Hugging Face's logo

Spaces:
L3n4
/
LibreChat
Paused

App Files Community
L3n4 commited on
Commit
7b074ea
·
verified ·
1 Parent(s): 40d8d4c

Update librechat.yaml

Browse files
Files changed (1) hide show
  1. librechat.yaml +1626 -64
librechat.yaml CHANGED
@@ -1,92 +1,1654 @@
1
- # Configuration version (required)
2
- version: 1.0.0
3
 
4
- # Cache settings: Set to true to enable caching
5
  cache: true
6
 
7
- # Definition of custom endpoints
 
 
 
 
 
 
 
8
  endpoints:
9
  custom:
10
- # Mistral AI API
11
- - name: "Mistral" # Unique name for the endpoint
12
- # For `apiKey` and `baseURL`, you can use environment variables that you define.
13
- # recommended environment variables:
14
- apiKey: "${MISTRAL_API_KEY}"
15
- baseURL: "https://api.mistral.ai/v1"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
 
17
- # Models configuration
18
- models:
19
- # List of default models to use. At least one value is required.
20
- default: ["mistral-tiny", "mistral-small", "mistral-medium"]
21
- # Fetch option: Set to true to fetch models from API.
22
- fetch: true # Defaults to false.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
 
24
- # Optional configurations
25
-
26
- # Title Conversation setting
27
- titleConvo: true # Set to true to enable title conversation
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
 
29
- # Title Method: Choose between "completion" or "functions".
30
- titleMethod: "completion" # Defaults to "completion" if omitted.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
 
32
- # Title Model: Specify the model to use for titles.
33
- titleModel: "mistral-tiny" # Defaults to "gpt-3.5-turbo" if omitted.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
 
35
- # Summarize setting: Set to true to enable summarization.
36
- summarize: false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
 
38
- # Summary Model: Specify the model to use if summarization is enabled.
39
- summaryModel: "mistral-tiny" # Defaults to "gpt-3.5-turbo" if omitted.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
 
41
- # Force Prompt setting: If true, sends a `prompt` parameter instead of `messages`.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  forcePrompt: false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
 
44
- # The label displayed for the AI model in messages.
45
- modelDisplayLabel: "Mistral" # Default is "AI" when not set.
46
-
47
- # Add additional parameters to the request. Default params will be overwritten.
48
- addParams:
49
- safe_mode: true # This field is specific to Mistral AI: https://docs.mistral.ai/api/
50
-
51
- # Drop Default params parameters from the request. See default params in guide linked below.
52
- dropParams: ["stop", "temperature", "top_p"]
53
- # - stop # dropped since it's not recognized by Mistral AI API
54
- # `temperature` and `top_p` are removed to allow Mistral AI API defaults to be used:
55
- # - temperature
56
- # - top_p
57
-
58
- # OpenRouter.ai Example
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
  - name: "OpenRouter"
60
- # For `apiKey` and `baseURL`, you can use environment variables that you define.
61
- # recommended environment variables:
62
- # Known issue: you should not use `OPENROUTER_API_KEY` as it will then override the `openAI` endpoint to use OpenRouter as well.
63
  apiKey: "${OPENROUTER_KEY}"
64
  baseURL: "https://openrouter.ai/api/v1"
65
  models:
66
- default: ["nousresearch/nous-capybara-7b:free", "mistralai/mistral-7b-instruct:free", "huggingfaceh4/zephyr-7b-beta:free", "openchat/openchat-7b:free", "gryphe/mythomist-7b:free", "undi95/toppy-m-7b:free", "openrouter/cinematika-7b:free", "openrouter/auto", "nousresearch/nous-capybara-7b", "mistralai/mistral-7b-instruct", "huggingfaceh4/zephyr-7b-beta", "openchat/openchat-7b", "gryphe/mythomist-7b", "openrouter/cinematika-7b", "rwkv/rwkv-5-world-3b", "recursal/rwkv-5-3b-ai-town", "jondurbin/bagel-34b", "jebcarter/psyfighter-13b", "koboldai/psyfighter-13b-2", "neversleep/noromaid-mixtral-8x7b-instruct", "nousresearch/nous-hermes-llama2-13b", "meta-llama/codellama-34b-instruct", "phind/phind-codellama-34b", "intel/neural-chat-7b", "nousresearch/nous-hermes-2-mixtral-8x7b-dpo", "nousresearch/nous-hermes-2-mixtral-8x7b-sft", "haotian-liu/llava-13b", "nousresearch/nous-hermes-2-vision-7b", "meta-llama/llama-2-13b-chat", "gryphe/mythomax-l2-13b", "nousresearch/nous-hermes-llama2-70b", "teknium/openhermes-2-mistral-7b", "teknium/openhermes-2.5-mistral-7b", "undi95/remm-slerp-l2-13b", "undi95/toppy-m-7b", "01-ai/yi-34b-chat", "01-ai/yi-34b", "01-ai/yi-6b", "togethercomputer/stripedhyena-nous-7b", "togethercomputer/stripedhyena-hessian-7b", "mistralai/mixtral-8x7b", "nousresearch/nous-hermes-yi-34b", "open-orca/mistral-7b-openorca", "openai/gpt-3.5-turbo", "openai/gpt-3.5-turbo-1106", "openai/gpt-3.5-turbo-16k", "openai/gpt-4-1106-preview", "openai/gpt-4", "openai/gpt-4-32k", "openai/gpt-4-vision-preview", "openai/gpt-3.5-turbo-instruct", "google/palm-2-chat-bison", "google/palm-2-codechat-bison", "google/palm-2-chat-bison-32k", "google/palm-2-codechat-bison-32k", "google/gemini-pro", "google/gemini-pro-vision", "perplexity/pplx-70b-online", "perplexity/pplx-7b-online", "perplexity/pplx-7b-chat", "perplexity/pplx-70b-chat", "meta-llama/llama-2-70b-chat", "nousresearch/nous-capybara-34b", "jondurbin/airoboros-l2-70b", "austism/chronos-hermes-13b", "migtissera/synthia-70b", "pygmalionai/mythalion-13b", "undi95/remm-slerp-l2-13b-6k", "xwin-lm/xwin-lm-70b", "gryphe/mythomax-l2-13b-8k", "alpindale/goliath-120b ", "lizpreciatior/lzlv-70b-fp16-hf", "neversleep/noromaid-20b", "mistralai/mixtral-8x7b-instruct", "cognitivecomputations/dolphin-mixtral-8x7b", "anthropic/claude-2", "anthropic/claude-2.0", "anthropic/claude-instant-v1", "mancer/weaver", "mistralai/mistral-tiny", "mistralai/mistral-small", "mistralai/mistral-medium"]
67
- fetch: true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  titleConvo: true
69
- titleModel: "gpt-3.5-turbo"
70
  summarize: false
71
- summaryModel: "gpt-3.5-turbo"
72
  forcePrompt: false
73
  modelDisplayLabel: "OpenRouter"
74
 
75
- - name: "Reverse Proxy"
76
- # For `apiKey` and `baseURL`, you can use environment variables that you define.
77
- # recommended environment variables:
78
- # Known issue: you should not use `OPENROUTER_API_KEY` as it will then override the `openAI` endpoint to use OpenRouter as well.
79
- apiKey: "user_provided"
80
- baseURL: "user_provided"
81
  models:
82
- default: ["gpt-3.5-turbo"]
83
- fetch: true
 
 
 
 
 
 
84
  titleConvo: true
85
- titleModel: "gpt-3.5-turbo"
86
  summarize: false
87
- summaryModel: "gpt-3.5-turbo"
88
  forcePrompt: false
89
- modelDisplayLabel: "AI"
 
 
 
90
 
91
- # See the Custom Configuration Guide for more information:
92
- # https://docs.librechat.ai/install/configuration/custom_config.html
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ version: 1.2.1
 
