per_request_limits:
|
|
4214
|
-
prompt_tokens: '
|
|
4215
|
-
completion_tokens: '
|
|
4348
|
+
prompt_tokens: '17951246'
|
|
4349
|
+
completion_tokens: '17951246'
|
|
4216
4350
|
- :id: openai/gpt-4-32k-0314
|
|
4217
4351
|
:name: 'OpenAI: GPT-4 32k (older v0314)'
|
|
4218
4352
|
:created: 1693180800
|
|
@@ -4236,8 +4370,8 @@
|
|
|
4236
4370
|
max_completion_tokens: 4096
|
|
4237
4371
|
is_moderated: true
|
|
4238
4372
|
:per_request_limits:
|
|
4239
|
-
prompt_tokens: '
|
|
4240
|
-
completion_tokens: '
|
|
4373
|
+
prompt_tokens: '336585'
|
|
4374
|
+
completion_tokens: '168292'
|
|
4241
4375
|
- :id: openai/gpt-4-32k
|
|
4242
4376
|
:name: 'OpenAI: GPT-4 32k'
|
|
4243
4377
|
:created: 1693180800
|
|
@@ -4261,8 +4395,8 @@
|
|
|
4261
4395
|
max_completion_tokens: 4096
|
|
4262
4396
|
is_moderated: true
|
|
4263
4397
|
:per_request_limits:
|
|
4264
|
-
prompt_tokens: '
|
|
4265
|
-
completion_tokens: '
|
|
4398
|
+
prompt_tokens: '336585'
|
|
4399
|
+
completion_tokens: '168292'
|
|
4266
4400
|
- :id: openai/gpt-3.5-turbo-16k
|
|
4267
4401
|
:name: 'OpenAI: GPT-3.5 Turbo 16k'
|
|
4268
4402
|
:created: 1693180800
|
|
@@ -4284,8 +4418,8 @@
|
|
|
4284
4418
|
max_completion_tokens: 4096
|
|
4285
4419
|
is_moderated: true
|
|
4286
4420
|
:per_request_limits:
|
|
4287
|
-
prompt_tokens: '
|
|
4288
|
-
completion_tokens: '
|
|
4421
|
+
prompt_tokens: '6731717'
|
|
4422
|
+
completion_tokens: '5048788'
|
|
4289
4423
|
- :id: nousresearch/nous-hermes-llama2-13b
|
|
4290
4424
|
:name: 'Nous: Hermes 13B'
|
|
4291
4425
|
:created: 1692489600
|
|
@@ -4306,8 +4440,8 @@
|
|
|
4306
4440
|
max_completion_tokens:
|
|
4307
4441
|
is_moderated: false
|
|
4308
4442
|
:per_request_limits:
|
|
4309
|
-
prompt_tokens: '
|
|
4310
|
-
completion_tokens: '
|
|
4443
|
+
prompt_tokens: '118795016'
|
|
4444
|
+
completion_tokens: '118795016'
|
|
4311
4445
|
- :id: huggingfaceh4/zephyr-7b-beta:free
|
|
4312
4446
|
:name: 'Hugging Face: Zephyr 7B (free)'
|
|
4313
4447
|
:created: 1690934400
|
|
@@ -4352,8 +4486,8 @@
|
|
|
4352
4486
|
max_completion_tokens: 1000
|
|
4353
4487
|
is_moderated: false
|
|
4354
4488
|
:per_request_limits:
|
|
4355
|
-
prompt_tokens: '
|
|
4356
|
-
completion_tokens: '
|
|
4489
|
+
prompt_tokens: '10770748'
|
|
4490
|
+
completion_tokens: '8975623'
|
|
4357
4491
|
- :id: anthropic/claude-instant-1.0
|
|
4358
4492
|
:name: 'Anthropic: Claude Instant v1.0'
|
|
4359
4493
|
:created: 1690502400
|
|
@@ -4374,8 +4508,8 @@
|
|
|
4374
4508
|
max_completion_tokens: 4096
|
|
4375
4509
|
is_moderated: true
|
|
4376
4510
|
:per_request_limits:
|
|
4377
|
-
prompt_tokens: '
|
|
4378
|
-
completion_tokens: '
|
|
4511
|
+
prompt_tokens: '25243940'
|
|
4512
|
+
completion_tokens: '8414646'
|
|
4379
4513
|
- :id: anthropic/claude-1.2
|
|
4380
4514
|
