LibreChat / librechat.yaml
dastratman's picture
Update librechat.yaml
ae55b22 verified
Raw
History Blame Contribute Delete
75.9 kB
version: 1.2.4
cache: true
registration:
socialLogins:
- "discord"
- "facebook"
- "github"
- "google"
- "openid"
endpoints:
custom:
# APIpie
# https://apipie.ai/dashboard/
# Script to fetch models: https://github.com/LibreChat-AI/librechat-config-yaml/blob/main/scripts/apipie.py
- name: "APIpie"
apiKey: "${APIPIE_API_KEY}"
baseURL: "https://apipie.ai/v1/"
models:
default:
- DeepSeek-Prover-V2-671B
- DeepSeek-R1
- DeepSeek-R1-Distill-Llama-70B
- DeepSeek-R1-Distill-Llama-70B-free
- DeepSeek-R1-Distill-Qwen-1.5B
- DeepSeek-R1-Distill-Qwen-14B
- DeepSeek-R1-Distill-Qwen-32B
- DeepSeek-R1-Turbo
- DeepSeek-V3
- DeepSeek-V3-0324
- DeepSeek-V3-p-dp
- Hermes-3-Llama-3.1-405B
- L3-70B-Euryale-v2.1
- L3-8B-Lunaris-v1
- L3-8B-Lunaris-v1-Turbo
- L3.1-70B-Euryale-v2.2
- L3.3-70B-Euryale-v2.3
- LLaMA2-13B-Tiefighter
- Llama-2-13b-chat-hf
- Llama-2-70b-chat-hf
- Llama-2-70b-hf
- Llama-3-70b-chat-hf
- Llama-3-8b-chat-hf
- Llama-3.1-Nemotron-70B-Instruct
- Llama-3.1-Nemotron-70B-Instruct-HF
- Llama-3.2-11B-Vision-Instruct
- Llama-3.2-11B-Vision-Instruct-Turbo
- Llama-3.2-1B-Instruct
- Llama-3.2-3B-Instruct
- Llama-3.2-3B-Instruct-Turbo
- Llama-3.2-90B-Vision-Instruct
- Llama-3.2-90B-Vision-Instruct-Turbo
- Llama-3.3-70B-Instruct
- Llama-3.3-70B-Instruct-Turbo
- Llama-3.3-70B-Instruct-Turbo-Free
- Llama-4-Maverick-17B-128E-Instruct-FP8
- Llama-4-Maverick-17B-128E-Instruct-Turbo
- Llama-4-Scout-17B-16E-Instruct
- Llama-Guard-3-8B
- Llama-Guard-4-12B
- Llama-Vision-Free
- Meta-Llama-3-70B-Instruct
- Meta-Llama-3-70B-Instruct-Turbo
- Meta-Llama-3-8B-Instruct
- Meta-Llama-3-8B-Instruct-Lite
- Meta-Llama-3.1-405B-Instruct
- Meta-Llama-3.1-405B-Instruct-Turbo
- Meta-Llama-3.1-70B-Instruct
- Meta-Llama-3.1-70B-Instruct-Turbo
- Meta-Llama-3.1-8B-Instruct
- Meta-Llama-3.1-8B-Instruct-Turbo
- MiniCPM-Llama3-V-2_5
- Mistral-7B-Instruct-v0.1
- Mistral-7B-Instruct-v0.2
- Mistral-7B-Instruct-v0.3
- Mistral-Nemo-Instruct-2407
- Mistral-Small-24B-Instruct-2501
- Mixtral-8x22B-Instruct-v0.1
- Mixtral-8x7B-Instruct-v0.1
- MoA-1
- MoA-1-Turbo
- MythoMax-L2-13b
- MythoMax-L2-13b-Lite
- MythoMax-L2-13b-turbo
- Nemotron-4-340B-Instruct
- Nous-Hermes-2-Mixtral-8x7B-DPO
- Phi-3-medium-4k-instruct
- Phi-4-multimodal-instruct
- Phind-CodeLlama-34B-v2
- QVQ-72B-Preview
- QwQ-32B
- QwQ-32B-Preview
- Qwen2-72B-Instruct
- Qwen2-7B-Instruct
- Qwen2-VL-72B-Instruct
- Qwen2.5-72B-Instruct
- Qwen2.5-72B-Instruct-Turbo
- Qwen2.5-7B-Instruct
- Qwen2.5-7B-Instruct-Turbo
- Qwen2.5-Coder-32B-Instruct
- Qwen2.5-Coder-7B
- Qwen2.5-VL-72B-Instruct
- Qwen3-14B
- Qwen3-235B-A22B
- Qwen3-235B-A22B-fp8
- Qwen3-235B-A22B-fp8-tput
- Qwen3-30B-A3B
- Qwen3-32B
- Reflection-Llama-3.1-70B
- Refuel-Llm-V2
- Refuel-Llm-V2-Small
- Sky-T1-32B-Preview
- Wan2.1-T2V-1.3B
- WizardLM-2-7B
- WizardLM-2-8x22B
- aion-1.0
- aion-1.0-mini
- aion-rp-llama-3.1-8b
- airoboros-70b
- amazon.nova-lite-v1
- amazon.nova-lite-v1:0
- amazon.nova-micro-v1:0
- amazon.nova-pro-v1:0
- anubis-pro-105b-v1
- arcee-blitz
- babbage-002
- caller-large
- chatgpt-4o-latest
- chatx
- chatx-fast
- chatx_cheap_128k
- chatx_cheap_32k
- chatx_cheap_4k
- chatx_cheap_64k
- chatx_cheap_8k
- chatx_mids_4k
- chatx_premium_128k
- chatx_premium_32k
- chatx_premium_4k
- chatx_premium_8k
- chronos-hermes-13b-v2
- claude-2
- claude-2.0
- claude-2.1
- claude-3-5-haiku
- claude-3-5-haiku-20241022
- claude-3-5-haiku-20241022-v1
- claude-3-5-haiku-latest
- claude-3-5-sonnet
- claude-3-5-sonnet-20240620
- claude-3-5-sonnet-20240620-v1
- claude-3-5-sonnet-20241022
- claude-3-5-sonnet-20241022-v2
- claude-3-5-sonnet-latest
- claude-3-7-sonnet-20250219
- claude-3-7-sonnet-20250219-v1
- claude-3-7-sonnet-latest
- claude-3-haiku
- claude-3-haiku-20240307
- claude-3-haiku-20240307-v1
- claude-3-opus
- claude-3-opus-20240229
- claude-3-opus-20240229-v1
- claude-3-opus-latest
- claude-3-sonnet
- claude-3-sonnet-20240229
- claude-3-sonnet-20240229-v1
- claude-3.5-haiku
- claude-3.5-haiku-20241022
- claude-3.7-sonnet
- claude-instant-v1
- claude-opus-4
- claude-opus-4-20250514
- claude-opus-4-20250514-v1
- claude-sonnet-4
- claude-sonnet-4-20250514
- claude-sonnet-4-20250514-v1
- claude-v2
- codegemma-7b-it
- codellama-7b-instruct-solidity
- coder-large
- codestral-2405
- codestral-2501
- codestral-latest
- codestral-mamba
- codestral-mamba-latest
- codex-mini
- codex-mini-latest
- command
- command-a
- command-light
- command-light-nightly
- command-light-text-v14
- command-nightly
- command-r
- command-r-03-2024
- command-r-08-2024
- command-r-plus
- command-r-plus-04-2024
- command-r-plus-08-2024
- command-r-plus-v1
- command-r-v1
- command-r7b-12-2024
- command-text-v14
- computer-use-preview
- computer-use-preview-2025-03-11
- davinci-002
- deepcoder-14b-preview
- deephermes-3-llama-3-8b-preview
- deephermes-3-mistral-24b-preview
- deepseek-chat
- deepseek-chat-v3-0324
- deepseek-coder
- deepseek-prover-v2
- deepseek-r1
- deepseek-r1-distill-llama-70b
- deepseek-r1-distill-llama-8b
- deepseek-r1-distill-qwen-1.5b
- deepseek-r1-distill-qwen-14b
- deepseek-r1-distill-qwen-32b
- deepseek-r1-zero
- deepseek-r1t-chimera
- deepseek-reasoner
- deepseek-v3-base
- devstral-small
- dolphin-2.6-mixtral-8x7b
- dolphin-2.9.1-llama-3-70b
- dolphin-mixtral-8x22b
- dolphin3.0-mistral-24b
- dolphin3.0-r1-mistral-24b
- eu.amazon.nova-lite-v1:0
- eva-llama-3.33-70b
- eva-qwen-2.5-32b
- eva-qwen-2.5-72b
- fimbulvetr-11b-v2
- gemini-1.5-flash
- gemini-1.5-flash-8b
- gemini-1.5-flash-8b-latest
- gemini-1.5-flash-latest
- gemini-1.5-pro
- gemini-1.5-pro-latest
- gemini-2.0-flash
- gemini-2.0-flash-001
- gemini-2.0-flash-exp
- gemini-2.0-flash-lite
- gemini-2.0-flash-lite-001
- gemini-2.0-flash-lite-preview-02-05
- gemini-2.5-flash
- gemini-2.5-flash-preview
- gemini-2.5-flash-preview-04-17
- gemini-2.5-flash-preview-05-20
- gemini-2.5-pro
- gemini-2.5-pro-exp-03-25
- gemini-2.5-pro-preview
- gemini-2.5-pro-preview-03-25
- gemini-2.5-pro-preview-05-06
- gemini-flash-1.5
- gemini-flash-1.5-8b
- gemini-flash-1.5-8b-exp
- gemini-pro
- gemini-pro-1.5
- gemini-pro-vision
- gemma-1.1-7b-it
- gemma-2
- gemma-2-27b-it
- gemma-2-9b-it
- gemma-2b-it
- gemma-3
- gemma-3-12b-it
- gemma-3-1b-it
- gemma-3-27b-it