2
 
 
3
  cache: true
4
 
5
+ registration:
6
+ socialLogins:
7
+ - "discord"
8
+ - "facebook"
9
+ - "github"
10
+ - "google"
11
+ - "openid"
12
+
13
  endpoints:
14
  custom:
15
+ # APIpie
16
+ # https://apipie.ai/dashboard/
17
+ # Script to fetch models: https://github.com/LibreChat-AI/librechat-config-yaml/blob/main/scripts/apipie.py
18
+ - name: "APIpie"
19
+ apiKey: "${APIPIE_API_KEY}"
20
+ baseURL: "https://apipie.ai/v1/"
21
+ models:
22
+ default:
23
+ - DeepSeek-V3
24
+ - Llama-2-13b-chat-hf
25
+ - Llama-2-70b-chat-hf
26
+ - Llama-2-70b-hf
27
+ - Llama-2-7b-chat-hf
28
+ - Llama-3-70b-chat-hf
29
+ - Llama-3-8b-chat-hf
30
+ - Llama-3.1-Nemotron-70B-Instruct-HF
31
+ - Llama-3.2-11B-Vision-Instruct-Turbo
32
+ - Llama-3.2-3B-Instruct-Turbo
33
+ - Llama-3.2-90B-Vision-Instruct-Turbo
34
+ - Llama-3.3-70B-Instruct-Turbo
35
+ - Meta-Llama-3-70B-Instruct
36
+ - Meta-Llama-3-70B-Instruct-Lite
37
+ - Meta-Llama-3-70B-Instruct-Turbo
38
+ - Meta-Llama-3-8B-Instruct
39
+ - Meta-Llama-3-8B-Instruct-Lite
40
+ - Meta-Llama-3-8B-Instruct-Turbo
41
+ - Meta-Llama-3.1-70B-Instruct-Turbo
42
+ - Meta-Llama-3.1-8B-Instruct-Turbo
43
+ - Meta-Llama-3.1-8B-Instruct-Turbo-128K
44
+ - Mistral-7B-Instruct-v0.1
45
+ - Mistral-7B-Instruct-v0.2
46
+ - Mistral-7B-Instruct-v0.3
47
+ - Mixtral-8x22B-Instruct-v0.1
48
+ - Mixtral-8x22B-v0.1
49
+ - Mixtral-8x7B-Instruct-v0.1
50
+ - Mixtral-8x7B-v0.1
51
+ - MythoMax-L2-13b
52
+ - MythoMax-L2-13b-Lite
53
+ - Nous-Hermes-2-Mixtral-8x7B-DPO
54
+ - QwQ-32B-Preview
55
+ - Qwen2.5-72B-Instruct-Turbo
56
+ - Qwen2.5-7B-Instruct-Turbo
57
+ - SOLAR-10.7B-Instruct-v1.0
58
+ - WizardLM-2-7B
59
+ - WizardLM-2-8x22B
60
+ - aion-1.0
61
+ - aion-1.0-mini
62
+ - aion-rp-llama-3.1-8b
63
+ - airoboros-70b
64
+ - airoboros-l2-70b
65
+ - amazon.nova-lite-v1:0
66
+ - amazon.nova-micro-v1:0
67
+ - amazon.nova-pro-v1:0
68
+ - chatgpt-4o-latest
69
+ - chatx_cheap_128k
70
+ - chatx_cheap_32k
71
+ - chatx_cheap_4k
72
+ - chatx_cheap_64k
73
+ - chatx_cheap_8k
74
+ - chatx_mids_4k
75
+ - chatx_premium_128k
76
+ - chatx_premium_32k
77
+ - chatx_premium_4k
78
+ - chatx_premium_8k
79
+ - chronos-hermes-13b-v2
80
+ - claude-2
81
+ - claude-2.0
82
+ - claude-2.1
83
+ - claude-3-5-haiku
84
+ - claude-3-5-haiku-20241022
85
+ - claude-3-5-haiku-20241022-v1
86
+ - claude-3-5-haiku-latest
87
+ - claude-3-5-sonnet
88
+ - claude-3-5-sonnet-20240620
89
+ - claude-3-5-sonnet-20240620-v1
90
+ - claude-3-5-sonnet-20241022
91
+ - claude-3-5-sonnet-20241022-v2
92
+ - claude-3-5-sonnet-latest
93
+ - claude-3-7-sonnet-20250219
94
+ - claude-3-7-sonnet-20250219-v1
95
+ - claude-3-7-sonnet-latest
96
+ - claude-3-haiku
97
+ - claude-3-haiku-20240307
98
+ - claude-3-haiku-20240307-v1
99
+ - claude-3-opus
100
+ - claude-3-opus-20240229
101
+ - claude-3-opus-20240229-v1
102
+ - claude-3-opus-latest
103
+ - claude-3-sonnet
104
+ - claude-3-sonnet-20240229
105
+ - claude-3-sonnet-20240229-v1
106
+ - claude-3.5-haiku
107
+ - claude-3.5-haiku-20241022
108
+ - claude-3.5-sonnet
109
+ - claude-3.5-sonnet-20240620
110
+ - claude-3.7-sonnet
111
+ - claude2
112
+ - codestral-2501
113
+ - codestral-mamba
114
+ - command
115
+ - command-light
116
+ - command-light-text-v14
117
+ - command-nightly
118
+ - command-r
119
+ - command-r-03-2024
120
+ - command-r-08-2024
121
+ - command-r-plus
122
+ - command-r-plus-04-2024
123
+ - command-r-plus-08-2024
124
+ - command-r-plus-v1
125
+ - command-r-v1
126
+ - command-r7b-12-2024
127
+ - command-text-v14
128
+ - dbrx-instruct
129
+ - deepseek-chat
130
+ - deepseek-r1
131
+ - deepseek-r1-distill-llama-70b
132
+ - deepseek-r1-distill-llama-8b
133
+ - deepseek-r1-distill-qwen-1.5b
134
+ - deepseek-r1-distill-qwen-14b
135
+ - deepseek-r1-distill-qwen-32b
136
+ - dolphin-2.6-mixtral-8x7b
137
+ - dolphin-mixtral-8x22b
138
+ - dolphin-mixtral-8x7b
139
+ - dolphin3.0-mistral-24b
140
+ - dolphin3.0-r1-mistral-24b
141
+ - eva-llama-3.33-70b
142
+ - eva-qwen-2.5-32b
143
+ - eva-qwen-2.5-72b
144
+ - fimbulvetr-11b-v2
145
+ - gemini-1.5-flash
146
+ - gemini-1.5-flash-8b
147
+ - gemini-1.5-flash-8b-latest
148
+ - gemini-1.5-flash-latest
149
+ - gemini-1.5-pro
150
+ - gemini-1.5-pro-latest
151
+ - gemini-2.0-flash
152
+ - gemini-2.0-flash-001
153
+ - gemini-2.0-flash-lite-001
154
+ - gemini-2.0-flash-lite-preview-02-05
155
+ - gemini-2.0-flash-thinking-exp-1219
156
+ - gemini-2.0-pro-exp-02-05
157
+ - gemini-flash
158
+ - gemini-flash-1.5
159
+ - gemini-flash-1.5-8b
160
+ - gemini-pro
161
+ - gemini-pro-1.5
162
+ - gemini-pro-vision
163
+ - gemma-1.1-7b-it
164
+ - gemma-2-27b-it
165
+ - gemma-2-9b-it
166
+ - gemma-2b-it
167
+ - gemma-7b-it
168
+ - general
169
+ - goliath-120b
170
+ - gpt-3.5
171
+ - gpt-3.5-turbo
172
+ - gpt-3.5-turbo-0125
173
+ - gpt-3.5-turbo-0613
174
+ - gpt-3.5-turbo-1106
175
+ - gpt-3.5-turbo-16k
176
+ - gpt-3.5-turbo-instruct
177
+ - gpt-4
178
+ - gpt-4-0125-preview
179
+ - gpt-4-0314
180
+ - gpt-4-0613
181
+ - gpt-4-1106-preview
182
+ - gpt-4-1106-vision-preview
183
+ - gpt-4-32k
184
+ - gpt-4-32k-0314
185
+ - gpt-4-turbo
186
+ - gpt-4-turbo-2024-04-09
187
+ - gpt-4-turbo-preview
188
+ - gpt-4-vision-preview
189
+ - gpt-4o
190
+ - gpt-4o-2024-05-13
191
+ - gpt-4o-2024-08-06
192
+ - gpt-4o-2024-11-20
193
+ - gpt-4o-audio-preview-2024-10-01
194
+ - gpt-4o-audio-preview-2024-12-17
195
+ - gpt-4o-mini
196
+ - gpt-4o-mini-2024-07-18
197
+ - gpt-4o-mini-audio-preview
198
+ - gpt-4o-mini-audio-preview-2024-12-17
199
+ - grok-2-1212
200
+ - grok-2-vision-1212
201
+ - grok-beta
202
+ - grok-vision-beta
203
+ - hermes-2-pro-llama-3-8b
204
+ - hermes-3-llama-3.1-405b
205
+ - hermes-3-llama-3.1-70b
206
+ - inflection-3-pi
207
+ - j2-grande-instruct
208
+ - j2-jumbo-instruct
209
+ - j2-mid
210
+ - j2-mid-v1
211
+ - j2-ultra
212
+ - j2-ultra-v1
213
+ - jamba-1-5-large
214
+ - jamba-1-5-large-v1
215
+ - jamba-1-5-mini
216
+ - jamba-1-5-mini-v1
217
+ - jamba-instruct
218
+ - jamba-instruct-v1
219
+ - l3-euryale-70b
220
+ - l3-lunaris-8b
221
+ - l3.1-70b-hanami-x1
222
+ - l3.1-euryale-70b
223
+ - l3.3-euryale-70b
224
+ - lfm-3b
225
+ - lfm-40b
226
+ - lfm-7b
227
+ - llama-2-13b-chat
228
+ - llama-2-70b-chat
229
+ - llama-3-70b-instruct
230
+ - llama-3-8b-instruct
231
+ - llama-3-lumimaid-70b
232
+ - llama-3-lumimaid-8b
233
+ - llama-3-sonar-large-32k-chat
234
+ - llama-3.1-405b
235
+ - llama-3.1-405b-instruct
236
+ - llama-3.1-70b-instruct
237
+ - llama-3.1-8b-instruct
238
+ - llama-3.1-lumimaid-70b
239
+ - llama-3.1-lumimaid-8b
240
+ - llama-3.1-nemotron-70b-instruct
241
+ - llama-3.1-sonar-huge-128k-online
242
+ - llama-3.1-sonar-large-128k-chat
243
+ - llama-3.1-sonar-large-128k-online
244
+ - llama-3.1-sonar-small-128k-chat
245
+ - llama-3.1-sonar-small-128k-online
246
+ - llama-3.1-tulu-3-405b
247
+ - llama-3.2-11b-vision-instruct
248
+ - llama-3.2-1b-instruct
249
+ - llama-3.2-3b-instruct
250
+ - llama-3.2-90b-vision-instruct
251
+ - llama-3.3-70b-instruct
252
+ - llama-guard-2-8b
253
+ - llama-guard-3-8b
254
+ - llama2-13b-chat-v1
255
+ - llama2-70b-chat-v1
256
+ - llama3-1
257
+ - llama3-1-405b-instruct-v1:0
258
+ - llama3-1-70b-instruct-v1
259
+ - llama3-1-70b-instruct-v1:0
260
+ - llama3-1-8b-instruct-v1
261
+ - llama3-1-8b-instruct-v1:0
262
+ - llama3-2
263
+ - llama3-2-11b-instruct-v1
264
+ - llama3-2-1b-instruct-v1
265
+ - llama3-2-3b-instruct-v1
266
+ - llama3-2-90b-instruct-v1
267
+ - llama3-3-70b-instruct-v1
268
+ - llama3-70b-instruct-v1
269
+ - llama3-8b-instruct-v1
270
+ - magnum-72b
271
+ - magnum-v2-72b
272
+ - magnum-v4-72b
273
+ - meta-llama-3.1-8b-instruct
274
+ - midnight-rose-70b
275
+ - minimax-01
276
+ - ministral-3b
277
+ - ministral-8b
278
+ - mistral
279
+ - mistral-7b-instruct
280
+ - mistral-7b-instruct-v0
281
+ - mistral-7b-instruct-v0.1
282
+ - mistral-7b-instruct-v0.3
283
+ - mistral-large
284
+ - mistral-large-2402-v1
285
+ - mistral-large-2407
286
+ - mistral-large-2411
287
+ - mistral-large-latest
288
+ - mistral-medium
289
+ - mistral-nemo
290
+ - mistral-saba
291
+ - mistral-small
292
+ - mistral-small-2402-v1
293
+ - mistral-small-24b-instruct-2501
294
+ - mistral-small-latest
295
+ - mistral-tiny
296
+ - mixtral
297
+ - mixtral-8x22b-instruct
298
+ - mixtral-8x7b
299
+ - mixtral-8x7b-instruct
300
+ - mixtral-8x7b-instruct-v0
301
+ - mn-celeste-12b
302
+ - mn-inferor-12b
303
+ - mn-starcannon-12b
304
+ - mythalion-13b
305
+ - mythomax-l2-13b
306
+ - nai-meta-v1
307
+ - noromaid-20b
308
+ - nous-hermes-2-mixtral-8x7b-dpo
309
+ - nous-hermes-2-vision-7b
310
+ - nous-hermes-llama2-13b
311
+ - nova-canvas-v1
312
+ - nova-lite-v1
313
+ - nova-micro-v1
314
+ - nova-pro-v1
315
+ - nova-reel-v1
316
+ - o1
317
+ - o1-2024-12-17
318
+ - o1-mini
319
+ - o1-mini-2024-09-12
320
+ - o1-preview
321
+ - o1-preview-2024-09-12
322
+ - o3-mini
323
+ - o3-mini-2025-01-31
324
+ - o3-mini-high
325
+ - olympus-premier-v1
326
+ - online-llama
327
+ - openchat-7b
328
+ - openchat_3.5
329
+ - openhermes-2.5-mistral-7b
330
+ - palm-2-chat-bison
331
+ - palm-2-chat-bison-32k
332
+ - palm-2-codechat-bison
333
+ - palm-2-codechat-bison-32k
334
+ - phi-3-medium-128k-instruct
335
+ - phi-3-mini-128k-instruct
336
+ - phi-3.5-mini-128k-instruct
337
+ - phi-4
338
+ - pixtral-12b
339
+ - pixtral-large-2411
340
+ - pixtral-large-latest
341
+ - qvq-72b-preview
342
+ - qwen-2-72b-instruct
343
+ - qwen-2-vl-72b-instruct
344
+ - qwen-2-vl-7b-instruct
345
+ - qwen-2.5-72b-instruct
346
+ - qwen-2.5-7b-instruct
347
+ - qwen-2.5-coder-32b-instruct
348
+ - qwen-max
349
+ - qwen-plus
350
+ - qwen-turbo
351
+ - qwen-vl-plus
352
+ - qwen1-5
353
+ - qwen2
354
+ - qwen2.5-vl-72b-instruct
355
+ - qwq-32b-preview
356
+ - r1-1776
357
+ - remm-slerp-l2-13b
358
+ - rocinante-12b
359
+ - rogue-rose-103b-v0.2
360
+ - scb10x-llama3-typhoon-v1-5-8b-instruct
361
+ - scb10x-llama3-typhoon-v1-5x-4f316
362
+ - sonar
363
+ - sonar-reasoning
364
+ - sorcererlm-8x22b
365
+ - titan
366
+ - titan-text-express-v1
367
+ - titan-text-lite-v1
368
+ - titan-text-premier-v1
369
+ - titan-tg1-large
370
+ - toppy-m-7b
371
+ - unslopnemo-12b
372
+ - weaver
373
+ - wizardlm-2-7b
374
+ - wizardlm-2-8x22b
375
+ - xwin-lm-70b
376
+ - yi-large
377
+ - yi-vision
378
+ - zephyr-orpo-141b-A35b-v0.1
379
+ fetch: false
380
+ titleConvo: true
381
+ titleModel: "claude-3-haiku"
382
+ summarize: false
383
+ summaryModel: "claude-3-haiku"
384
+ dropParams:
385
+ - "stream"
386
+ modelDisplayLabel: "APIpie"
387
+ iconURL: "https://raw.githubusercontent.com/fuegovic/lc-config-yaml/main/icons/APIpie.png"
388
 