:name: 'Anthropic: Claude v1.2'
|
|
4381
4515
|
:created: 1690502400
|
|
@@ -4396,8 +4530,8 @@
|
|
|
4396
4530
|
max_completion_tokens: 4096
|
|
4397
4531
|
is_moderated: true
|
|
4398
4532
|
:per_request_limits:
|
|
4399
|
-
prompt_tokens: '
|
|
4400
|
-
completion_tokens: '
|
|
4533
|
+
prompt_tokens: '2524394'
|
|
4534
|
+
completion_tokens: '841464'
|
|
4401
4535
|
- :id: anthropic/claude-1
|
|
4402
4536
|
:name: 'Anthropic: Claude v1'
|
|
4403
4537
|
:created: 1690502400
|
|
@@ -4418,8 +4552,8 @@
|
|
|
4418
4552
|
max_completion_tokens: 4096
|
|
4419
4553
|
is_moderated: true
|
|
4420
4554
|
:per_request_limits:
|
|
4421
|
-
prompt_tokens: '
|
|
4422
|
-
completion_tokens: '
|
|
4555
|
+
prompt_tokens: '2524394'
|
|
4556
|
+
completion_tokens: '841464'
|
|
4423
4557
|
- :id: anthropic/claude-instant-1
|
|
4424
4558
|
:name: 'Anthropic: Claude Instant v1'
|
|
4425
4559
|
:created: 1690502400
|
|
@@ -4440,8 +4574,8 @@
|
|
|
4440
4574
|
max_completion_tokens: 4096
|
|
4441
4575
|
is_moderated: true
|
|
4442
4576
|
:per_request_limits:
|
|
4443
|
-
prompt_tokens: '
|
|
4444
|
-
completion_tokens: '
|
|
4577
|
+
prompt_tokens: '25243940'
|
|
4578
|
+
completion_tokens: '8414646'
|
|
4445
4579
|
- :id: anthropic/claude-instant-1:beta
|
|
4446
4580
|
:name: 'Anthropic: Claude Instant v1 (self-moderated)'
|
|
4447
4581
|
:created: 1690502400
|
|
@@ -4464,8 +4598,8 @@
|
|
|
4464
4598
|
max_completion_tokens: 4096
|
|
4465
4599
|
is_moderated: false
|
|
4466
4600
|
:per_request_limits:
|
|
4467
|
-
prompt_tokens: '
|
|
4468
|
-
completion_tokens: '
|
|
4601
|
+
prompt_tokens: '25243940'
|
|
4602
|
+
completion_tokens: '8414646'
|
|
4469
4603
|
- :id: anthropic/claude-2.0
|
|
4470
4604
|
:name: 'Anthropic: Claude v2.0'
|
|
4471
4605
|
:created: 1690502400
|
|
@@ -4486,8 +4620,8 @@
|
|
|
4486
4620
|
max_completion_tokens: 4096
|
|
4487
4621
|
is_moderated: true
|
|
4488
4622
|
:per_request_limits:
|
|
4489
|
-
prompt_tokens: '
|
|
4490
|
-
completion_tokens: '
|
|
4623
|
+
prompt_tokens: '2524394'
|
|
4624
|
+
completion_tokens: '841464'
|
|
4491
4625
|
- :id: anthropic/claude-2.0:beta
|
|
4492
4626
|
:name: 'Anthropic: Claude v2.0 (self-moderated)'
|
|
4493
4627
|
:created: 1690502400
|
|
@@ -4510,8 +4644,8 @@
|
|
|
4510
4644
|
max_completion_tokens: 4096
|
|
4511
4645
|
is_moderated: false
|
|
4512
4646
|
:per_request_limits:
|
|
4513
|
-
prompt_tokens: '
|
|
4514
|
-
completion_tokens: '
|
|
4647
|
+
prompt_tokens: '2524394'
|
|
4648
|
+
completion_tokens: '841464'
|
|
4515
4649
|
- :id: undi95/remm-slerp-l2-13b
|
|
4516
4650
|
:name: ReMM SLERP 13B
|
|
4517
4651
|
:created: 1689984000
|
|
@@ -4532,8 +4666,8 @@
|
|
|
4532
4666
|
max_completion_tokens: 400
|
|
4533
4667
|
is_moderated: false
|
|
4534
4668
|
:per_request_limits:
|
|
4535
|
-
prompt_tokens: '
|
|