- gemma-3-4b-it
- gemma2-9b-it
- glm-4-32b
- glm-4-9b
- glm-z1-32b
- glm-z1-9b
- glm-z1-rumination-32b
- goliath-120b
- gpt-3.5-turbo
- gpt-3.5-turbo-0125
- gpt-3.5-turbo-0613
- gpt-3.5-turbo-1106
- gpt-3.5-turbo-16k
- gpt-3.5-turbo-16k-0613
- gpt-3.5-turbo-instruct
- gpt-3.5-turbo-instruct-0914
- gpt-35-turbo
- gpt-35-turbo-16k
- gpt-4
- gpt-4-0125-preview
- gpt-4-0314
- gpt-4-0613
- gpt-4-1106-preview
- gpt-4-1106-vision-preview
- gpt-4-32k
- gpt-4-32k-0314
- gpt-4-turbo
- gpt-4-turbo-2024-04-09
- gpt-4-turbo-preview
- gpt-4-vision-preview
- gpt-4.1
- gpt-4.1-2025-04-14
- gpt-4.1-mini
- gpt-4.1-mini-2025-04-14
- gpt-4.1-nano
- gpt-4.1-nano-2025-04-14
- gpt-4.5-preview
- gpt-4.5-preview-2025-02-27
- gpt-4o
- gpt-4o-2024-05-13
- gpt-4o-2024-08-06
- gpt-4o-2024-11-20
- gpt-4o-audio-preview
- gpt-4o-audio-preview-2024-10-01
- gpt-4o-audio-preview-2024-12-17
- gpt-4o-mini
- gpt-4o-mini-2024-07-18
- gpt-4o-mini-audio-preview
- gpt-4o-mini-audio-preview-2024-12-17
- gpt-4o-mini-realtime-preview
- gpt-4o-mini-realtime-preview-2024-12-17
- gpt-4o-mini-search-preview
- gpt-4o-mini-search-preview-2025-03-11
- gpt-4o-mini-transcribe
- gpt-4o-realtime-preview
- gpt-4o-realtime-preview-2024-10-01
- gpt-4o-realtime-preview-2024-12-17
- gpt-4o-search-preview
- gpt-4o-search-preview-2025-03-11
- gpt-4o-transcribe
- gpt-image-1
- grok-2
- grok-2-1212
- grok-2-latest
- grok-2-vision
- grok-2-vision-1212
- grok-2-vision-latest
- grok-3
- grok-3-beta
- grok-3-mini-beta
- grok-beta
- grok-vision-beta
- hermes-2-pro-llama-3-8b
- hermes-3-llama-3.1-405b
- hermes-3-llama-3.1-70b
- inflection-3-pi
- inflection-3-productivity
- internvl3-14b
- internvl3-2b
- j2-mid
- j2-ultra
- jamba-1-5-large-v1
- jamba-1-5-mini-v1
- jamba-1.6-large
- jamba-1.6-mini
- jamba-instruct
- jamba-instruct-v1
- kimi-vl-a3b-thinking
- l3-euryale-70b
- l3-lunaris-8b
- l3.1-euryale-70b
- l3.3-electra-r1-70b
- l3.3-euryale-70b
- large-latest
- learnlm-1.5-pro-experimental
- lfm-3b
- lfm-40b
- lfm-7b
- llama-2-70b-chat
- llama-3-2-large
- llama-3-2-small
- llama-3-70b-instruct
- llama-3-8b-instruct
- llama-3-lumimaid-70b
- llama-3-lumimaid-8b
- llama-3.1-405b
- llama-3.1-405b-instruct
- llama-3.1-70b-instruct
- llama-3.1-8b-instant
- llama-3.1-8b-instruct
- llama-3.1-lumimaid-70b
- llama-3.1-lumimaid-8b
- llama-3.1-nemotron-70b-instruct
- llama-3.1-nemotron-ultra-253b-v1
- llama-3.1-sonar-large-128k-online
- llama-3.1-sonar-small-128k-online
- llama-3.1-swallow-70b-instruct-v0.3
- llama-3.2-11b-vision-instruct
- llama-3.2-1b-instruct
- llama-3.2-3b-instruct
- llama-3.2-90b-vision-instruct
- llama-3.3-70b-instruct
- llama-3.3-70b-versatile
- llama-3.3-8b-instruct
- llama-3.3-nemotron-super-49b-v1
- llama-4-maverick
- llama-4-scout
- llama-guard-2-8b
- llama-guard-3-8b
- llama-guard-4-12b
- llama2-13b-chat-v1
- llama2-70b-chat-v1
- llama3-1-405b-instruct-v1
- llama3-1-405b-instruct-v1:0
- llama3-1-70b-instruct-v1
- llama3-1-70b-instruct-v1:0
- llama3-1-8b-instruct-v1
- llama3-2-11b-instruct-v1
- llama3-2-1b-instruct-v1
- llama3-2-3b-instruct-v1
- llama3-2-90b-instruct-v1
- llama3-3-70b-instruct-v1
- llama3-70b-8192
- llama3-70b-instruct-v1
- llama3-70b-instruct-v1:0
- llama3-8b-8192
- llama3-8b-instruct-v1
- llama3-8b-instruct-v1:0
- llama3.1-typhoon2-70b-instruct
- llama3.1-typhoon2-8b-instruct
- llama4-maverick-17b-instruct-v1
- llama4-scout-17b-instruct-v1
- llemma_7b
- lzlv_70b_fp16_hf
- maestro-reasoning
- magnum-72b
- magnum-v2-72b
- magnum-v4-72b
- mai-ds-r1
- medium
- mercury-coder-small-beta
- meta-llama-3.1-8b-instruct
- meta-llama-llama-2-70b-hf
- meta.llama3-1-405b-instruct-v1:0
- meta.llama3-1-70b-instruct-v1:0
- meta.llama3-1-8b-instruct-v1:0
- midnight-rose-70b
- minimax-01
- ministral-3b
- ministral-8b
- mistral-7b-instruct
- mistral-7b-instruct-v0
- mistral-7b-instruct-v0.1
- mistral-7b-instruct-v0.2
- mistral-7b-instruct-v0.3
- mistral-large
- mistral-large-2402
- mistral-large-2402-v1
- mistral-large-2407
- mistral-large-2411
- mistral-large-latest
- mistral-medium
- mistral-medium-2312
- mistral-medium-3
- mistral-medium-latest
- mistral-nemo
- mistral-saba
- mistral-saba-latest
- mistral-small
- mistral-small-2402-v1
- mistral-small-24b-instruct-2501
- mistral-small-3.1-24b-instruct
- mistral-small-latest
- mistral-tiny
- mixtral-8x22b-instruct
- mixtral-8x7b
- mixtral-8x7b-instruct
- mixtral-8x7b-instruct-v0
- mn-celeste-12b
- mn-inferor-12b
- mn-starcannon-12b
- molmo-7b-d
- moonlight-16b-a3b-instruct
- multimodal
- mythalion-13b
- mythomax
- mythomax-l2-13b
- noromaid-20b
- nous-hermes-2-mixtral-8x7b-dpo
- nous-hermes-2-vision-7b
- nova-canvas-v1
- nova-lite-v1
- nova-micro-v1
- nova-premier-v1
- nova-pro-v1
- nova-reel-v1
- nova-sonic-v1
- o1
- o1-2024-12-17
- o1-mini
- o1-mini-2024-09-12
- o1-preview
- o1-preview-2024-09-12
- o1-pro
- o1-pro-2025-03-19
- o3
- o3-2025-04-16
- o3-mini
- o3-mini-2025-01-31
- o3-mini-high
- o4-mini
- o4-mini-2025-04-16
- o4-mini-high
- olmo-7b-instruct
- olympiccoder-32b
- omni-moderation-2024-09-26
- omni-moderation-latest
- open-codestral-mamba
- open-mistral-7b
- open-mistral-nemo
- open-mistral-nemo-2407
- open-mixtral-8x22b
- open-mixtral-8x7b
- openchat-3.6-8b
- openchat_3.5
- openhands-lm-32b-v0.1
- palm-2-chat-bison
- palm-2-chat-bison-32k
- palm-2-codechat-bison
- palm-2-codechat-bison-32k
- phi-3-medium-128k-instruct
- phi-3-mini-128k-instruct
- phi-3.5-mini-128k-instruct
- phi-4
- phi-4-multimodal-instruct
- phi-4-reasoning
- phi-4-reasoning-plus
- pixtral-12b
- pixtral-large-2411
- pixtral-large-2502-v1
- pixtral-large-latest
- qvq-72b-preview
- qwen-2-5-large
- qwen-2-72b-instruct
- qwen-2-large
- qwen-2-small
- qwen-2-vl-7b-instruct
- qwen-2.5-72b-instruct
- qwen-2.5-7b-instruct
- qwen-2.5-coder-32b-instruct
- qwen-2.5-vl-72b-instruct
- qwen-2.5-vl-7b-instruct
- qwen-max
- qwen-plus
- qwen-turbo
- qwen-vl-max
- qwen-vl-plus
- qwen2.5-coder-7b-instruct
- qwen2.5-vl-32b-instruct
- qwen2.5-vl-3b-instruct
- qwen2.5-vl-72b-instruct
- qwen3-0.6b-04-28
- qwen3-1.7b
- qwen3-14b
- qwen3-235b-a22b
- qwen3-30b-a3b
- qwen3-32b
- qwen3-4b
- qwen3-8b
- qwerky-72b
- qwq-32b
- qwq-32b-arliai-rpr-v1
- qwq-32b-preview
- r1-1776
- r1-v1
- reka-flash-3
- remm-slerp-l2-13b
- rocinante-12b
- scb10x-llama3-1-typhoon2-70b-instruct
- scb10x-llama3-1-typhoon2-8b-instruct