389
+ # cohere
390
+ # Model list: https://dashboard.cohere.com/playground/chat
391
+ - name: "cohere"
392
+ apiKey: "${COHERE_API_KEY}"
393
+ baseURL: "https://api.cohere.ai/v1"
394
+ models:
395
+ default:
396
+ - c4ai-aya-expanse-32b
397
+ - command
398
+ - command-light-nightly
399
+ - command-r
400
+ - command-r-08-2024
401
+ - command-r-plus
402
+ - command-r-plus-08-2024
403
+ - command-r7b-12-2024
404
+ fetch: false
405
+ modelDisplayLabel: "cohere"
406
+ titleModel: "command"
407
+ dropParams:
408
+ - "stop"
409
+ - "user"
410
+ - "frequency_penalty"
411
+ - "presence_penalty"
412
+ - "temperature"
413
+ - "top_p"
414
+
415
+ # deepseek
416
+ # https://platform.deepseek.com/api_keys
417
+ # Model list: https://platform.deepseek.com/api-docs/pricing
418
+ - name: "deepseek"
419
+ apiKey: "${DEEPSEEK_API_KEY}"
420
+ baseURL: "https://api.deepseek.com"
421
+ models:
422
+ default:
423
+ - deepseek-chat
424
+ - deepseek-reasoner
425
+ fetch: false
426
+ titleConvo: true
427
+ titleModel: "deepseek-chat"
428
+ summarize: false
429
+ summaryModel: "deepseek-chat"
430
+ modelDisplayLabel: "DeepSeek"
431
+
432
+ # Fireworks.ai
433
+ # Models: https://fireworks.ai/models?show=Serverless
434
+ - name: "Fireworks"
435
+ apiKey: "${FIREWORKS_API_KEY}"
436
+ baseURL: "https://api.fireworks.ai/inference/v1"
437
+ models:
438
+ default:
439
+ - accounts/fireworks/models/deepseek-r1
440
+ - accounts/fireworks/models/deepseek-v3
441
+ - accounts/fireworks/models/llama-guard-3-8b
442
+ - accounts/fireworks/models/llama-v3-70b-instruct
443
+ - accounts/fireworks/models/llama-v3-8b-instruct
444
+ - accounts/fireworks/models/llama-v3-8b-instruct-hf
445
+ - accounts/fireworks/models/llama-v3p1-405b-instruct
446
+ - accounts/fireworks/models/llama-v3p1-405b-instruct-long
447
+ - accounts/fireworks/models/llama-v3p1-70b-instruct
448
+ - accounts/fireworks/models/llama-v3p1-8b-instruct
449
+ - accounts/fireworks/models/llama-v3p2-11b-vision-instruct
450
+ - accounts/fireworks/models/llama-v3p2-3b-instruct
451
+ - accounts/fireworks/models/llama-v3p2-90b-vision-instruct
452
+ - accounts/fireworks/models/llama-v3p3-70b-instruct
453
+ - accounts/fireworks/models/mistral-small-24b-instruct-2501
454
+ - accounts/fireworks/models/mixtral-8x22b-instruct
455
+ - accounts/fireworks/models/mixtral-8x7b-instruct
456
+ - accounts/fireworks/models/mythomax-l2-13b
457
+ - accounts/fireworks/models/phi-3-vision-128k-instruct
458
+ - accounts/fireworks/models/qwen-qwq-32b-preview
459
+ - accounts/fireworks/models/qwen2-vl-72b-instruct
460
+ - accounts/fireworks/models/qwen2p5-72b-instruct
461
+ - accounts/fireworks/models/qwen2p5-coder-32b-instruct
462
+ - accounts/mels-e0299e/models/aiderlm-v0
463
+ - accounts/perplexity/models/r1-1776
464
+ - accounts/sentientfoundation/models/dobby-mini-leashed-llama-3-1-8b
465
+ - accounts/sentientfoundation/models/dobby-mini-unhinged-llama-3-1-8b
466
+ - accounts/sentientfoundation/models/dobby-unhinged-llama-3-3-70b-new
467
+ - accounts/yi-01-ai/models/yi-large
468
+ fetch: false
469
+ titleConvo: true
470
+ titleModel: "accounts/fireworks/models/llama-v2-7b-chat"
471
+ summarize: false
472
+ summaryModel: "accounts/fireworks/models/llama-v2-7b-chat"
473
+ forcePrompt: false
474
+ modelDisplayLabel: "Fireworks"
475
+ dropParams:
476
+ - "user"
477
 
478
+ # GitHub
479
+ - name: "Github Models"
480
+ iconURL: https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png
481
+ apiKey: "${GITHUB_TOKEN}"
482
+ baseURL: "https://models.inference.ai.azure.com"
483
+ models:
484
+ default:
485
+ - AI21-Jamba-Instruct
486
+ - Cohere-command-r
487
+ - Cohere-command-r-plus
488
+ - Cohere-embed-v3-english
489
+ - Cohere-embed-v3-multilingual
490
+ - Meta-Llama-3-70B-Instruct
491
+ - Meta-Llama-3-8B-Instruct
492
+ - Meta-Llama-3.1-405B-Instruct
493
+ - Meta-Llama-3.1-70B-Instruct
494
+ - Meta-Llama-3.1-8B-Instruct
495
+ - Mistral-Nemo
496
+ - Mistral-large
497
+ - Mistral-large-2407
498
+ - Mistral-small
499
+ - Phi-3-medium-128k-instruct
500
+ - Phi-3-medium-4k-instruct
501
+ - Phi-3-mini-128k-instruct
502
+ - Phi-3-mini-4k-instruct
503
+ - Phi-3-small-128k-instruct
504
+ - Phi-3-small-8k-instruct
505
+ - Phi-3.5-mini-instruct
506
+ - gpt-4o
507
+ - gpt-4o-mini
508
+ - text-embedding-3-large
509
+ - text-embedding-3-small
510
+ fetch: false
511
+ titleConvo: true
512
+ titleModel: "gpt-4o-mini"
513
 
514
+ # groq
515
+ # Model list: https://console.groq.com/settings/limits
516
+ - name: "groq"
517
+ apiKey: "${GROQ_API_KEY}"
518
+ baseURL: "https://api.groq.com/openai/v1/"
519
+ models:
520
+ default:
521
+ - deepseek-r1-distill-llama-70b
522
+ - deepseek-r1-distill-qwen-32b
523
+ - gemma2-9b-it
524
+ - llama-3.1-8b-instant
525
+ - llama-3.2-11b-vision-preview
526
+ - llama-3.2-1b-preview
527
+ - llama-3.2-3b-preview
528
+ - llama-3.2-90b-vision-preview
529
+ - llama-3.3-70b-specdec
530
+ - llama-3.3-70b-versatile
531
+ - llama-guard-3-8b
532
+ - llama3-70b-8192
533
+ - llama3-8b-8192
534
+ - mistral-saba-24b
535
+ - mixtral-8x7b-32768
536
+ - qwen-2.5-32b
537
+ - qwen-2.5-coder-32b
538
+ fetch: false
539
+ titleConvo: true
540
+ titleModel: "mixtral-8x7b-32768"
541
+ modelDisplayLabel: "groq"
542
 