4536
|
-
completion_tokens: '
|
|
4669
|
+
prompt_tokens: '17951246'
|
|
4670
|
+
completion_tokens: '17951246'
|
|
4537
4671
|
- :id: undi95/remm-slerp-l2-13b:extended
|
|
4538
4672
|
:name: ReMM SLERP 13B (extended)
|
|
4539
4673
|
:created: 1689984000
|
|
@@ -4556,8 +4690,8 @@
|
|
|
4556
4690
|
max_completion_tokens: 400
|
|
4557
4691
|
is_moderated: false
|
|
4558
4692
|
:per_request_limits:
|
|
4559
|
-
prompt_tokens: '
|
|
4560
|
-
completion_tokens: '
|
|
4693
|
+
prompt_tokens: '17951246'
|
|
4694
|
+
completion_tokens: '17951246'
|
|
4561
4695
|
- :id: google/palm-2-codechat-bison
|
|
4562
4696
|
:name: 'Google: PaLM 2 Code Chat'
|
|
4563
4697
|
:created: 1689811200
|
|
@@ -4578,8 +4712,8 @@
|
|
|
4578
4712
|
max_completion_tokens: 1024
|
|
4579
4713
|
is_moderated: false
|
|
4580
4714
|
:per_request_limits:
|
|
4581
|
-
prompt_tokens: '
|
|
4582
|
-
completion_tokens: '
|
|
4715
|
+
prompt_tokens: '20195152'
|
|
4716
|
+
completion_tokens: '10097576'
|
|
4583
4717
|
- :id: google/palm-2-chat-bison
|
|
4584
4718
|
:name: 'Google: PaLM 2 Chat'
|
|
4585
4719
|
:created: 1689811200
|
|
@@ -4600,8 +4734,8 @@
|
|
|
4600
4734
|
max_completion_tokens: 1024
|
|
4601
4735
|
is_moderated: false
|
|
4602
4736
|
:per_request_limits:
|
|
4603
|
-
prompt_tokens: '
|
|
4604
|
-
completion_tokens: '
|
|
4737
|
+
prompt_tokens: '20195152'
|
|
4738
|
+
completion_tokens: '10097576'
|
|
4605
4739
|
- :id: gryphe/mythomax-l2-13b:free
|
|
4606
4740
|
:name: MythoMax 13B (free)
|
|
4607
4741
|
:created: 1688256000
|
|
@@ -4646,8 +4780,8 @@
|
|
|
4646
4780
|
max_completion_tokens:
|
|
4647
4781
|
is_moderated: false
|
|
4648
4782
|
:per_request_limits:
|
|
4649
|
-
prompt_tokens: '
|
|
4650
|
-
completion_tokens: '
|
|
4783
|
+
prompt_tokens: '201951527'
|
|
4784
|
+
completion_tokens: '201951527'
|
|
4651
4785
|
- :id: gryphe/mythomax-l2-13b:nitro
|
|
4652
4786
|
:name: MythoMax 13B (nitro)
|
|
4653
4787
|
:created: 1688256000
|
|
@@ -4670,8 +4804,8 @@
|
|
|
4670
4804
|
max_completion_tokens:
|
|
4671
4805
|
is_moderated: false
|
|
4672
4806
|
:per_request_limits:
|
|
4673
|
-
prompt_tokens: '
|
|
4674
|
-
completion_tokens: '
|
|
4807
|
+
prompt_tokens: '100975763'
|
|
4808
|
+
completion_tokens: '100975763'
|
|
4675
4809
|
- :id: gryphe/mythomax-l2-13b:extended
|
|
4676
4810
|
:name: MythoMax 13B (extended)
|
|
4677
4811
|
:created: 1688256000
|
|
@@ -4694,8 +4828,8 @@
|
|
|
4694
4828
|
max_completion_tokens: 400
|
|
4695
4829
|
is_moderated: false
|
|
4696
4830
|
:per_request_limits:
|
|
4697
|
-
prompt_tokens: '
|
|
4698
|
-
completion_tokens: '
|
|
4831
|
+
prompt_tokens: '17951246'
|
|
4832
|
+
completion_tokens: '17951246'
|
|
4699
4833
|
- :id: meta-llama/llama-2-13b-chat
|
|
4700
4834
|
:name: 'Meta: Llama v2 13B Chat'
|
|
4701
4835
|
:created: 1687219200