- shisa-v2-llama3.3-70b
- skyfall-36b-v2
- small
- sonar
- sonar-deep-research
- sonar-pro
- sonar-reasoning
- sonar-reasoning-pro
- sorcererlm-8x22b
- spotlight
- starcoder2-15b-instruct-v0.1
- text-babbage-002
- text-davinci-002
- tiny
- titan-text-express-v1
- titan-text-lite-v1
- titan-text-premier-v1
- titan-tg1-large
- toppy-m-7b
- tts-1
- ui-tars-72b
- ultra-fast
- unslopnemo-12b
- valkyrie-49b-v1
- virtuoso-large
- virtuoso-medium-v2
- weaver
- wizardlm-2-8x22b
- yi-large
- yi-vision
- zephyr-7b-beta
fetch: false
titleConvo: true
titleModel: "claude-3-haiku"
summarize: false
summaryModel: "claude-3-haiku"
dropParams:
- "stream"
modelDisplayLabel: "APIpie"
iconURL: "https://raw.githubusercontent.com/fuegovic/lc-config-yaml/main/icons/APIpie.png"
# cohere
# Model list: https://dashboard.cohere.com/playground/chat
- name: "cohere"
apiKey: "${COHERE_API_KEY}"
baseURL: "https://api.cohere.ai/v1"
models:
default:
- c4ai-aya-expanse-32b
- c4ai-aya-vision-32b
- command
- command-a-03-2025
- command-light-nightly
- command-nightly
- command-r
- command-r-08-2024
- command-r-plus-08-2024
- command-r7b-12-2024
- command-r7b-arabic-02-2025
fetch: false
modelDisplayLabel: "cohere"
titleModel: "command"
dropParams:
- "stop"
- "user"
- "frequency_penalty"
- "presence_penalty"
- "temperature"
- "top_p"
# deepseek
# https://platform.deepseek.com/api_keys
# Model list: https://platform.deepseek.com/api-docs/pricing
- name: "deepseek"
apiKey: "${DEEPSEEK_API_KEY}"
baseURL: "https://api.deepseek.com"
models:
default:
- deepseek-chat
- deepseek-reasoner
fetch: false
titleConvo: true
titleModel: "deepseek-chat"
summarize: false
summaryModel: "deepseek-chat"
modelDisplayLabel: "DeepSeek"
# Fireworks.ai
# Models: https://fireworks.ai/models?show=Serverless
- name: "Fireworks"
apiKey: "${FIREWORKS_API_KEY}"
baseURL: "https://api.fireworks.ai/inference/v1"
models:
default:
- accounts/fireworks/models/deepseek-r1
- accounts/fireworks/models/deepseek-r1-basic
- accounts/fireworks/models/deepseek-v3
- accounts/fireworks/models/deepseek-v3-0324
- accounts/fireworks/models/firesearch-ocr-v6
- accounts/fireworks/models/llama-guard-3-8b
- accounts/fireworks/models/llama-v3p1-405b-instruct
- accounts/fireworks/models/llama-v3p1-405b-instruct-long
- accounts/fireworks/models/llama-v3p1-70b-instruct
- accounts/fireworks/models/llama-v3p1-8b-instruct
- accounts/fireworks/models/llama-v3p3-70b-instruct
- accounts/fireworks/models/llama4-maverick-instruct-basic
- accounts/fireworks/models/llama4-scout-instruct-basic
- accounts/fireworks/models/mixtral-8x22b-instruct
- accounts/fireworks/models/qwen2-vl-72b-instruct
- accounts/fireworks/models/qwen2p5-72b-instruct
- accounts/fireworks/models/qwen2p5-vl-32b-instruct
- accounts/fireworks/models/qwen3-235b-a22b
- accounts/fireworks/models/qwen3-30b-a3b
- accounts/fireworks/models/qwq-32b
- accounts/instacart/models/srl-finetune-0417-debug
- accounts/perplexity/models/r1-1776
- accounts/sentientfoundation/models/dobby-unhinged-llama-3-3-70b-new
fetch: false
titleConvo: true
titleModel: "accounts/fireworks/models/llama-v2-7b-chat"
summarize: false
summaryModel: "accounts/fireworks/models/llama-v2-7b-chat"
forcePrompt: false
modelDisplayLabel: "Fireworks"
dropParams:
- "user"
# GitHub
- name: "Github Models"
iconURL: https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png
apiKey: "${GITHUB_TOKEN}"
baseURL: "https://models.inference.ai.azure.com"
models:
default:
- AI21-Jamba-Instruct
- Cohere-command-r
- Cohere-command-r-plus
- Cohere-embed-v3-english
- Cohere-embed-v3-multilingual
- Meta-Llama-3-70B-Instruct
- Meta-Llama-3-8B-Instruct
- Meta-Llama-3.1-405B-Instruct
- Meta-Llama-3.1-70B-Instruct
- Meta-Llama-3.1-8B-Instruct
- Mistral-Nemo
- Mistral-large-2407
- Mistral-small
- Phi-3-medium-128k-instruct
- Phi-3-medium-4k-instruct
- Phi-3-mini-128k-instruct
- Phi-3-mini-4k-instruct
- Phi-3-small-128k-instruct
- Phi-3-small-8k-instruct
- Phi-3.5-mini-instruct
- gpt-4o
- gpt-4o-mini
- text-embedding-3-large
- text-embedding-3-small
fetch: false
titleConvo: true
titleModel: "gpt-4o-mini"
# groq
# Model list: https://console.groq.com/settings/limits
- name: "groq"
apiKey: "${GROQ_API_KEY}"
baseURL: "https://api.groq.com/openai/v1/"
models:
default:
- allam-2-7b
- compound-beta
- compound-beta-mini
- deepseek-r1-distill-llama-70b
- gemma2-9b-it
- llama-3.1-8b-instant
- llama-3.3-70b-versatile
- llama-guard-3-8b
- llama3-70b-8192
- llama3-8b-8192
- meta-llama/llama-4-maverick-17b-128e-instruct
- meta-llama/llama-4-scout-17b-16e-instruct
- meta-llama/llama-guard-4-12b
- mistral-saba-24b
- playai-tts
- playai-tts-arabic
- qwen-qwq-32b
fetch: false
titleConvo: true
titleModel: "mixtral-8x7b-32768"
modelDisplayLabel: "groq"
# HuggingFace
# https://huggingface.co/settings/tokens
- name: 'HuggingFace'
apiKey: '${HUGGINGFACE_TOKEN}'
baseURL: 'https://api-inference.huggingface.co/v1'
models:
default:
- AIDC-AI/Marco-o1
- CohereLabs/c4ai-command-r-plus
- CohereLabs/c4ai-command-r-v01
- HuggingFaceH4/zephyr-7b-alpha
- HuggingFaceH4/zephyr-7b-beta
- HuggingFaceTB/SmolLM2-1.7B-Instruct
- Intel/neural-chat-7b-v3-1
- MiniMaxAI/MiniMax-Text-01
- NexaAIDev/Octopus-v2
- Open-Orca/Mistral-7B-OpenOrca
- PygmalionAI/pygmalion-6b
- Qwen/QwQ-32B
- Qwen/QwQ-32B-Preview
- Qwen/Qwen2-72B-Instruct
- Qwen/Qwen2-7B-Instruct
- Qwen/Qwen2.5-72B-Instruct
- Qwen/Qwen2.5-7B-Instruct
- Qwen/Qwen2.5-Coder-32B-Instruct
- Qwen/Qwen3-235B-A22B
- Qwen/Qwen3-30B-A3B
- TinyLlama/TinyLlama-1.1B-Chat-v1.0
- agentica-org/DeepCoder-14B-Preview
- berkeley-nest/Starling-LM-7B-alpha
- cognitivecomputations/dolphin-2.5-mixtral-8x7b
- databricks/dbrx-base
- databricks/dbrx-instruct
- deepseek-ai/DeepSeek-Coder-V2-Instruct
- deepseek-ai/DeepSeek-Prover-V2-671B
- deepseek-ai/DeepSeek-R1
- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
- deepseek-ai/DeepSeek-R1-Zero
- deepseek-ai/DeepSeek-V2.5
- deepseek-ai/DeepSeek-V3
- deepseek-ai/DeepSeek-V3-0324
- google/gemma-2-2b-it
- google/gemma-2-9b-it
- google/gemma-2b-it
- google/gemma-7b-it
- gradientai/Llama-3-8B-Instruct-Gradient-1048k
- jinaai/ReaderLM-v2
- jinaai/reader-lm-1.5b
- manycore-research/SpatialLM-Llama-1B
- mattshumer/Reflection-Llama-3.1-70B
- meta-llama/Llama-2-13b-chat-hf
- meta-llama/Llama-2-70b-chat-hf
- meta-llama/Llama-2-7b-chat-hf