543
+ # HuggingFace
544
+ # https://huggingface.co/settings/tokens
545
+ - name: 'HuggingFace'
546
+ apiKey: '${HUGGINGFACE_TOKEN}'
547
+ baseURL: 'https://api-inference.huggingface.co/v1'
548
+ models:
549
+ default:
550
+ - AIDC-AI/Marco-o1
551
+ - BioMistral/BioMistral-7B
552
+ - CohereForAI/c4ai-command-r-plus
553
+ - CohereForAI/c4ai-command-r-v01
554
+ - HuggingFaceH4/zephyr-7b-alpha
555
+ - HuggingFaceH4/zephyr-7b-beta
556
+ - HuggingFaceTB/SmolLM2-1.7B-Instruct
557
+ - Intel/neural-chat-7b-v3-1
558
+ - MiniMaxAI/MiniMax-Text-01
559
+ - NexaAIDev/Octopus-v2
560
+ - NousResearch/Hermes-2-Pro-Mistral-7B
561
+ - NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
562
+ - NovaSky-AI/Sky-T1-32B-Preview
563
+ - Open-Orca/Mistral-7B-OpenOrca
564
+ - PygmalionAI/pygmalion-6b
565
+ - Qwen/QwQ-32B-Preview
566
+ - Qwen/Qwen2-72B-Instruct
567
+ - Qwen/Qwen2-7B-Instruct
568
+ - Qwen/Qwen2.5-72B-Instruct
569
+ - Qwen/Qwen2.5-7B-Instruct
570
+ - Qwen/Qwen2.5-Coder-32B-Instruct
571
+ - Qwen/Qwen2.5-Coder-7B-Instruct
572
+ - TheBloke/Mistral-7B-Instruct-v0.2-GGUF
573
+ - TinyLlama/TinyLlama-1.1B-Chat-v1.0
574
+ - berkeley-nest/Starling-LM-7B-alpha
575
+ - cognitivecomputations/dolphin-2.5-mixtral-8x7b
576
+ - cognitivecomputations/dolphin-2.9-llama3-8b
577
+ - databricks/dbrx-base
578
+ - databricks/dbrx-instruct
579
+ - deepseek-ai/DeepSeek-Coder-V2-Instruct
580
+ - deepseek-ai/DeepSeek-R1
581
+ - deepseek-ai/DeepSeek-R1-Distill-Llama-70B
582
+ - deepseek-ai/DeepSeek-R1-Distill-Llama-8B
583
+ - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
584
+ - deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
585
+ - deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
586
+ - deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
587
+ - deepseek-ai/DeepSeek-R1-Zero
588
+ - deepseek-ai/DeepSeek-V2-Chat
589
+ - deepseek-ai/DeepSeek-V2.5
590
+ - deepseek-ai/DeepSeek-V3
591
+ - deepseek-ai/deepseek-coder-33b-instruct
592
+ - google/gemma-2-27b-it
593
+ - google/gemma-2-2b-it
594
+ - google/gemma-2-9b-it
595
+ - google/gemma-2b-it
596
+ - google/gemma-7b-it
597
+ - gradientai/Llama-3-8B-Instruct-Gradient-1048k
598
+ - jinaai/ReaderLM-v2
599
+ - jinaai/reader-lm-1.5b
600
+ - mattshumer/Reflection-Llama-3.1-70B
601
+ - meta-llama/Llama-2-13b-chat-hf
602
+ - meta-llama/Llama-2-70b-chat-hf
603
+ - meta-llama/Llama-2-7b-chat-hf
604
+ - meta-llama/Llama-3.1-405B-Instruct
605
+ - meta-llama/Llama-3.1-70B-Instruct
606
+ - meta-llama/Llama-3.1-8B-Instruct
607
+ - meta-llama/Llama-3.2-1B-Instruct
608
+ - meta-llama/Llama-3.2-3B-Instruct
609
+ - meta-llama/Llama-3.3-70B-Instruct
610
+ - meta-llama/Meta-Llama-3-70B-Instruct
611
+ - meta-llama/Meta-Llama-3-8B-Instruct
612
+ - microsoft/Phi-3-mini-128k-instruct
613
+ - microsoft/Phi-3-mini-4k-instruct
614
+ - microsoft/Phi-3-vision-128k-instruct
615
+ - microsoft/Phi-3.5-MoE-instruct
616
+ - microsoft/Phi-3.5-mini-instruct
617
+ - microsoft/phi-4
618
+ - mistralai/Codestral-22B-v0.1
619
+ - mistralai/Mistral-7B-Instruct-v0.1
620
+ - mistralai/Mistral-7B-Instruct-v0.2
621
+ - mistralai/Mistral-7B-Instruct-v0.3
622
+ - mistralai/Mistral-Nemo-Instruct-2407
623
+ - mistralai/Mistral-Small-24B-Instruct-2501
624
+ - mistralai/Mixtral-8x22B-Instruct-v0.1
625
+ - mistralai/Mixtral-8x7B-Instruct-v0.1
626
+ - nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
627
+ - nvidia/Llama3-ChatQA-1.5-8B
628
+ - openchat/openchat_3.5
629
+ - shenzhi-wang/Llama3-8B-Chinese-Chat
630
+ - teknium/OpenHermes-2.5-Mistral-7B
631
+ - tiiuae/falcon-180B-chat
632
+ - tiiuae/falcon-7b-instruct
633
+ - unsloth/DeepSeek-R1-GGUF
634
+ - upstage/SOLAR-10.7B-Instruct-v1.0
635
+ - upstage/solar-pro-preview-instruct
636
+ fetch: false
637
+ titleConvo: true
638
+ titleModel: "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO"
639
+ dropParams:
640
+ - "top_p"
641
 
642
+ # Hyperbolic
643
+ # https://app.hyperbolic.xyz/models
644
+ - name: 'Hyperbolic'
645
+ apiKey: '${HYPERBOLIC_API_KEY}'
646
+ baseURL: 'https://api.hyperbolic.xyz/v1/'
647
+ models:
648
+ default:
649
+ - NousResearch/Hermes-3-Llama-3.1-70B
650
+ - Qwen/QwQ-32B-Preview
651
+ - Qwen/Qwen2-VL-72B-Instruct
652
+ - Qwen/Qwen2-VL-7B-Instruct
653
+ - Qwen/Qwen2.5-72B-Instruct
654
+ - Qwen/Qwen2.5-Coder-32B-Instruct
655
+ - deepseek-ai/DeepSeek-R1
656
+ - deepseek-ai/DeepSeek-V3
657
+ - meta-llama/Llama-3.2-3B-Instruct
658
+ - meta-llama/Llama-3.3-70B-Instruct
659
+ - meta-llama/Meta-Llama-3-70B-Instruct
660
+ - meta-llama/Meta-Llama-3.1-405B
661
+ - meta-llama/Meta-Llama-3.1-405B-FP8
662
+ - meta-llama/Meta-Llama-3.1-405B-Instruct
663
+ - meta-llama/Meta-Llama-3.1-405B-Instruct-Virtuals
664
+ - meta-llama/Meta-Llama-3.1-70B-Instruct
665
+ - meta-llama/Meta-Llama-3.1-8B-Instruct
666
+ - mistralai/Pixtral-12B-2409
667
+ fetch: false
668
+ titleConvo: true
669
+ titleModel: "meta-llama/Meta-Llama-3.1-8B-Instruct"
670
+ modelDisplayLabel: "Hyperbolic"
671
+ iconURL: "https://app.hyperbolic.xyz/icon.svg"
672
 
673
+ # kluster.ai
674
+ # https://platform.kluster.ai/apikeys
675
+ - name: "Kluster"
676
+ apiKey: "${KLUSTER_API_KEY}"
677
+ baseURL: "https://api.kluster.ai/v1/"
678
+ models:
679
+ default:
680
+ - deepseek-ai/DeepSeek-R1
681
+ - klusterai/Meta-Llama-3.1-405B-Instruct-Turbo
682
+ - klusterai/Meta-Llama-3.1-8B-Instruct-Turbo
683
+ - klusterai/Meta-Llama-3.3-70B-Instruct-Turbo
684
+ fetch: false
685
+ titleConvo: true
686
+ titleModel: 'klusterai/Meta-Llama-3.1-8B-Instruct-Turbo'
687
+ modelDisplayLabel: 'Kluster'
688
+ iconURL: "https://platform.kluster.ai/cropped-fav-1-144x144.png"
689
 