|
|
@@ -4716,8 +4850,8 @@
|
|
|
4716
4850
|
max_completion_tokens:
|
|
4717
4851
|
is_moderated: false
|
|
4718
4852
|
:per_request_limits:
|
|
4719
|
-
prompt_tokens: '
|
|
4720
|
-
completion_tokens: '
|
|
4853
|
+
prompt_tokens: '101995720'
|
|
4854
|
+
completion_tokens: '101995720'
|
|
4721
4855
|
- :id: openai/gpt-4-0314
|
|
4722
4856
|
:name: 'OpenAI: GPT-4 (older v0314)'
|
|
4723
4857
|
:created: 1685232000
|
|
@@ -4739,8 +4873,8 @@
|
|
|
4739
4873
|
max_completion_tokens: 4096
|
|
4740
4874
|
is_moderated: true
|
|
4741
4875
|
:per_request_limits:
|
|
4742
|
-
prompt_tokens: '
|
|
4743
|
-
completion_tokens: '
|
|
4876
|
+
prompt_tokens: '673171'
|
|
4877
|
+
completion_tokens: '336585'
|
|
4744
4878
|
- :id: openai/gpt-4
|
|
4745
4879
|
:name: 'OpenAI: GPT-4'
|
|
4746
4880
|
:created: 1685232000
|
|
@@ -4763,32 +4897,8 @@
|
|
|
4763
4897
|
max_completion_tokens: 4096
|
|
4764
4898
|
is_moderated: true
|
|
4765
4899
|
:per_request_limits:
|
|
4766
|
-
prompt_tokens: '
|
|
4767
|
-
completion_tokens: '
|
|
4768
|
-
- :id: openai/gpt-3.5-turbo-0301
|
|
4769
|
-
:name: 'OpenAI: GPT-3.5 Turbo (older v0301)'
|
|
4770
|
-
:created: 1685232000
|
|
4771
|
-
:description: |-
|
|
4772
|
-
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.
|
|
4773
|
-
|
|
4774
|
-
Training data up to Sep 2021.
|
|
4775
|
-
:context_length: 4095
|
|
4776
|
-
:architecture:
|
|
4777
|
-
modality: text->text
|
|
4778
|
-
tokenizer: GPT
|
|
4779
|
-
instruct_type:
|
|
4780
|
-
:pricing:
|
|
4781
|
-
prompt: '0.000001'
|
|
4782
|
-
completion: '0.000002'
|
|
4783
|
-
image: '0'
|
|
4784
|
-
request: '0'
|
|
4785
|
-
:top_provider:
|
|
4786
|
-
context_length: 4095
|
|
4787
|
-
max_completion_tokens: 4096
|
|
4788
|
-
is_moderated: true
|
|
4789
|
-
:per_request_limits:
|
|
4790
|
-
prompt_tokens: '20197816'
|
|
4791
|
-
completion_tokens: '10098908'
|
|
4900
|
+
prompt_tokens: '673171'
|
|
4901
|
+
completion_tokens: '336585'
|
|
4792
4902
|
- :id: openai/gpt-3.5-turbo-0125
|
|
4793
4903
|
:name: 'OpenAI: GPT-3.5 Turbo 16k'
|
|
4794
4904
|
:created: 1685232000
|
|
@@ -4811,8 +4921,8 @@
|
|
|
4811
4921
|
max_completion_tokens: 4096
|
|
4812
4922
|
is_moderated: true
|
|
4813
4923
|
:per_request_limits:
|
|
4814
|
-
prompt_tokens: '
|
|
4815
|
-
completion_tokens: '
|
|
4924
|
+
prompt_tokens: '40390305'
|
|
4925
|
+
completion_tokens: '13463435'
|
|
4816
4926
|
- :id: openai/gpt-3.5-turbo
|
|
4817
4927
|
:name: 'OpenAI: GPT-3.5 Turbo'
|
|
4818
4928
|
:created: 1685232000
|
|
@@ -4835,5 +4945,5 @@
|
|
|
4835
4945
|
max_completion_tokens: 4096
|
|
4836
4946
|
is_moderated: true
|
|
4837
4947
|
:per_request_limits:
|
|
4838
|
-
prompt_tokens: '
|
|
4839
|
-
completion_tokens: '
|
|
4948
|
+
prompt_tokens: '40390305'
|
|
4949
|
+
completion_tokens: '13463435'
|