- meta-llama/Llama-3.1-405B-Instruct
- meta-llama/Llama-3.1-70B-Instruct
- meta-llama/Llama-3.1-8B-Instruct
- meta-llama/Llama-3.2-1B-Instruct
- meta-llama/Llama-3.2-3B-Instruct
- meta-llama/Llama-3.3-70B-Instruct
- meta-llama/Meta-Llama-3-70B-Instruct
- meta-llama/Meta-Llama-3-8B-Instruct
- microsoft/Phi-3-mini-128k-instruct
- microsoft/Phi-3-mini-4k-instruct
- microsoft/Phi-3-vision-128k-instruct
- microsoft/Phi-3.5-MoE-instruct
- microsoft/Phi-3.5-mini-instruct
- microsoft/bitnet-b1.58-2B-4T
- microsoft/phi-4
- mistralai/Codestral-22B-v0.1
- mistralai/Mistral-7B-Instruct-v0.1
- mistralai/Mistral-7B-Instruct-v0.2
- mistralai/Mistral-7B-Instruct-v0.3
- mistralai/Mistral-Nemo-Instruct-2407
- mistralai/Mistral-Small-24B-Instruct-2501
- mistralai/Mixtral-8x22B-Instruct-v0.1
- mistralai/Mixtral-8x7B-Instruct-v0.1
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
- nvidia/Llama3-ChatQA-1.5-8B
- openchat/openchat_3.5
- perplexity-ai/r1-1776
- shenzhi-wang/Llama3-8B-Chinese-Chat
- teknium/OpenHermes-2.5-Mistral-7B
- tiiuae/falcon-180B-chat
- tiiuae/falcon-7b-instruct
- unsloth/DeepSeek-R1-GGUF
- upstage/SOLAR-10.7B-Instruct-v1.0
fetch: false
titleConvo: true
titleModel: "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO"
dropParams:
- "top_p"
# Hyperbolic
# https://app.hyperbolic.xyz/models
- name: 'Hyperbolic'
apiKey: '${HYPERBOLIC_API_KEY}'
baseURL: 'https://api.hyperbolic.xyz/v1/'
models:
default:
- NousResearch/Hermes-3-Llama-3.1-70B
- Qwen/QwQ-32B
- Qwen/QwQ-32B-Preview
- Qwen/Qwen2.5-72B-Instruct
- Qwen/Qwen2.5-Coder-32B-Instruct
- SDXL1.0-base
- deepseek-ai/DeepSeek-R1
- deepseek-ai/DeepSeek-V3
- deepseek-ai/DeepSeek-V3-0324
- meta-llama/Llama-3.2-3B-Instruct
- meta-llama/Llama-3.3-70B-Instruct
- meta-llama/Meta-Llama-3-70B-Instruct
- meta-llama/Meta-Llama-3.1-405B
- meta-llama/Meta-Llama-3.1-405B-FP8
- meta-llama/Meta-Llama-3.1-405B-Instruct
- meta-llama/Meta-Llama-3.1-70B-Instruct
- meta-llama/Meta-Llama-3.1-8B-Instruct
fetch: false
titleConvo: true
titleModel: "meta-llama/Meta-Llama-3.1-8B-Instruct"
modelDisplayLabel: "Hyperbolic"
iconURL: "https://app.hyperbolic.xyz/icon.svg"
# kluster.ai
# https://platform.kluster.ai/apikeys
- name: "Kluster"
apiKey: "${KLUSTER_API_KEY}"
baseURL: "https://api.kluster.ai/v1/"
models:
default:
- Qwen/Qwen2.5-VL-7B-Instruct
- Qwen/Qwen3-235B-A22B-FP8
- deepseek-ai/DeepSeek-R1
- deepseek-ai/DeepSeek-V3-0324
- google/gemma-3-27b-it
- klusterai/Meta-Llama-3.1-8B-Instruct-Turbo
- klusterai/Meta-Llama-3.3-70B-Instruct-Turbo
- meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
- meta-llama/Llama-4-Scout-17B-16E-Instruct
- mistralai/Mistral-Nemo-Instruct-2407
fetch: false
titleConvo: true
titleModel: 'klusterai/Meta-Llama-3.1-8B-Instruct-Turbo'
modelDisplayLabel: 'Kluster'
iconURL: "https://platform.kluster.ai/cropped-fav-1-144x144.png"
# Mistral AI API
# Model list: https://docs.mistral.ai/getting-started/models/
- name: "Mistral"
apiKey: "${MISTRAL_API_KEY}"
baseURL: "https://api.mistral.ai/v1"
models:
default:
- codestral-2405
- codestral-2411-rc5
- codestral-2412
- codestral-2501
- codestral-latest
- codestral-mamba-2407
- codestral-mamba-latest
- devstral-small-2505
- devstral-small-latest
- ministral-3b-2410
- ministral-3b-latest
- ministral-8b-2410
- ministral-8b-latest
- mistral-embed
- mistral-large-2402
- mistral-large-2407
- mistral-large-2411
- mistral-large-latest
- mistral-large-pixtral-2411
- mistral-medium
- mistral-medium-2312
- mistral-medium-2505
- mistral-medium-latest
- mistral-moderation-2411
- mistral-moderation-latest
- mistral-ocr-2503
- mistral-ocr-2505
- mistral-ocr-latest
- mistral-saba-2502
- mistral-saba-latest
- mistral-small
- mistral-small-2312
- mistral-small-2402
- mistral-small-2409
- mistral-small-2501
- mistral-small-2503
- mistral-small-latest
- mistral-tiny
- mistral-tiny-2312
- mistral-tiny-2407
- mistral-tiny-latest
- open-codestral-mamba
- open-mistral-7b
- open-mistral-nemo
- open-mistral-nemo-2407
- open-mixtral-8x22b
- open-mixtral-8x22b-2404
- open-mixtral-8x7b
- pixtral-12b
- pixtral-12b-2409
- pixtral-12b-latest
- pixtral-large-2411
- pixtral-large-latest
fetch: false
titleConvo: true
titleMethod: "completion"
titleModel: "mistral-tiny"
summarize: false
summaryModel: "mistral-tiny"
forcePrompt: false
modelDisplayLabel: "Mistral"
dropParams:
- "stop"
- "user"
- "frequency_penalty"
- "presence_penalty"
# NanoGPT
# https://nano-gpt.com/api
# Model list: https://nano-gpt.com/api/models
- name: "NanoGPT"
iconURL: "https://nano-gpt.com/logo.png"
apiKey: "${NANOGPT_API_KEY}"
baseURL: "https://nano-gpt.com/api/v1/"
models:
default:
- EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0
- EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
- EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
- EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2
- Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B
- Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B
- GalrionSoftworks/MN-LooseCannon-12B-v1
- Gryphe/MythoMax-L2-13b
- Infermatic/MN-12B-Inferor-v0.0
- LatitudeGames/Wayfarer-Large-70B-Llama-3.3
- Llama-3.3+(3.1v3.3)-70B-Hanami-x1
- Llama-3.3+(3.1v3.3)-70B-WhiteRabbitNeo-2
- Llama-3.3+(3v3.3)-70B-TenyxChat-DaybreakStorywriter
- Llama-3.3+3.1-70B-ArliAI-RPMax-v1.3
- Llama-3.3-70B-Anubis-v1
- Llama-3.3-70B-ArliAI-RPMax-v1.4
- Llama-3.3-70B-Cu-Mai-R1
- Llama-3.3-70B-Electra-R1
- Llama-3.3-70B-Electranova-v1.0
- Llama-3.3-70B-Fallen-R1-v1
- Llama-3.3-70B-Legion-V2.1
- Llama-3.3-70B-Magnum-v4-SE
- Llama-3.3-70B-MiraiFanfare
- Llama-3.3-70B-Vulpecula-R1
- MarinaraSpaghetti/NemoMix-Unleashed-12B
- Meta-Llama-3-1-405B-Instruct-FP8
- Meta-Llama-3-1-8B-Instruct-FP8
- Mistral-Nemo-12B-ArliAI-RPMax-v1.1
- Mistral-Nemo-12B-ArliAI-RPMax-v1.2
- Mistral-Nemo-12B-ArliAI-RPMax-v1.3
- Mistral-Nemo-12B-Instruct-2407
- Mistral-Nemo-12B-NemoMix-Unleashed
- Mistral-Nemo-12B-SauerkrautLM
- Mistral-Nemo-12B-Wayfarer
- NeverSleep/Llama-3-Lumimaid-70B-v0.1
- NeverSleep/Lumimaid-v0.2-70B
- Nexusflow/Athene-V2-Chat
- NousResearch/DeepHermes-3-Mistral-24B-Preview
- QwQ-32B-ArliAI-RpR-v1
- QwQ-32B-ArliAI-RpR-v2
- QwQ-32B-ArliAI-RpR-v3
- QwQ-32B-Snowdrop-v0
- QwQ-32B-Snowdrop-v0-nothink
- Qwen/QwQ-32B-Preview
- Qwen/Qwen2.5-Coder-32B-Instruct
- Qwen/Qwen3-8B
- Qwen2.5-32B-Dazzling-Star-Aurora-32b-v0.0