690
+ # Mistral AI API
691
+ # Model list: https://docs.mistral.ai/getting-started/models/
692
+ - name: "Mistral"
693
+ apiKey: "${MISTRAL_API_KEY}"
694
+ baseURL: "https://api.mistral.ai/v1"
695
+ models:
696
+ default:
697
+ - codestral-2405
698
+ - codestral-2411-rc5
699
+ - codestral-2412
700
+ - codestral-2501
701
+ - codestral-latest
702
+ - codestral-mamba-2407
703
+ - codestral-mamba-latest
704
+ - ministral-3b-2410
705
+ - ministral-3b-latest
706
+ - ministral-8b-2410
707
+ - ministral-8b-latest
708
+ - mistral-embed
709
+ - mistral-large-2402
710
+ - mistral-large-2407
711
+ - mistral-large-2411
712
+ - mistral-large-latest
713
+ - mistral-large-pixtral-2411
714
+ - mistral-medium
715
+ - mistral-medium-2312
716
+ - mistral-medium-latest
717
+ - mistral-moderation-2411
718
+ - mistral-moderation-latest
719
+ - mistral-saba-2502
720
+ - mistral-saba-latest
721
+ - mistral-small
722
+ - mistral-small-2312
723
+ - mistral-small-2402
724
+ - mistral-small-2409
725
+ - mistral-small-2501
726
+ - mistral-small-latest
727
+ - mistral-tiny
728
+ - mistral-tiny-2312
729
+ - mistral-tiny-2407
730
+ - mistral-tiny-latest
731
+ - open-codestral-mamba
732
+ - open-mistral-7b
733
+ - open-mistral-nemo
734
+ - open-mistral-nemo-2407
735
+ - open-mixtral-8x22b
736
+ - open-mixtral-8x22b-2404
737
+ - open-mixtral-8x7b
738
+ - pixtral-12b
739
+ - pixtral-12b-2409
740
+ - pixtral-12b-latest
741
+ - pixtral-large-2411
742
+ - pixtral-large-latest
743
+ fetch: false
744
+ titleConvo: true
745
+ titleMethod: "completion"
746
+ titleModel: "mistral-tiny"
747
+ summarize: false
748
+ summaryModel: "mistral-tiny"
749
  forcePrompt: false
750
+ modelDisplayLabel: "Mistral"
751
+ dropParams:
752
+ - "stop"
753
+ - "user"
754
+ - "frequency_penalty"
755
+ - "presence_penalty"
756
+
757
+ # NanoGPT
758
+ # https://nano-gpt.com/api
759
+ # Model list: https://nano-gpt.com/api/models
760
+ - name: "NanoGPT"
761
+ iconURL: "https://nano-gpt.com/logo.png"
762
+ apiKey: "${NANOGPT_API_KEY}"
763
+ baseURL: "https://nano-gpt.com/api/v1/"
764
+ models:
765
+ default:
766
+ - EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0
767
+ - EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
768
+ - EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
769
+ - EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2
770
+ - Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B
771
+ - Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B
772
+ - GalrionSoftworks/MN-LooseCannon-12B-v1
773
+ - Gryphe/MythoMax-L2-13b
774
+ - Infermatic/MN-12B-Inferor-v0.0
775
+ - LatitudeGames/Wayfarer-Large-70B-Llama-3.3
776
+ - Llama-3.1-Tulu-3-405B
777
+ - Llama-3.3+3.1-70B-ArliAI-RPMax-v1.3
778
+ - Llama-3.3-70B-MiraiFanfare
779
+ - MarinaraSpaghetti/NemoMix-Unleashed-12B
780
+ - Meta-Llama-3-1-405B-Instruct-FP8
781
+ - Meta-Llama-3-1-8B-Instruct-FP8
782
+ - Mistral-Nemo-12B-ArliAI-RPMax-v1.2
783
+ - Mistral-Nemo-12B-Wayfarer
784
+ - NeverSleep/Llama-3-Lumimaid-70B-v0.1
785
+ - NeverSleep/Lumimaid-v0.2-70B
786
+ - Nexusflow/Athene-V2-Chat
787
+ - Qwen/QwQ-32B-Preview
788
+ - Qwen/Qwen2.5-Coder-32B-Instruct
789
+ - Qwen2.5-32B-Dazzling-Star-Aurora-32b-v0.0
790
+ - Qwen2.5-32B-EVA-v0.2
791
+ - Sao10K/L3.1-70B-Euryale-v2.2
792
+ - Sao10K/L3.1-70B-Hanami-x1
793
+ - Sao10K/L3.3-70B-Euryale-v2.3
794
+ - Steelskull/L3.3-Damascus-R1
795
+ - Steelskull/L3.3-MS-Evalebis-70b
796
+ - Steelskull/L3.3-MS-Evayale-70B
797
+ - TheDrummer/Anubis-70B-v1
798
+ - TheDrummer/Cydonia-24B-v2
799
+ - TheDrummer/Rocinante-12B-v1.1
800
+ - TheDrummer/UnslopNemo-12B-v4.1
801
+ - VongolaChouko/Starcannon-Unleashed-12B-v1.0
802
+ - abacusai/Dracarys-72B-Instruct
803
+ - aion-labs/aion-1.0
804
+ - aion-labs/aion-1.0-mini
805
+ - aion-labs/aion-rp-llama-3.1-8b
806
+ - amazon/nova-lite-v1
807
+ - amazon/nova-micro-v1
808
+ - amazon/nova-pro-v1
809
+ - anthracite-org/magnum-v2-72b
810
+ - anthracite-org/magnum-v4-72b
811
+ - azure-gpt-4-turbo
812
+ - azure-gpt-4o
813
+ - azure-gpt-4o-mini
814
+ - azure-o1
815
+ - azure-o3-mini
816
+ - chatgpt-4o-latest
817
+ - claude-3-5-haiku-20241022
818
+ - claude-3-5-sonnet-20240620
819
+ - claude-3-5-sonnet-20241022
820
+ - claude-3-7-sonnet-20250219
821
+ - claude-3-7-sonnet-thinking
822
+ - claude-3-7-sonnet-thinking:1024
823
+ - claude-3-7-sonnet-thinking:128000
824
+ - claude-3-7-sonnet-thinking:32768
825
+ - claude-3-7-sonnet-thinking:8192
826
+ - claude-3-opus-20240229
827
+ - cognitivecomputations/dolphin-mixtral-8x22b
828
+ - cohere/command-r
829
+ - cohere/command-r-plus-08-2024
830
+ - deep-research
831
+ - deepclaude
832
+ - deepseek-ai/DeepSeek-R1-Zero
833
+ - deepseek-chat
834
+ - deepseek-chat-cheaper
835
+ - deepseek-r1-llama-70b
836
+ - deepseek-r1-nano
837
+ - deepseek-r1-sambanova
838
+ - deepseek-reasoner
839
+ - deepseek-reasoner-cheaper
840
+ - dolphin-2.9.2-qwen2-72b
841
+ - doubao-1.5-pro-256k
842
+ - doubao-1.5-pro-32k
843
+ - doubao-1.5-vision-pro-32k
844
+ - eva-unit-01/eva-qwen-2.5-72b
845
+ - failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5
846
+ - free-model
847
+ - gemini-2.0-flash-001
848
+ - gemini-2.0-flash-exp-search
849
+ - gemini-2.0-flash-lite
850
+ - gemini-2.0-flash-thinking-exp-01-21
851
+ - gemini-2.0-flash-thinking-exp-1219
852
+ - gemini-2.0-pro-exp-02-05
853
+ - gemini-exp-1206
854
+ - gemini-exp-1206
855
+ - glm-4
856
+ - glm-4-air
857
+ - glm-4-air-0111
858
+ - glm-4-airx
859
+ - glm-4-flash
860
+ - glm-4-long
861
+ - glm-4-plus
862
+ - glm-4-plus-0111
863
+ - glm-zero-preview
864
+ - google/gemini-flash-1.5
865
+ - gpt-3.5-turbo
866
+ - gpt-4-turbo-preview
867
+ - gpt-4o
868
+ - gpt-4o-2024-08-06
869
+ - gpt-4o-2024-11-20
870
+ - gpt-4o-mini
871
+ - grok-2-1212
872
+ - grok-2-vision-1212
873
+ - grok-3
874
+ - grok-3-deepsearch
875
+ - grok-3-reasoner
876
+ - grok-beta
877
+ - huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
878
+ - huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated
879
+ - huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
880
+ - huihui-ai/Llama-3.3-70B-Instruct-abliterated
881
+ - inflatebot/MN-12B-Mag-Mell-R1
882
+ - inflection/inflection-3-pi
883
+ - inflection/inflection-3-productivity
884
+ - kimi-k1.5-preview
885
+ - kimi-latest
886
+ - learnlm-1.5-pro-experimental
887
+ - llama-3.3-70b
888
+ - meta-llama/llama-3.1-8b-instruct
889
+ - meta-llama/llama-3.2-3b-instruct
890
+ - meta-llama/llama-3.2-90b-vision-instruct
891
+ - microsoft/wizardlm-2-7b
892
+ - microsoft/wizardlm-2-8x22b
893
+ - minimax/minimax-01
894
+ - mistralai/Mistral-Nemo-Instruct-2407
895
+ - mistralai/mistral-7b-instruct
896
+ - mistralai/mistral-large
897
+ - mistralai/mistral-saba
898
+ - mistralai/mistral-tiny
899
+ - mlabonne/NeuralDaredevil-8B-abliterated
900
+ - model-selector
901
+ - nothingiisreal/L3.1-70B-Celeste-V0.1-BF16
902
+ - nousresearch/hermes-3-llama-3.1-405b
903
+ - nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
904
+ - o1
905
+ - o1-plus
906
+ - o1-preview
907
+ - o3-mini
908
+ - o3-mini-high
909
+ - o3-mini-low
910
+ - qwen-long
911
+ - qwen-max
912
+ - qwen-plus
913
+ - qwen-turbo
914
+ - qwen/qwen-2.5-72b-instruct
915
+ - r1-1776
916
+ - raifle/sorcererlm-8x22b
917
+ - recommended-model
918
+ - sonar
919
+ - sonar-deep-research
920
+ - sonar-pro
921
+ - sonar-reasoning
922
+ - sonar-reasoning-pro
923
+ - step-2-16k
924
+ - step-2-16k-exp
925
+ - step-2-mini
926
+ - undi95/remm-slerp-l2-13b
927
+ - yi-34b-chat-0205
928
+ - yi-34b-chat-200k
929
+ - yi-large
930
+ - yi-large-turbo
931
+ - yi-lightning
932
+ - yi-medium-200k
933
+ fetch: false
934
+ titleConvo: true
935
+ titleModel: "current_model"
936
+ modelDisplayLabel: "NanoGPT"
937
 
938
+ # NVIDIA
939
+ # https://build.nvidia.com/explore/discover
940
+ - name: "Nvidia"
941
+ apiKey: "${NVIDIA_API_KEY}"
942
+ baseURL: "https://integrate.api.nvidia.com/v1/"
943
+ models:
944
+ default:
945
+ - 01-ai/yi-large
946
+ - abacusai/dracarys-llama-3.1-70b-instruct
947
+ - adept/fuyu-8b
948
+ - ai21labs/jamba-1.5-large-instruct
949
+ - ai21labs/jamba-1.5-mini-instruct
950
+ - aisingapore/sea-lion-7b-instruct
951
+ - baai/bge-m3
952
+ - baichuan-inc/baichuan2-13b-chat
953
+ - bigcode/starcoder2-15b
954
+ - bigcode/starcoder2-7b
955
+ - databricks/dbrx-instruct
956
+ - deepseek-ai/deepseek-coder-6.7b-instruct
957
+ - deepseek-ai/deepseek-r1
958
+ - google/codegemma-1.1-7b
959
+ - google/codegemma-7b
960
+ - google/deplot
961
+ - google/gemma-2-27b-it
962
+ - google/gemma-2-2b-it
963
+ - google/gemma-2-9b-it
964
+ - google/gemma-2b
965
+ - google/gemma-7b
966
+ - google/paligemma
967
+ - google/recurrentgemma-2b
968
+ - google/shieldgemma-9b
969
+ - ibm/granite-3.0-3b-a800m-instruct
970
+ - ibm/granite-3.0-8b-instruct
971
+ - ibm/granite-34b-code-instruct
972
+ - ibm/granite-8b-code-instruct
973
+ - ibm/granite-guardian-3.0-8b
974
+ - igenius/colosseum_355b_instruct_16k
975
+ - igenius/italia_10b_instruct_16k
976
+ - institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1
977
+ - institute-of-science-tokyo/llama-3.1-swallow-8b-instruct-v0.1
978
+ - mediatek/breeze-7b-instruct
979
+ - meta/codellama-70b
980
+ - meta/llama-3.1-405b-instruct
981
+ - meta/llama-3.1-70b-instruct
982
+ - meta/llama-3.1-8b-instruct
983
+ - meta/llama-3.2-1b-instruct
984
+ - meta/llama-3.2-3b-instruct
985
+ - meta/llama-3.3-70b-instruct
986
+ - meta/llama2-70b
987
+ - meta/llama3-70b-instruct
988
+ - meta/llama3-8b-instruct
989
+ - microsoft/kosmos-2
990
+ - microsoft/phi-3-medium-128k-instruct
991
+ - microsoft/phi-3-medium-4k-instruct
992
+ - microsoft/phi-3-mini-128k-instruct
993
+ - microsoft/phi-3-mini-4k-instruct
994
+ - microsoft/phi-3-small-128k-instruct
995
+ - microsoft/phi-3-small-8k-instruct
996
+ - microsoft/phi-3-vision-128k-instruct
997
+ - microsoft/phi-3.5-mini-instruct
998
+ - microsoft/phi-3.5-moe-instruct
999
+ - microsoft/phi-3.5-vision-instruct
1000
+ - microsoft/phi-4-mini-instruct
1001
+ - mistralai/codestral-22b-instruct-v0.1
1002
+ - mistralai/mamba-codestral-7b-v0.1
1003
+ - mistralai/mathstral-7b-v0.1
1004
+ - mistralai/mistral-7b-instruct-v0.2
1005
+ - mistralai/mistral-7b-instruct-v0.3
1006
+ - mistralai/mistral-large
1007
+ - mistralai/mistral-large-2-instruct
1008
+ - mistralai/mistral-small-24b-instruct
1009
+ - mistralai/mixtral-8x22b-instruct-v0.1
1010
+ - mistralai/mixtral-8x22b-v0.1
1011
+ - mistralai/mixtral-8x7b-instruct-v0.1
1012
+ - nv-mistralai/mistral-nemo-12b-instruct
1013
+ - nvidia/embed-qa-4
1014
+ - nvidia/llama-3.1-nemoguard-8b-content-safety
1015
+ - nvidia/llama-3.1-nemoguard-8b-topic-control
1016
+ - nvidia/llama-3.1-nemotron-51b-instruct
1017
+ - nvidia/llama-3.1-nemotron-70b-instruct
1018
+ - nvidia/llama-3.1-nemotron-70b-reward
1019
+ - nvidia/llama-3.2-nv-embedqa-1b-v1
1020
+ - nvidia/llama-3.2-nv-embedqa-1b-v2
1021
+ - nvidia/llama3-chatqa-1.5-70b
1022
+ - nvidia/llama3-chatqa-1.5-8b
1023
+ - nvidia/mistral-nemo-minitron-8b-8k-instruct
1024
+ - nvidia/mistral-nemo-minitron-8b-base
1025
+ - nvidia/nemotron-4-340b-instruct
1026
+ - nvidia/nemotron-4-340b-reward
1027
+ - nvidia/nemotron-4-mini-hindi-4b-instruct
1028
+ - nvidia/nemotron-mini-4b-instruct
1029
+ - nvidia/neva-22b
1030
+ - nvidia/nv-embed-v1
1031
+ - nvidia/nv-embedqa-e5-v5
1032
+ - nvidia/nv-embedqa-mistral-7b-v2
1033
+ - nvidia/nvclip
1034
+ - nvidia/usdcode-llama-3.1-70b-instruct
1035
+ - nvidia/vila
1036
+ - qwen/qwen2-7b-instruct
1037
+ - qwen/qwen2.5-7b-instruct
1038
+ - qwen/qwen2.5-coder-32b-instruct
1039
+ - qwen/qwen2.5-coder-7b-instruct
1040
+ - rakuten/rakutenai-7b-chat
1041
+ - rakuten/rakutenai-7b-instruct
1042
+ - snowflake/arctic-embed-l
1043
+ - thudm/chatglm3-6b
1044
+ - tiiuae/falcon3-7b-instruct
1045
+ - tokyotech-llm/llama-3-swallow-70b-instruct-v0.1
1046
+ - upstage/solar-10.7b-instruct
1047
+ - writer/palmyra-creative-122b
1048
+ - writer/palmyra-fin-70b-32k
1049
+ - writer/palmyra-med-70b
1050
+ - writer/palmyra-med-70b-32k
1051
+ - yentinglin/llama-3-taiwan-70b-instruct
1052
+ - zyphra/zamba2-7b-instruct
1053
+ fetch: false
1054
+ titleConvo: true
1055
+ titleModel: "nvidia/nemotron-mini-4b-instruct"
1056
+ modelDisplayLabel: "Nvidia"
1057
+ iconURL: "https://raw.githubusercontent.com/LibreChat-AI/librechat-config-yaml/refs/heads/main/icons/nvidia.png"
1058
+
1059
+ # OpenRouter.ai
1060
+ # Model list: https://openrouter.ai/models
1061
+ # Script to fetch models: https://github.com/LibreChat-AI/librechat-config-yaml/blob/main/scripts/openrouter.py
1062
  - name: "OpenRouter"
 