- Qwen2.5-32B-EVA-v0.2
- Qwen2.5-72B-Instruct
- Qwen3-32B
- ReadyArt/The-Omega-Abomination-L-70B-v1.0
- ReadyArt/The-Omega-Abomination-L-70B-v5.0
- Salesforce/Llama-xLAM-2-70b-fc-r
- Sao10K/L3-8B-Stheno-v3.2
- Sao10K/L3.1-70B-Euryale-v2.2
- Sao10K/L3.1-70B-Hanami-x1
- Sao10K/L3.3-70B-Euryale-v2.3
- Steelskull/L3.3-Cu-Mai-R1-70b
- Steelskull/L3.3-Damascus-R1
- Steelskull/L3.3-Electra-R1-70b
- Steelskull/L3.3-MS-Evalebis-70b
- Steelskull/L3.3-MS-Evayale-70B
- Steelskull/L3.3-MS-Nevoria-70b
- Steelskull/L3.3-Nevoria-R1-70b
- TEE/deepseek-r1-70b
- TEE/hermes-3-llama-3.1-70b
- TEE/llama-3.3-70b-instruct
- TEE/qwen-2.5-7b-instruct
- THUDM/GLM-4-32B-0414
- THUDM/GLM-4-9B-0414
- THUDM/GLM-Z1-32B-0414
- THUDM/GLM-Z1-9B-0414
- THUDM/GLM-Z1-Rumination-32B-0414
- TheDrummer/Anubis-70B-v1
- TheDrummer/Cydonia-24B-v2
- TheDrummer/Rocinante-12B-v1.1
- TheDrummer/UnslopNemo-12B-v4.1
- VongolaChouko/Starcannon-Unleashed-12B-v1.0
- abacusai/Dracarys-72B-Instruct
- agentica-org/DeepCoder-14B-Preview
- aion-labs/aion-1.0
- aion-labs/aion-1.0-mini
- aion-labs/aion-rp-llama-3.1-8b
- amazon/nova-lite-v1
- amazon/nova-micro-v1
- amazon/nova-pro-v1
- anthracite-org/magnum-v2-72b
- anthracite-org/magnum-v4-72b
- anubis-pro-105b-v1
- asi1-mini
- azure-gpt-4-turbo
- azure-gpt-4o
- azure-gpt-4o-mini
- azure-o1
- azure-o3-mini
- chatgpt-4o-latest
- chatgpt-4o-latest-reasoner
- claude-3-5-haiku-20241022
- claude-3-5-sonnet-20240620
- claude-3-5-sonnet-20241022
- claude-3-7-sonnet-20250219
- claude-3-7-sonnet-reasoner
- claude-3-7-sonnet-thinking
- claude-3-7-sonnet-thinking:1024
- claude-3-7-sonnet-thinking:128000
- claude-3-7-sonnet-thinking:32768
- claude-3-7-sonnet-thinking:8192
- claude-3-opus-20240229
- claude-opus-4-20250514
- claude-opus-4-thinking
- claude-opus-4-thinking:1024
- claude-opus-4-thinking:128000
- claude-opus-4-thinking:32768
- claude-opus-4-thinking:8192
- claude-sonnet-4-20250514
- claude-sonnet-4-thinking
- claude-sonnet-4-thinking:1024
- claude-sonnet-4-thinking:128000
- claude-sonnet-4-thinking:32768
- claude-sonnet-4-thinking:8192
- cognitivecomputations/dolphin-mixtral-8x22b
- cohere/command-r
- cohere/command-r-plus-08-2024
- deepclaude
- deepcogito/cogito-v1-preview-qwen-32B
- deepseek-ai/DeepSeek-Prover-V2-671B
- deepseek-ai/DeepSeek-R1-Zero
- deepseek-chat
- deepseek-chat-cheaper
- deepseek-r1-llama-70b
- deepseek-r1-nano
- deepseek-r1-sambanova
- deepseek-reasoner
- deepseek-reasoner-cheaper
- deepseek-v3-0324
- dolphin-2.9.2-qwen2-72b
- doubao-1-5-thinking-pro-250415
- doubao-1-5-thinking-pro-vision-250415
- doubao-1-5-thinking-vision-pro-250428
- doubao-1.5-pro-256k
- doubao-1.5-pro-32k
- doubao-1.5-vision-pro-32k
- ernie-4.5-8k-preview
- ernie-4.5-turbo-128k
- ernie-4.5-turbo-vl-32k
- ernie-x1-32k
- ernie-x1-32k-preview
- ernie-x1-turbo-32k
- eva-unit-01/eva-qwen-2.5-72b
- failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5
- featherless-ai/Qwerky-72B
- free-model
- gemini-2.0-flash-001
- gemini-2.0-flash-exp-image-generation
- gemini-2.0-flash-exp-search
- gemini-2.0-flash-lite
- gemini-2.0-flash-thinking-exp-01-21
- gemini-2.0-flash-thinking-exp-1219
- gemini-2.0-pro-exp-02-05
- gemini-2.0-pro-reasoner
- gemini-2.5-flash-preview-04-17
- gemini-2.5-flash-preview-04-17:thinking
- gemini-2.5-flash-preview-05-20
- gemini-2.5-flash-preview-05-20:thinking
- gemini-2.5-pro-exp-03-25
- gemini-2.5-pro-preview-03-25
- gemini-2.5-pro-preview-05-06
- gemini-exp-1206
- gemini-exp-1206
- glm-4
- glm-4-air
- glm-4-air-0111
- glm-4-airx
- glm-4-flash
- glm-4-long
- glm-4-plus
- glm-4-plus-0111
- glm-z1-air
- glm-z1-airx
- glm-zero-preview
- google/gemini-flash-1.5
- gpt-3.5-turbo
- gpt-4-turbo-preview
- gpt-4.1-reasoner
- gpt-4.5-preview
- gpt-4.5-preview-2025-02-27
- gpt-4o
- gpt-4o-2024-08-06
- gpt-4o-2024-11-20
- gpt-4o-mini
- gpt-4o-mini-search-preview
- gpt-4o-reasoner
- gpt-4o-search-preview
- grok-3-beta
- grok-3-fast-beta
- grok-3-mini-beta
- grok-3-mini-fast-beta
- huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
- huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated
- huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
- huihui-ai/Llama-3.3-70B-Instruct-abliterated
- hunyuan-t1-latest
- hunyuan-turbos-20250226
- inflatebot/MN-12B-Mag-Mell-R1
- inflection/inflection-3-pi
- inflection/inflection-3-productivity
- jamba-large-1.6
- jamba-mini-1.6
- kimi-latest
- kimi-thinking-preview
- learnlm-1.5-pro-experimental
- mercury-coder-small
- meta-llama/llama-3.1-8b-instruct
- meta-llama/llama-3.2-3b-instruct
- meta-llama/llama-3.2-90b-vision-instruct
- meta-llama/llama-3.3-70b-instruct
- meta-llama/llama-4-maverick
- meta-llama/llama-4-scout
- microsoft/MAI-DS-R1-FP8
- microsoft/Phi-4-reasoning
- microsoft/Phi-4-reasoning-plus
- microsoft/wizardlm-2-8x22b
- minimax/minimax-01
- mistral-small-31-24b-instruct
- mistralai/Devstral-Small-2505
- mistralai/Mistral-Nemo-Instruct-2407
- mistralai/mistral-7b-instruct
- mistralai/mistral-large
- mistralai/mistral-medium-3
- mistralai/mistral-saba
- mistralai/mistral-tiny
- mlabonne/NeuralDaredevil-8B-abliterated
- moonshotai/Kimi-VL-A3B-Thinking
- nothingiisreal/L3.1-70B-Celeste-V0.1-BF16
- nousresearch/hermes-3-llama-3.1-405b
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
- nvidia/Llama-3.1-Nemotron-Ultra-253B-v1
- nvidia/Llama-3.3-Nemotron-Super-49B-v1
- o1
- o1-mini
- o1-preview
- o3
- o3-mini
- o3-mini-high
- o3-mini-low
- o4-mini
- o4-mini-high
- open-r1/OlympicCoder-32B
- open-r1/OlympicCoder-7b
- openai/gpt-4.1
- openai/gpt-4.1-mini
- openai/gpt-4.1-nano
- openai/o1-pro
- phi-4-mini-instruct
- phi-4-multimodal-instruct
- qvq-max
- qwen-long
- qwen-max
- qwen-plus
- qwen-turbo
- qwen/qwen-2.5-72b-instruct
- qwen/qwen3-14b
- qwen/qwen3-235b-a22b
- qwen/qwen3-30b-a3b
- qwen/qwen3-32b
- qwen25-vl-72b-instruct
- qwq-32b
- r1-1776
- raifle/sorcererlm-8x22b
- sarvan-medium
- shisa-ai/shisa-v2-llama3.3-70b
- sonar
- sonar-deep-research
- sonar-pro
- sonar-reasoning
- sonar-reasoning-pro
- soob3123/GrayLine-Qwen3-8B
- soob3123/Veiled-Calla-12B
- soob3123/amoral-gemma3-27B-v2
- step-2-16k-exp
- step-2-mini
- step-r1-v-mini
- thedrummer/skyfall-36b-v2
- tngtech/DeepSeek-R1T-Chimera
- undi95/remm-slerp-l2-13b
- unsloth/gemma-3-12b-it
- unsloth/gemma-3-1b-it
- unsloth/gemma-3-27b-it
- unsloth/gemma-3-4b-it