 
 
1063
  apiKey: "${OPENROUTER_KEY}"
1064
  baseURL: "https://openrouter.ai/api/v1"
1065
  models:
1066
+ default:
1067
+ - openrouter/auto
1068
+ - '---FREE---'
1069
+ - cognitivecomputations/dolphin3.0-mistral-24b:free
1070
+ - cognitivecomputations/dolphin3.0-r1-mistral-24b:free
1071
+ - deepseek/deepseek-chat:free
1072
+ - deepseek/deepseek-r1-distill-llama-70b:free
1073
+ - deepseek/deepseek-r1:free
1074
+ - google/gemini-2.0-flash-exp:free
1075
+ - google/gemini-2.0-flash-lite-preview-02-05:free
1076
+ - google/gemini-2.0-flash-thinking-exp-1219:free
1077
+ - google/gemini-2.0-flash-thinking-exp:free
1078
+ - google/gemini-2.0-pro-exp-02-05:free
1079
+ - google/gemini-exp-1206:free
1080
+ - google/gemma-2-9b-it:free
1081
+ - google/learnlm-1.5-pro-experimental:free
1082
+ - gryphe/mythomax-l2-13b:free
1083
+ - huggingfaceh4/zephyr-7b-beta:free
1084
+ - meta-llama/llama-3-8b-instruct:free
1085
+ - meta-llama/llama-3.1-8b-instruct:free
1086
+ - meta-llama/llama-3.2-11b-vision-instruct:free
1087
+ - meta-llama/llama-3.2-1b-instruct:free
1088
+ - meta-llama/llama-3.3-70b-instruct:free
1089
+ - microsoft/phi-3-medium-128k-instruct:free
1090
+ - microsoft/phi-3-mini-128k-instruct:free
1091
+ - mistralai/mistral-7b-instruct:free
1092
+ - mistralai/mistral-nemo:free
1093
+ - mistralai/mistral-small-24b-instruct-2501:free
1094
+ - nvidia/llama-3.1-nemotron-70b-instruct:free
1095
+ - openchat/openchat-7b:free
1096
+ - qwen/qwen-vl-plus:free
1097
+ - qwen/qwen2.5-vl-72b-instruct:free
1098
+ - sophosympatheia/rogue-rose-103b-v0.2:free
1099
+ - undi95/toppy-m-7b:free
1100
+ - '---BETA---'
1101
+ - anthropic/claude-2.0:beta
1102
+ - anthropic/claude-2.1:beta
1103
+ - anthropic/claude-2:beta
1104
+ - anthropic/claude-3-haiku:beta
1105
+ - anthropic/claude-3-opus:beta
1106
+ - anthropic/claude-3-sonnet:beta
1107
+ - anthropic/claude-3.5-haiku-20241022:beta
1108
+ - anthropic/claude-3.5-haiku:beta
1109
+ - anthropic/claude-3.5-sonnet-20240620:beta
1110
+ - anthropic/claude-3.5-sonnet:beta
1111
+ - anthropic/claude-3.7-sonnet:beta
1112
+ - '---EXTENDED---'
1113
+ - neversleep/llama-3-lumimaid-8b:extended
1114
+ - openai/gpt-4o:extended
1115
+ - '---AI21---'
1116
+ - ai21/jamba-1-5-large
1117
+ - ai21/jamba-1-5-mini
1118
+ - ai21/jamba-instruct
1119
+ - '---AION-LABS---'
1120
+ - aion-labs/aion-1.0
1121
+ - aion-labs/aion-1.0-mini
1122
+ - aion-labs/aion-rp-llama-3.1-8b
1123
+ - '---AMAZON---'
1124
+ - amazon/nova-lite-v1
1125
+ - amazon/nova-micro-v1
1126
+ - amazon/nova-pro-v1
1127
+ - '---ANTHROPIC---'
1128
+ - anthropic/claude-2
1129
+ - anthropic/claude-2.0
1130
+ - anthropic/claude-2.1
1131
+ - anthropic/claude-3-7-sonnet
1132
+ - anthropic/claude-3-haiku
1133
+ - anthropic/claude-3-opus
1134
+ - anthropic/claude-3-sonnet
1135
+ - anthropic/claude-3.5-haiku
1136
+ - anthropic/claude-3.5-haiku-20241022
1137
+ - anthropic/claude-3.5-sonnet
1138
+ - anthropic/claude-3.5-sonnet-20240620
1139
+ - anthropic/claude-3.7-sonnet
1140
+ - anthropic/claude-3.7-sonnet:thinking
1141
+ - '---COHERE---'
1142
+ - cohere/command
1143
+ - cohere/command-r
1144
+ - cohere/command-r-03-2024
1145
+ - cohere/command-r-08-2024
1146
+ - cohere/command-r-plus
1147
+ - cohere/command-r-plus-04-2024
1148
+ - cohere/command-r-plus-08-2024
1149
+ - cohere/command-r7b-12-2024
1150
+ - '---DEEPSEEK---'
1151
+ - deepseek/deepseek-chat
1152
+ - deepseek/deepseek-chat-v2.5
1153
+ - deepseek/deepseek-r1
1154
+ - deepseek/deepseek-r1-distill-llama-70b
1155
+ - deepseek/deepseek-r1-distill-llama-8b
1156
+ - deepseek/deepseek-r1-distill-qwen-1.5b
1157
+ - deepseek/deepseek-r1-distill-qwen-14b
1158
+ - deepseek/deepseek-r1-distill-qwen-32b
1159
+ - '---EVA-UNIT-01---'
1160
+ - eva-unit-01/eva-llama-3.33-70b
1161
+ - eva-unit-01/eva-qwen-2.5-32b
1162
+ - eva-unit-01/eva-qwen-2.5-72b
1163
+ - '---GOOGLE---'
1164
+ - google/gemini-2.0-flash-001
1165
+ - google/gemini-2.0-flash-lite-001
1166
+ - google/gemini-flash-1.5
1167
+ - google/gemini-flash-1.5-8b
1168
+ - google/gemini-flash-1.5-8b-exp
1169
+ - google/gemini-pro
1170
+ - google/gemini-pro-1.5
1171
+ - google/gemini-pro-vision
1172
+ - google/gemma-2-27b-it
1173
+ - google/gemma-2-9b-it
1174
+ - google/gemma-7b-it
1175
+ - google/palm-2-chat-bison
1176
+ - google/palm-2-chat-bison-32k
1177
+ - google/palm-2-codechat-bison
1178
+ - google/palm-2-codechat-bison-32k
1179
+ - '---LIQUID---'
1180
+ - liquid/lfm-3b
1181
+ - liquid/lfm-40b
1182
+ - liquid/lfm-7b
1183
+ - '---META-LLAMA---'
1184
+ - meta-llama/llama-2-13b-chat
1185
+ - meta-llama/llama-2-70b-chat
1186
+ - meta-llama/llama-3-70b-instruct
1187
+ - meta-llama/llama-3-8b-instruct
1188
+ - meta-llama/llama-3.1-405b
1189
+ - meta-llama/llama-3.1-405b-instruct
1190
+ - meta-llama/llama-3.1-70b-instruct
1191
+ - meta-llama/llama-3.1-8b-instruct
1192
+ - meta-llama/llama-3.2-11b-vision-instruct
1193
+ - meta-llama/llama-3.2-1b-instruct
1194
+ - meta-llama/llama-3.2-3b-instruct
1195
+ - meta-llama/llama-3.2-90b-vision-instruct
1196
+ - meta-llama/llama-3.3-70b-instruct
1197
+ - meta-llama/llama-guard-2-8b
1198
+ - meta-llama/llama-guard-3-8b
1199
+ - '---MICROSOFT---'
1200
+ - microsoft/phi-3-medium-128k-instruct
1201
+ - microsoft/phi-3-mini-128k-instruct
1202
+ - microsoft/phi-3.5-mini-128k-instruct
1203
+ - microsoft/phi-4
1204
+ - microsoft/wizardlm-2-7b
1205
+ - microsoft/wizardlm-2-8x22b
1206
+ - '---MISTRALAI---'
1207
+ - mistralai/codestral-2501
1208
+ - mistralai/codestral-mamba
1209
+ - mistralai/ministral-3b
1210
+ - mistralai/ministral-8b
1211
+ - mistralai/mistral-7b-instruct
1212
+ - mistralai/mistral-7b-instruct-v0.1
1213
+ - mistralai/mistral-7b-instruct-v0.3
1214
+ - mistralai/mistral-large
1215
+ - mistralai/mistral-large-2407
1216
+ - mistralai/mistral-large-2411
1217
+ - mistralai/mistral-medium
1218
+ - mistralai/mistral-nemo
1219
+ - mistralai/mistral-saba
1220
+ - mistralai/mistral-small
1221
+ - mistralai/mistral-small-24b-instruct-2501
1222
+ - mistralai/mistral-tiny
1223
+ - mistralai/mixtral-8x22b-instruct
1224
+ - mistralai/mixtral-8x7b
1225
+ - mistralai/mixtral-8x7b-instruct
1226
+ - mistralai/pixtral-12b
1227
+ - mistralai/pixtral-large-2411
1228
+ - '---NEVERSLEEP---'
1229
+ - neversleep/llama-3-lumimaid-70b
1230
+ - neversleep/llama-3-lumimaid-8b
1231
+ - neversleep/llama-3.1-lumimaid-70b
1232
+ - neversleep/llama-3.1-lumimaid-8b
1233
+ - neversleep/noromaid-20b
1234
+ - '---NOUSRESEARCH---'
1235
+ - nousresearch/hermes-2-pro-llama-3-8b
1236
+ - nousresearch/hermes-3-llama-3.1-405b
1237
+ - nousresearch/hermes-3-llama-3.1-70b
1238
+ - nousresearch/nous-hermes-2-mixtral-8x7b-dpo
1239
+ - nousresearch/nous-hermes-llama2-13b
1240
+ - '---OPENAI---'
1241
+ - openai/chatgpt-4o-latest
1242
+ - openai/gpt-3.5-turbo
1243
+ - openai/gpt-3.5-turbo-0125
1244
+ - openai/gpt-3.5-turbo-0613
1245
+ - openai/gpt-3.5-turbo-1106
1246
+ - openai/gpt-3.5-turbo-16k
1247
+ - openai/gpt-3.5-turbo-instruct
1248
+ - openai/gpt-4
1249
+ - openai/gpt-4-0314
1250
+ - openai/gpt-4-1106-preview
1251
+ - openai/gpt-4-32k
1252
+ - openai/gpt-4-32k-0314
1253
+ - openai/gpt-4-turbo
1254
+ - openai/gpt-4-turbo-preview
1255
+ - openai/gpt-4o
1256
+ - openai/gpt-4o-2024-05-13
1257
+ - openai/gpt-4o-2024-08-06
1258
+ - openai/gpt-4o-2024-11-20
1259
+ - openai/gpt-4o-mini
1260
+ - openai/gpt-4o-mini-2024-07-18
1261
+ - openai/o1
1262
+ - openai/o1-mini
1263
+ - openai/o1-mini-2024-09-12
1264
+ - openai/o1-preview
1265
+ - openai/o1-preview-2024-09-12
1266
+ - openai/o3-mini
1267
+ - openai/o3-mini-high
1268
+ - '---PERPLEXITY---'
1269
+ - perplexity/llama-3.1-sonar-huge-128k-online
1270
+ - perplexity/llama-3.1-sonar-large-128k-chat
1271
+ - perplexity/llama-3.1-sonar-large-128k-online
1272
+ - perplexity/llama-3.1-sonar-small-128k-chat
1273
+ - perplexity/llama-3.1-sonar-small-128k-online
1274
+ - perplexity/r1-1776
1275
+ - perplexity/sonar
1276
+ - perplexity/sonar-reasoning
1277
+ - '---QWEN---'
1278
+ - qwen/qvq-72b-preview
1279
+ - qwen/qwen-2-72b-instruct
1280
+ - qwen/qwen-2-vl-72b-instruct
1281
+ - qwen/qwen-2-vl-7b-instruct
1282
+ - qwen/qwen-2.5-72b-instruct
1283
+ - qwen/qwen-2.5-7b-instruct
1284
+ - qwen/qwen-2.5-coder-32b-instruct
1285
+ - qwen/qwen-max
1286
+ - qwen/qwen-plus
1287
+ - qwen/qwen-turbo
1288
+ - qwen/qwq-32b-preview
1289
+ - '---SAO10K---'
1290
+ - sao10k/fimbulvetr-11b-v2
1291
+ - sao10k/l3-euryale-70b
1292
+ - sao10k/l3-lunaris-8b
1293
+ - sao10k/l3.1-70b-hanami-x1
1294
+ - sao10k/l3.1-euryale-70b
1295
+ - sao10k/l3.3-euryale-70b
1296
+ - '---X-AI---'
1297
+ - x-ai/grok-2-1212
1298
+ - x-ai/grok-2-vision-1212
1299
+ - x-ai/grok-beta
1300
+ - x-ai/grok-vision-beta
1301
+ - '---OTHERS---'
1302
+ - 01-ai/yi-large
1303
+ - aetherwiing/mn-starcannon-12b
1304
+ - allenai/llama-3.1-tulu-3-405b
1305
+ - alpindale/goliath-120b
1306
+ - alpindale/magnum-72b
1307
+ - anthracite-org/magnum-v2-72b
1308
+ - anthracite-org/magnum-v4-72b
1309
+ - cognitivecomputations/dolphin-mixtral-8x22b
1310
+ - cognitivecomputations/dolphin-mixtral-8x7b
1311
+ - databricks/dbrx-instruct
1312
+ - gryphe/mythomax-l2-13b
1313
+ - infermatic/mn-inferor-12b
1314
+ - inflatebot/mn-mag-mell-r1
1315
+ - inflection/inflection-3-pi
1316
+ - inflection/inflection-3-productivity
1317
+ - jondurbin/airoboros-l2-70b
1318
+ - mancer/weaver
1319
+ - minimax/minimax-01
1320
+ - nothingiisreal/mn-celeste-12b
1321
+ - nvidia/llama-3.1-nemotron-70b-instruct
1322
+ - openchat/openchat-7b
1323
+ - pygmalionai/mythalion-13b
1324
+ - raifle/sorcererlm-8x22b
1325
+ - sophosympatheia/midnight-rose-70b
1326
+ - teknium/openhermes-2.5-mistral-7b
1327
+ - thedrummer/rocinante-12b
1328
+ - thedrummer/unslopnemo-12b
1329
+ - undi95/remm-slerp-l2-13b
1330
+ - undi95/toppy-m-7b
1331
+ - xwin-lm/xwin-lm-70b
1332
+ fetch: false
1333
+ dropParams:
1334
+ - "stop"
1335
  titleConvo: true
1336
+ titleModel: "openai/gpt-4o-mini"
1337
  summarize: false
1338
+ summaryModel: "openai/gpt-4o-mini"
1339
  forcePrompt: false
1340
  modelDisplayLabel: "OpenRouter"
1341
 
1342
+ # Preplexity
1343
+ # Model list: https://docs.perplexity.ai/docs/model-cards
1344
+ - name: "Perplexity"
1345
+ apiKey: "${PERPLEXITY_API_KEY}"
1346
+ baseURL: "https://api.perplexity.ai/"
 
1347
  models:
1348
+ default:
1349
+ - r1-1776
1350
+ - sonar
1351
+ - sonar-deep-research
1352
+ - sonar-pro
1353
+ - sonar-reasoning
1354
+ - sonar-reasoning-pro
1355
+ fetch: false # fetching list of models is not supported
1356
  titleConvo: true
1357
+ titleModel: "llama-3.1-sonar-small-128k-chat"
1358
  summarize: false
1359
+ summaryModel: "llama-3.1-sonar-small-128k-chat"
1360
  forcePrompt: false
1361
+ dropParams:
1362
+ - "stop"
1363
+ - "frequency_penalty"
1364
+ modelDisplayLabel: "Perplexity"
1365
 
1366
+ # SambaNova
1367
+ # https://cloud.sambanova.ai/apis
1368
+ - name: "SambaNova"
1369
+ iconURL: "https://sambanova.ai/hubfs/logotype_sambanova_orange.png"
1370
+ apiKey: "${SAMBANOVA_API_KEY}"
1371
+ baseURL: "https://api.sambanova.ai/v1/"
1372
+ models:
1373
+ default:
1374
+ - DeepSeek-R1
1375
+ - DeepSeek-R1-Distill-Llama-70B
1376
+ - Llama-3.1-Tulu-3-405B
1377
+ - Llama-3.2-11B-Vision-Instruct
1378
+ - Llama-3.2-90B-Vision-Instruct
1379
+ - Meta-Llama-3.1-405B-Instruct
1380
+ - Meta-Llama-3.1-70B-Instruct
1381
+ - Meta-Llama-3.1-8B-Instruct
1382
+ - Meta-Llama-3.2-1B-Instruct
1383
+ - Meta-Llama-3.2-3B-Instruct
1384
+ - Meta-Llama-3.3-70B-Instruct
1385
+ - Meta-Llama-Guard-3-8B
1386
+ - QwQ-32B-Preview
1387
+ - Qwen2-Audio-7B-Instruct
1388
+ - Qwen2.5-72B-Instruct
1389
+ - Qwen2.5-Coder-32B-Instruct
1390
+ fetch: false
1391
+ titleConvo: true
1392
+ titleModel: "Meta-Llama-3.1-8B-Instruct"
1393
+ modelDisplayLabel: "SambaNova"
1394
+
1395
+ # together.ai
1396
+ # https://api.together.ai/settings/api-keys
1397
+ # Model list: https://docs.together.ai/docs/inference-models
1398
+ - name: "together.ai"
1399
+ apiKey: "${TOGETHERAI_API_KEY}"
1400
+ baseURL: "https://api.together.xyz"
1401
+ models:
1402
+ default:
1403
+ - Gryphe/MythoMax-L2-13b
1404
+ - Gryphe/MythoMax-L2-13b-Lite
1405
+ - NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
1406
+ - Qwen/QwQ-32B-Preview
1407
+ - Qwen/Qwen2-72B-Instruct
1408
+ - Qwen/Qwen2-VL-72B-Instruct
1409
+ - Qwen/Qwen2.5-72B-Instruct-Turbo
1410
+ - Qwen/Qwen2.5-7B-Instruct-Turbo
1411
+ - Qwen/Qwen2.5-Coder-32B-Instruct
1412
+ - databricks/dbrx-instruct
1413
+ - deepseek-ai/DeepSeek-R1
1414
+ - deepseek-ai/DeepSeek-R1-Distill-Llama-70B
1415
+ - deepseek-ai/DeepSeek-R1-Distill-Llama-70B-free
1416
+ - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
1417
+ - deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
1418
+ - deepseek-ai/DeepSeek-V3
1419
+ - google/gemma-2-27b-it
1420
+ - google/gemma-2-9b-it
1421
+ - google/gemma-2b-it
1422
+ - meta-llama/Llama-2-13b-chat-hf
1423
+ - meta-llama/Llama-2-7b-chat-hf
1424
+ - meta-llama/Llama-3-70b-chat-hf
1425
+ - meta-llama/Llama-3-8b-chat-hf
1426
+ - meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
1427
+ - meta-llama/Llama-3.2-3B-Instruct-Turbo
1428
+ - meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
1429
+ - meta-llama/Llama-3.3-70B-Instruct-Turbo
1430
+ - meta-llama/Llama-3.3-70B-Instruct-Turbo-Free
1431
+ - meta-llama/Llama-Vision-Free
1432
+ - meta-llama/Meta-Llama-3-70B-Instruct-Lite
1433
+ - meta-llama/Meta-Llama-3-70B-Instruct-Turbo
1434
+ - meta-llama/Meta-Llama-3-8B-Instruct-Lite
1435
+ - meta-llama/Meta-Llama-3-8B-Instruct-Turbo
1436
+ - meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
1437
+ - meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
1438
+ - meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
1439
+ - meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo-128K
1440
+ - meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo-classifier
1441
+ - microsoft/WizardLM-2-8x22B
1442
+ - mistralai/Mistral-7B-Instruct-v0.1
1443
+ - mistralai/Mistral-7B-Instruct-v0.2
1444
+ - mistralai/Mistral-7B-Instruct-v0.3
1445
+ - mistralai/Mistral-Small-24B-Instruct-2501
1446
+ - mistralai/Mixtral-8x22B-Instruct-v0.1
1447
+ - mistralai/Mixtral-8x7B-Instruct-v0.1
1448
+ - nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
1449
+ - scb10x/scb10x-llama3-1-typhoon2-60256
1450
+ - scb10x/scb10x-llama3-typhoon-v1-5-8b-instruct
1451
+ - scb10x/scb10x-llama3-typhoon-v1-5x-4f316
1452
+ - togethercomputer/MoA-1
1453
+ - togethercomputer/MoA-1-Turbo
1454
+ - upstage/SOLAR-10.7B-Instruct-v1.0
1455
+ fetch: false
1456
+ titleConvo: true
1457
+ titleModel: "togethercomputer/llama-2-7b-chat"
1458
+ summarize: false
1459
+ summaryModel: "togethercomputer/llama-2-7b-chat"
1460
+ forcePrompt: false
1461
+ modelDisplayLabel: "together.ai"
1462
+
1463
+ # Unify
1464
+ # Model list: https://unify.ai/chat
1465
+ - name: "Unify"
1466
+ apiKey: "${UNIFY_API_KEY}"
1467
+ baseURL: "https://api.unify.ai/v0/"
1468
+ models:
1469
+ default:
1470
+ - chatgpt-4o-latest@openai
1471
+ - claude-3-haiku@anthropic
1472
+ - claude-3-haiku@aws-bedrock
1473
+ - claude-3-haiku@vertex-ai
1474
+ - claude-3-opus@anthropic
1475
+ - claude-3-opus@aws-bedrock
1476
+ - claude-3-opus@vertex-ai
1477
+ - claude-3-sonnet@anthropic
1478
+ - claude-3-sonnet@aws-bedrock
1479
+ - claude-3.5-haiku@anthropic
1480
+ - claude-3.5-haiku@aws-bedrock
1481
+ - claude-3.5-haiku@replicate
1482
+ - claude-3.5-haiku@vertex-ai
1483
+ - claude-3.5-sonnet-20240620@anthropic
1484
+ - claude-3.5-sonnet-20240620@aws-bedrock
1485
+ - claude-3.5-sonnet-20240620@vertex-ai
1486
+ - claude-3.5-sonnet@anthropic
1487
+ - claude-3.5-sonnet@aws-bedrock
1488
+ - claude-3.5-sonnet@replicate
1489
+ - claude-3.5-sonnet@vertex-ai
1490
+ - claude-3.7-sonnet@anthropic
1491
+ - claude-3.7-sonnet@aws-bedrock
1492
+ - claude-3.7-sonnet@vertex-ai
1493
+ - command-r-plus@aws-bedrock
1494
+ - deepseek-r1@deepinfra
1495
+ - deepseek-r1@deepseek
1496
+ - deepseek-r1@fireworks-ai
1497
+ - deepseek-r1@replicate
1498
+ - deepseek-r1@together-ai
1499
+ - deepseek-v3@deepinfra
1500
+ - deepseek-v3@deepseek
1501
+ - deepseek-v3@fireworks-ai
1502
+ - deepseek-v3@together-ai
1503
+ - gemini-1.0-pro-001@vertex-ai
1504
+ - gemini-1.0-pro-002@vertex-ai
1505
+ - gemini-1.0-pro@vertex-ai
1506
+ - gemini-1.5-flash-001@vertex-ai
1507
+ - gemini-1.5-flash-002@vertex-ai
1508
+ - gemini-1.5-flash@vertex-ai
1509
+ - gemini-1.5-pro-001@vertex-ai
1510
+ - gemini-1.5-pro-002@vertex-ai
1511
+ - gemini-1.5-pro@vertex-ai
1512
+ - gemini-2.0-flash-lite@vertex-ai
1513
+ - gemini-2.0-flash@vertex-ai
1514
+ - gemma-2-27b-it@deepinfra
1515
+ - gemma-2-27b-it@together-ai
1516
+ - gemma-2-9b-it@deepinfra
1517
+ - gemma-2-9b-it@groq
1518
+ - gemma-2-9b-it@lepton-ai
1519
+ - gemma-2-9b-it@together-ai
1520
+ - gpt-3.5-turbo@openai
1521
+ - gpt-4-turbo@openai
1522
+ - gpt-4@openai
1523
+ - gpt-4o-2024-05-13@openai
1524
+ - gpt-4o-2024-08-06@openai
1525
+ - gpt-4o-2024-11-20@openai
1526
+ - gpt-4o-mini@openai
1527
+ - gpt-4o@openai
1528
+ - grok-2-vision@xai
1529
+ - grok-2@xai
1530
+ - llama-3-70b-chat@aws-bedrock
1531
+ - llama-3-70b-chat@deepinfra
1532
+ - llama-3-70b-chat@fireworks-ai
1533
+ - llama-3-70b-chat@groq
1534
+ - llama-3-70b-chat@replicate
1535
+ - llama-3-70b-chat@together-ai
1536
+ - llama-3-8b-chat@aws-bedrock
1537
+ - llama-3-8b-chat@deepinfra
1538
+ - llama-3-8b-chat@fireworks-ai
1539
+ - llama-3-8b-chat@groq
1540
+ - llama-3-8b-chat@replicate
1541
+ - llama-3-8b-chat@together-ai
1542
+ - llama-3.1-405b-chat@aws-bedrock
1543
+ - llama-3.1-405b-chat@deepinfra
1544
+ - llama-3.1-405b-chat@fireworks-ai
1545
+ - llama-3.1-405b-chat@replicate
1546
+ - llama-3.1-405b-chat@together-ai
1547
+ - llama-3.1-405b-chat@vertex-ai
1548
+ - llama-3.1-70b-chat@aws-bedrock
1549
+ - llama-3.1-70b-chat@deepinfra
1550
+ - llama-3.1-70b-chat@fireworks-ai
1551
+ - llama-3.1-70b-chat@together-ai
1552
+ - llama-3.1-70b-chat@vertex-ai
1553
+ - llama-3.1-8b-chat@aws-bedrock
1554
+ - llama-3.1-8b-chat@deepinfra
1555
+ - llama-3.1-8b-chat@fireworks-ai
1556
+ - llama-3.1-8b-chat@groq
1557
+ - llama-3.1-8b-chat@lepton-ai
1558
+ - llama-3.1-8b-chat@together-ai
1559
+ - llama-3.1-8b-chat@vertex-ai
1560
+ - llama-3.1-nemotron-70b-chat@deepinfra
1561
+ - llama-3.2-11b-chat@deepinfra
1562
+ - llama-3.2-11b-chat@fireworks-ai
1563
+ - llama-3.2-11b-chat@groq
1564
+ - llama-3.2-11b-chat@together-ai
1565
+ - llama-3.2-11b-chat@vertex-ai
1566
+ - llama-3.2-1b-chat@aws-bedrock
1567
+ - llama-3.2-1b-chat@deepinfra
1568
+ - llama-3.2-1b-chat@groq
1569
+ - llama-3.2-1b-chat@lepton-ai
1570
+ - llama-3.2-3b-chat@aws-bedrock
1571
+ - llama-3.2-3b-chat@deepinfra
1572
+ - llama-3.2-3b-chat@fireworks-ai
1573
+ - llama-3.2-3b-chat@groq
1574
+ - llama-3.2-3b-chat@lepton-ai
1575
+ - llama-3.2-3b-chat@together-ai
1576
+ - llama-3.2-90b-chat@deepinfra
1577
+ - llama-3.2-90b-chat@fireworks-ai
1578
+ - llama-3.2-90b-chat@groq
1579
+ - llama-3.2-90b-chat@together-ai
1580
+ - llama-3.2-90b-chat@vertex-ai
1581
+ - llama-3.3-70b-chat@aws-bedrock
1582
+ - llama-3.3-70b-chat@deepinfra
1583
+ - llama-3.3-70b-chat@fireworks-ai
1584
+ - llama-3.3-70b-chat@groq
1585
+ - llama-3.3-70b-chat@lepton-ai
1586
+ - llama-3.3-70b-chat@together-ai
1587
+ - ministral-3b@mistral-ai
1588
+ - ministral-8b@mistral-ai
1589
+ - mistral-7b-instruct-v0.2@aws-bedrock
1590
+ - mistral-7b-instruct-v0.3@deepinfra
1591
+ - mistral-7b-instruct-v0.3@lepton-ai
1592
+ - mistral-7b-instruct-v0.3@mistral-ai
1593
+ - mistral-7b-instruct-v0.3@together-ai
1594
+ - mistral-large@aws-bedrock
1595
+ - mistral-large@mistral-ai
1596
+ - mistral-large@vertex-ai
1597
+ - mistral-nemo@deepinfra
1598
+ - mistral-nemo@lepton-ai
1599
+ - mistral-nemo@mistral-ai
1600
+ - mistral-nemo@vertex-ai
1601
+ - mistral-small@deepinfra
1602
+ - mistral-small@fireworks-ai
1603
+ - mistral-small@mistral-ai
1604
+ - mistral-small@together-ai
1605
+ - mixtral-8x22b-instruct-v0.1@fireworks-ai
1606
+ - mixtral-8x22b-instruct-v0.1@mistral-ai
1607
+ - mixtral-8x22b-instruct-v0.1@together-ai
1608
+ - mixtral-8x7b-instruct-v0.1@aws-bedrock
1609
+ - mixtral-8x7b-instruct-v0.1@deepinfra
1610
+ - mixtral-8x7b-instruct-v0.1@fireworks-ai
1611
+ - mixtral-8x7b-instruct-v0.1@groq
1612
+ - mixtral-8x7b-instruct-v0.1@lepton-ai
1613
+ - mixtral-8x7b-instruct-v0.1@mistral-ai
1614
+ - mixtral-8x7b-instruct-v0.1@together-ai
1615
+ - o1-mini@openai
1616
+ - o1@openai
1617
+ - o3-mini@openai
1618
+ - qwen-2-72b-instruct@together-ai
1619
+ - qwen-2.5-72b-instruct@deepinfra
1620
+ - qwen-2.5-72b-instruct@fireworks-ai
1621
+ - qwen-2.5-72b-instruct@together-ai
1622
+ - qwen-2.5-7b-instruct@deepinfra
1623
+ - qwen-2.5-7b-instruct@together-ai
1624
+ - qwen-2.5-coder-32b-instruct@deepinfra
1625
+ - qwen-2.5-coder-32b-instruct@fireworks-ai
1626
+ - qwen-2.5-coder-32b-instruct@groq
1627
+ - qwen-2.5-coder-32b-instruct@together-ai
1628
+ - qwen-qwq-32b-preview@fireworks-ai
1629
+ - qwen-qwq-32b-preview@together-ai
1630
+ fetch: false
1631
+ titleConvo: true
1632
+ titleModel: "gpt-4o-mini@openai"
1633
+ dropParams:
1634
+ - "stop"
1635
+ - "user"
1636
+ - "frequency_penalty"
1637
+ - "presence_penalty"
1638
+
1639
+ # xAI
1640
+ # https://x.ai/api
1641
+ - name: "xai"
1642
+ apiKey: "${XAI_API_KEY}"
1643
+ baseURL: "https://api.x.ai/v1"
1644
+ models:
1645
+ default:
1646
+ - "grok-beta"
1647
+ fetch: false
1648
+ titleConvo: true
1649
+ titleMethod: "completion"
1650
+ titleModel: "grok-beta"
1651
+ summarize: false
1652
+ summaryModel: "grok-beta"
1653
+ forcePrompt: false
1654
+ modelDisplayLabel: "Grok"