- yi-34b-chat-0205
- yi-34b-chat-200k
- yi-large
- yi-lightning
- yi-medium-200k
fetch: false
titleConvo: true
titleModel: "current_model"
modelDisplayLabel: "NanoGPT"
# NVIDIA
# https://build.nvidia.com/explore/discover
- name: "Nvidia"
apiKey: "${NVIDIA_API_KEY}"
baseURL: "https://integrate.api.nvidia.com/v1/"
models:
default:
- 01-ai/yi-large
- abacusai/dracarys-llama-3.1-70b-instruct
- adept/fuyu-8b
- ai21labs/jamba-1.5-large-instruct
- ai21labs/jamba-1.5-mini-instruct
- aisingapore/sea-lion-7b-instruct
- baai/bge-m3
- baichuan-inc/baichuan2-13b-chat
- bigcode/starcoder2-15b
- bigcode/starcoder2-7b
- databricks/dbrx-instruct
- deepseek-ai/deepseek-coder-6.7b-instruct
- deepseek-ai/deepseek-r1
- deepseek-ai/deepseek-r1-distill-llama-8b
- deepseek-ai/deepseek-r1-distill-qwen-14b
- deepseek-ai/deepseek-r1-distill-qwen-32b
- deepseek-ai/deepseek-r1-distill-qwen-7b
- google/codegemma-1.1-7b
- google/codegemma-7b
- google/deplot
- google/gemma-2-27b-it
- google/gemma-2-2b-it
- google/gemma-2-9b-it
- google/gemma-2b
- google/gemma-3-12b-it
- google/gemma-3-1b-it
- google/gemma-3-27b-it
- google/gemma-3-4b-it
- google/gemma-7b
- google/paligemma
- google/recurrentgemma-2b
- google/shieldgemma-9b
- gotocompany/gemma-2-9b-cpt-sahabatai-instruct
- ibm/granite-3.0-3b-a800m-instruct
- ibm/granite-3.0-8b-instruct
- ibm/granite-3.3-8b-instruct
- ibm/granite-34b-code-instruct
- ibm/granite-8b-code-instruct
- ibm/granite-guardian-3.0-8b
- igenius/colosseum_355b_instruct_16k
- igenius/italia_10b_instruct_16k
- institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1
- institute-of-science-tokyo/llama-3.1-swallow-8b-instruct-v0.1
- marin/marin-8b-instruct
- mediatek/breeze-7b-instruct
- meta/codellama-70b
- meta/llama-3.1-405b-instruct
- meta/llama-3.1-70b-instruct
- meta/llama-3.1-8b-instruct
- meta/llama-3.2-11b-vision-instruct
- meta/llama-3.2-1b-instruct
- meta/llama-3.2-3b-instruct
- meta/llama-3.2-90b-vision-instruct
- meta/llama-3.3-70b-instruct
- meta/llama-4-maverick-17b-128e-instruct
- meta/llama-4-scout-17b-16e-instruct
- meta/llama2-70b
- meta/llama3-70b-instruct
- meta/llama3-8b-instruct
- microsoft/kosmos-2
- microsoft/phi-3-medium-128k-instruct
- microsoft/phi-3-medium-4k-instruct
- microsoft/phi-3-mini-128k-instruct
- microsoft/phi-3-mini-4k-instruct
- microsoft/phi-3-small-128k-instruct
- microsoft/phi-3-small-8k-instruct
- microsoft/phi-3-vision-128k-instruct
- microsoft/phi-3.5-mini-instruct
- microsoft/phi-3.5-moe-instruct
- microsoft/phi-3.5-vision-instruct
- microsoft/phi-4-mini-instruct
- microsoft/phi-4-multimodal-instruct
- mistralai/codestral-22b-instruct-v0.1
- mistralai/mamba-codestral-7b-v0.1
- mistralai/mathstral-7b-v0.1
- mistralai/mistral-7b-instruct-v0.2
- mistralai/mistral-7b-instruct-v0.3
- mistralai/mistral-large
- mistralai/mistral-large-2-instruct
- mistralai/mistral-medium-3-instruct
- mistralai/mistral-small-24b-instruct
- mistralai/mistral-small-3.1-24b-instruct-2503
- mistralai/mixtral-8x22b-instruct-v0.1
- mistralai/mixtral-8x22b-v0.1
- mistralai/mixtral-8x7b-instruct-v0.1
- nv-mistralai/mistral-nemo-12b-instruct
- nvidia/embed-qa-4
- nvidia/llama-3.1-nemoguard-8b-content-safety
- nvidia/llama-3.1-nemoguard-8b-topic-control
- nvidia/llama-3.1-nemotron-51b-instruct
- nvidia/llama-3.1-nemotron-70b-instruct
- nvidia/llama-3.1-nemotron-70b-reward
- nvidia/llama-3.1-nemotron-nano-8b-v1
- nvidia/llama-3.1-nemotron-ultra-253b-v1
- nvidia/llama-3.2-nv-embedqa-1b-v1
- nvidia/llama-3.2-nv-embedqa-1b-v2
- nvidia/llama-3.3-nemotron-super-49b-v1
- nvidia/llama3-chatqa-1.5-70b
- nvidia/llama3-chatqa-1.5-8b
- nvidia/mistral-nemo-minitron-8b-8k-instruct
- nvidia/mistral-nemo-minitron-8b-base
- nvidia/nemoretriever-parse
- nvidia/nemotron-4-340b-instruct
- nvidia/nemotron-4-340b-reward
- nvidia/nemotron-4-mini-hindi-4b-instruct
- nvidia/nemotron-mini-4b-instruct
- nvidia/neva-22b
- nvidia/nv-embed-v1
- nvidia/nv-embedcode-7b-v1
- nvidia/nv-embedqa-e5-v5
- nvidia/nv-embedqa-mistral-7b-v2
- nvidia/nvclip
- nvidia/usdcode-llama-3.1-70b-instruct
- nvidia/vila
- nvquery/meta/llama-3.3-70b-instruct
- qwen/qwen2-7b-instruct
- qwen/qwen2.5-7b-instruct
- qwen/qwen2.5-coder-32b-instruct
- qwen/qwen2.5-coder-7b-instruct
- qwen/qwen3-235b-a22b
- qwen/qwq-32b
- rakuten/rakutenai-7b-chat
- rakuten/rakutenai-7b-instruct
- snowflake/arctic-embed-l
- thudm/chatglm3-6b
- tiiuae/falcon3-7b-instruct
- tokyotech-llm/llama-3-swallow-70b-instruct-v0.1
- upstage/solar-10.7b-instruct
- utter-project/eurollm-9b-instruct
- writer/palmyra-creative-122b
- writer/palmyra-fin-70b-32k
- writer/palmyra-med-70b
- writer/palmyra-med-70b-32k
- yentinglin/llama-3-taiwan-70b-instruct
- zyphra/zamba2-7b-instruct
fetch: false
titleConvo: true
titleModel: "nvidia/nemotron-mini-4b-instruct"
modelDisplayLabel: "Nvidia"
iconURL: "https://raw.githubusercontent.com/LibreChat-AI/librechat-config-yaml/refs/heads/main/icons/nvidia.png"
# OpenRouter.ai
# Model list: https://openrouter.ai/models
# Script to fetch models: https://github.com/LibreChat-AI/librechat-config-yaml/blob/main/scripts/openrouter.py
- name: "OpenRouter"
apiKey: "${OPENROUTER_KEY}"
baseURL: "https://openrouter.ai/api/v1"
models:
default:
- openrouter/auto
- '---FREE---'
- agentica-org/deepcoder-14b-preview:free
- arliai/qwq-32b-arliai-rpr-v1:free
- cognitivecomputations/dolphin3.0-mistral-24b:free
- cognitivecomputations/dolphin3.0-r1-mistral-24b:free
- deepseek/deepseek-chat-v3-0324:free
- deepseek/deepseek-chat:free
- deepseek/deepseek-prover-v2:free
- deepseek/deepseek-r1-distill-llama-70b:free
- deepseek/deepseek-r1-distill-qwen-14b:free
- deepseek/deepseek-r1-distill-qwen-32b:free
- deepseek/deepseek-r1-zero:free
- deepseek/deepseek-r1:free
- deepseek/deepseek-v3-base:free
- featherless/qwerky-72b:free
- google/gemini-2.0-flash-exp:free
- google/gemma-2-9b-it:free
- google/gemma-3-12b-it:free
- google/gemma-3-1b-it:free
- google/gemma-3-27b-it:free
- google/gemma-3-4b-it:free
- google/gemma-3n-e4b-it:free
- meta-llama/llama-3.1-405b:free
- meta-llama/llama-3.1-8b-instruct:free
- meta-llama/llama-3.2-11b-vision-instruct:free
- meta-llama/llama-3.2-1b-instruct:free
- meta-llama/llama-3.2-3b-instruct:free
- meta-llama/llama-3.3-70b-instruct:free
- meta-llama/llama-3.3-8b-instruct:free
- meta-llama/llama-4-maverick:free
- meta-llama/llama-4-scout:free
- microsoft/mai-ds-r1:free
- microsoft/phi-4-reasoning-plus:free
- microsoft/phi-4-reasoning:free
- mistralai/devstral-small:free
- mistralai/mistral-7b-instruct:free
- mistralai/mistral-nemo:free
- mistralai/mistral-small-24b-instruct-2501:free
- mistralai/mistral-small-3.1-24b-instruct:free
- moonshotai/kimi-vl-a3b-thinking:free
- moonshotai/moonlight-16b-a3b-instruct:free
- nousresearch/deephermes-3-llama-3-8b-preview:free
- nousresearch/deephermes-3-mistral-24b-preview:free
- nvidia/llama-3.1-nemotron-ultra-253b-v1:free
- nvidia/llama-3.3-nemotron-super-49b-v1:free
- open-r1/olympiccoder-32b:free
- opengvlab/internvl3-14b:free
- opengvlab/internvl3-2b:free
- qwen/qwen-2.5-72b-instruct:free
- qwen/qwen-2.5-7b-instruct:free
- qwen/qwen-2.5-coder-32b-instruct:free
- qwen/qwen-2.5-vl-7b-instruct:free
- qwen/qwen2.5-vl-32b-instruct:free
- qwen/qwen2.5-vl-3b-instruct:free
- qwen/qwen2.5-vl-72b-instruct:free
- qwen/qwen3-14b:free
- qwen/qwen3-235b-a22b:free
- qwen/qwen3-30b-a3b:free
- qwen/qwen3-32b:free
- qwen/qwen3-8b:free
- qwen/qwq-32b:free
- rekaai/reka-flash-3:free
- shisa-ai/shisa-v2-llama3.3-70b:free
- thudm/glm-4-32b:free
- thudm/glm-z1-32b:free
- tngtech/deepseek-r1t-chimera:free
- '---BETA---'
- anthropic/claude-2.0:beta
- anthropic/claude-2.1:beta
- anthropic/claude-2:beta
- anthropic/claude-3-haiku:beta
- anthropic/claude-3-opus:beta
- anthropic/claude-3-sonnet:beta
- anthropic/claude-3.5-haiku-20241022:beta
- anthropic/claude-3.5-haiku:beta
- anthropic/claude-3.5-sonnet-20240620:beta
- anthropic/claude-3.5-sonnet:beta
- anthropic/claude-3.7-sonnet:beta
- '---EXTENDED---'
- neversleep/llama-3-lumimaid-8b:extended
- openai/gpt-4o:extended
- '---AION-LABS---'
- aion-labs/aion-1.0
- aion-labs/aion-1.0-mini
- aion-labs/aion-rp-llama-3.1-8b
- '---AMAZON---'
- amazon/nova-lite-v1
- amazon/nova-micro-v1
- amazon/nova-pro-v1
- '---ANTHROPIC---'
- anthropic/claude-2
- anthropic/claude-2.0
- anthropic/claude-2.1
- anthropic/claude-3-haiku
- anthropic/claude-3-opus
- anthropic/claude-3-sonnet
- anthropic/claude-3.5-haiku
- anthropic/claude-3.5-haiku-20241022
- anthropic/claude-3.5-sonnet
- anthropic/claude-3.5-sonnet-20240620
- anthropic/claude-3.7-sonnet
- anthropic/claude-3.7-sonnet:thinking
- anthropic/claude-opus-4
- anthropic/claude-sonnet-4
- '---ARCEE-AI---'
- arcee-ai/arcee-blitz
- arcee-ai/caller-large
- arcee-ai/coder-large
- arcee-ai/maestro-reasoning
- arcee-ai/spotlight
- arcee-ai/virtuoso-large
- arcee-ai/virtuoso-medium-v2
- '---COHERE---'
- cohere/command
- cohere/command-a
- cohere/command-r
- cohere/command-r-03-2024
- cohere/command-r-08-2024
- cohere/command-r-plus
- cohere/command-r-plus-04-2024
- cohere/command-r-plus-08-2024
- cohere/command-r7b-12-2024
- '---DEEPSEEK---'
- deepseek/deepseek-chat
- deepseek/deepseek-chat-v3-0324
- deepseek/deepseek-coder
- deepseek/deepseek-prover-v2
- deepseek/deepseek-r1
- deepseek/deepseek-r1-distill-llama-70b
- deepseek/deepseek-r1-distill-llama-8b
- deepseek/deepseek-r1-distill-qwen-1.5b
- deepseek/deepseek-r1-distill-qwen-14b
- deepseek/deepseek-r1-distill-qwen-32b
- '---EVA-UNIT-01---'
- eva-unit-01/eva-llama-3.33-70b
- eva-unit-01/eva-qwen-2.5-32b
- eva-unit-01/eva-qwen-2.5-72b
- '---GOOGLE---'
- google/gemini-2.0-flash-001
- google/gemini-2.0-flash-lite-001
- google/gemini-2.5-flash-preview
- google/gemini-2.5-flash-preview-05-20
- google/gemini-2.5-flash-preview-05-20:thinking
- google/gemini-2.5-flash-preview:thinking
- google/gemini-2.5-pro-exp-03-25
- google/gemini-2.5-pro-preview
- google/gemini-flash-1.5
- google/gemini-flash-1.5-8b
- google/gemini-pro-1.5
- google/gemma-2-27b-it
- google/gemma-2-9b-it
- google/gemma-3-12b-it
- google/gemma-3-27b-it
- google/gemma-3-4b-it
- '---LIQUID---'
- liquid/lfm-3b
- liquid/lfm-40b
- liquid/lfm-7b
- '---META-LLAMA---'
- meta-llama/llama-2-70b-chat
- meta-llama/llama-3-70b-instruct
- meta-llama/llama-3-8b-instruct
- meta-llama/llama-3.1-405b
- meta-llama/llama-3.1-405b-instruct
- meta-llama/llama-3.1-70b-instruct
- meta-llama/llama-3.1-8b-instruct
- meta-llama/llama-3.2-11b-vision-instruct
- meta-llama/llama-3.2-1b-instruct
- meta-llama/llama-3.2-3b-instruct
- meta-llama/llama-3.2-90b-vision-instruct
- meta-llama/llama-3.3-70b-instruct
- meta-llama/llama-4-maverick
- meta-llama/llama-4-scout
- meta-llama/llama-guard-2-8b
- meta-llama/llama-guard-3-8b
- meta-llama/llama-guard-4-12b
- '---MICROSOFT---'
- microsoft/phi-3-medium-128k-instruct
- microsoft/phi-3-mini-128k-instruct
- microsoft/phi-3.5-mini-128k-instruct
- microsoft/phi-4
- microsoft/phi-4-multimodal-instruct
- microsoft/phi-4-reasoning-plus
- microsoft/wizardlm-2-8x22b
- '---MISTRALAI---'
- mistralai/codestral-2501
- mistralai/codestral-mamba
- mistralai/devstral-small
- mistralai/ministral-3b
- mistralai/ministral-8b
- mistralai/mistral-7b-instruct
- mistralai/mistral-7b-instruct-v0.1
- mistralai/mistral-7b-instruct-v0.2
- mistralai/mistral-7b-instruct-v0.3
- mistralai/mistral-large
- mistralai/mistral-large-2407
- mistralai/mistral-large-2411
- mistralai/mistral-medium
- mistralai/mistral-medium-3
- mistralai/mistral-nemo
- mistralai/mistral-saba
- mistralai/mistral-small
- mistralai/mistral-small-24b-instruct-2501
- mistralai/mistral-small-3.1-24b-instruct
- mistralai/mistral-tiny
- mistralai/mixtral-8x22b-instruct
- mistralai/mixtral-8x7b-instruct
- mistralai/pixtral-12b
- mistralai/pixtral-large-2411
- '---NEVERSLEEP---'
- neversleep/llama-3-lumimaid-70b
- neversleep/llama-3-lumimaid-8b
- neversleep/llama-3.1-lumimaid-70b
- neversleep/llama-3.1-lumimaid-8b
- neversleep/noromaid-20b
- '---NOUSRESEARCH---'
- nousresearch/hermes-2-pro-llama-3-8b
- nousresearch/hermes-3-llama-3.1-405b
- nousresearch/hermes-3-llama-3.1-70b
- nousresearch/nous-hermes-2-mixtral-8x7b-dpo
- '---OPENAI---'
- openai/chatgpt-4o-latest
- openai/codex-mini
- openai/gpt-3.5-turbo
- openai/gpt-3.5-turbo-0125
- openai/gpt-3.5-turbo-0613
- openai/gpt-3.5-turbo-1106
- openai/gpt-3.5-turbo-16k
- openai/gpt-3.5-turbo-instruct
- openai/gpt-4
- openai/gpt-4-0314
- openai/gpt-4-1106-preview
- openai/gpt-4-32k
- openai/gpt-4-32k-0314
- openai/gpt-4-turbo
- openai/gpt-4-turbo-preview
- openai/gpt-4.1
- openai/gpt-4.1-mini
- openai/gpt-4.1-nano
- openai/gpt-4.5-preview
- openai/gpt-4o
- openai/gpt-4o-2024-05-13
- openai/gpt-4o-2024-08-06
- openai/gpt-4o-2024-11-20
- openai/gpt-4o-mini
- openai/gpt-4o-mini-2024-07-18
- openai/gpt-4o-mini-search-preview
- openai/gpt-4o-search-preview
- openai/o1
- openai/o1-mini
- openai/o1-mini-2024-09-12
- openai/o1-preview
- openai/o1-preview-2024-09-12
- openai/o1-pro
- openai/o3
- openai/o3-mini
- openai/o3-mini-high
- openai/o4-mini
- openai/o4-mini-high
- '---PERPLEXITY---'
- perplexity/llama-3.1-sonar-large-128k-online
- perplexity/llama-3.1-sonar-small-128k-online
- perplexity/r1-1776
- perplexity/sonar
- perplexity/sonar-deep-research
- perplexity/sonar-pro
- perplexity/sonar-reasoning
- perplexity/sonar-reasoning-pro
- '---QWEN---'
- qwen/qwen-2-72b-instruct
- qwen/qwen-2.5-72b-instruct
- qwen/qwen-2.5-7b-instruct
- qwen/qwen-2.5-coder-32b-instruct
- qwen/qwen-2.5-vl-7b-instruct
- qwen/qwen-max
- qwen/qwen-plus
- qwen/qwen-turbo
- qwen/qwen-vl-max
- qwen/qwen-vl-plus
- qwen/qwen2.5-coder-7b-instruct
- qwen/qwen2.5-vl-32b-instruct
- qwen/qwen2.5-vl-72b-instruct
- qwen/qwen3-14b
- qwen/qwen3-235b-a22b
- qwen/qwen3-30b-a3b
- qwen/qwen3-32b
- qwen/qwen3-8b
- qwen/qwq-32b
- qwen/qwq-32b-preview
- '---SAO10K---'
- sao10k/fimbulvetr-11b-v2
- sao10k/l3-euryale-70b
- sao10k/l3-lunaris-8b
- sao10k/l3.1-euryale-70b
- sao10k/l3.3-euryale-70b
- '---THEDRUMMER---'
- thedrummer/anubis-pro-105b-v1
- thedrummer/rocinante-12b
- thedrummer/skyfall-36b-v2
- thedrummer/unslopnemo-12b
- thedrummer/valkyrie-49b-v1
- '---THUDM---'
- thudm/glm-4-32b
- thudm/glm-z1-32b
- thudm/glm-z1-rumination-32b
- '---X-AI---'
- x-ai/grok-2-1212
- x-ai/grok-2-vision-1212
- x-ai/grok-3-beta
- x-ai/grok-3-mini-beta
- x-ai/grok-beta
- x-ai/grok-vision-beta
- '---OTHERS---'
- 01-ai/yi-large
- aetherwiing/mn-starcannon-12b
- ai21/jamba-1.6-large
- ai21/jamba-1.6-mini
- alfredpros/codellama-7b-instruct-solidity
- all-hands/openhands-lm-32b-v0.1
- allenai/olmo-7b-instruct
- alpindale/goliath-120b
- alpindale/magnum-72b
- anthracite-org/magnum-v2-72b
- anthracite-org/magnum-v4-72b
- cognitivecomputations/dolphin-mixtral-8x22b
- eleutherai/llemma_7b
- gryphe/mythomax-l2-13b
- inception/mercury-coder-small-beta
- infermatic/mn-inferor-12b
- inflection/inflection-3-pi
- inflection/inflection-3-productivity
- mancer/weaver
- minimax/minimax-01
- nothingiisreal/mn-celeste-12b
- nvidia/llama-3.1-nemotron-70b-instruct
- nvidia/llama-3.3-nemotron-super-49b-v1
- pygmalionai/mythalion-13b
- raifle/sorcererlm-8x22b
- sarvamai/sarvam-m
- scb10x/llama3.1-typhoon2-70b-instruct
- scb10x/llama3.1-typhoon2-8b-instruct
- sophosympatheia/midnight-rose-70b
- undi95/remm-slerp-l2-13b
- undi95/toppy-m-7b
fetch: false
dropParams:
- "stop"
titleConvo: true
titleModel: "openai/gpt-4o-mini"
summarize: false
summaryModel: "openai/gpt-4o-mini"
forcePrompt: false
modelDisplayLabel: "OpenRouter"
# Preplexity
# Model list: https://docs.perplexity.ai/docs/model-cards
- name: "Perplexity"
apiKey: "${PERPLEXITY_API_KEY}"
baseURL: "https://api.perplexity.ai/"
models:
default:
- r1-1776
- sonar
- sonar-deep-research
- sonar-pro
- sonar-reasoning
- sonar-reasoning-pro
fetch: false # fetching list of models is not supported
titleConvo: true
titleModel: "llama-3.1-sonar-small-128k-chat"
summarize: false
summaryModel: "llama-3.1-sonar-small-128k-chat"
forcePrompt: false
dropParams:
- "stop"
- "frequency_penalty"
modelDisplayLabel: "Perplexity"
# SambaNova
# https://cloud.sambanova.ai/apis
- name: "SambaNova"
iconURL: "https://sambanova.ai/hubfs/logotype_sambanova_orange.png"
apiKey: "${SAMBANOVA_API_KEY}"
baseURL: "https://api.sambanova.ai/v1/"
models:
default:
- DeepSeek-R1
- DeepSeek-R1-Distill-Llama-70B
- Llama-3.1-Tulu-3-405B
- Llama-3.2-11B-Vision-Instruct
- Llama-3.2-90B-Vision-Instruct
- Meta-Llama-3.1-405B-Instruct
- Meta-Llama-3.1-70B-Instruct
- Meta-Llama-3.1-8B-Instruct
- Meta-Llama-3.2-1B-Instruct
- Meta-Llama-3.2-3B-Instruct
- Meta-Llama-3.3-70B-Instruct
- Meta-Llama-Guard-3-8B
- QwQ-32B-Preview
- Qwen2-Audio-7B-Instruct
- Qwen2.5-72B-Instruct
- Qwen2.5-Coder-32B-Instruct
fetch: false
titleConvo: true
titleModel: "Meta-Llama-3.1-8B-Instruct"
modelDisplayLabel: "SambaNova"
# together.ai
# https://api.together.ai/settings/api-keys
# Model list: https://docs.together.ai/docs/inference-models
- name: "together.ai"
apiKey: "${TOGETHERAI_API_KEY}"
baseURL: "https://api.together.xyz"
models:
default:
- Gryphe/MythoMax-L2-13b
- Gryphe/MythoMax-L2-13b-Lite
- NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
- Qwen/QwQ-32B
- Qwen/Qwen2-72B-Instruct
- Qwen/Qwen2-VL-72B-Instruct
- Qwen/Qwen2.5-72B-Instruct-Turbo
- Qwen/Qwen2.5-7B-Instruct-Turbo
- Qwen/Qwen2.5-Coder-32B-Instruct
- Qwen/Qwen2.5-VL-72B-Instruct
- Qwen/Qwen3-235B-A22B-fp8
- Qwen/Qwen3-235B-A22B-fp8-tput
- arcee-ai/arcee-blitz
- arcee-ai/caller
- arcee-ai/coder-large
- arcee-ai/maestro-reasoning
- arcee-ai/virtuoso-large
- arcee-ai/virtuoso-medium-v2
- arcee_ai/arcee-spotlight
- deepseek-ai/DeepSeek-R1
- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- deepseek-ai/DeepSeek-R1-Distill-Llama-70B-free
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- deepseek-ai/DeepSeek-V3
- deepseek-ai/DeepSeek-V3-p-dp
- google/gemma-2-27b-it
- google/gemma-2b-it
- marin-community/marin-8b-instruct
- meta-llama/Llama-3-70b-chat-hf
- meta-llama/Llama-3-8b-chat-hf
- meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
- meta-llama/Llama-3.2-3B-Instruct-Turbo
- meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
- meta-llama/Llama-3.3-70B-Instruct-Turbo
- meta-llama/Llama-3.3-70B-Instruct-Turbo-Free
- meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
- meta-llama/Llama-4-Scout-17B-16E-Instruct
- meta-llama/Llama-Vision-Free
- meta-llama/Meta-Llama-3-70B-Instruct-Turbo
- meta-llama/Meta-Llama-3-8B-Instruct-Lite
- meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
- meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
- meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
- mistralai/Mistral-7B-Instruct-v0.1
- mistralai/Mistral-7B-Instruct-v0.2
- mistralai/Mistral-7B-Instruct-v0.3
- mistralai/Mistral-Small-24B-Instruct-2501
- mistralai/Mixtral-8x7B-Instruct-v0.1
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
- perplexity-ai/r1-1776
- scb10x/scb10x-llama3-1-typhoon2-70b-instruct
- scb10x/scb10x-llama3-1-typhoon2-8b-instruct
- togethercomputer/MoA-1
- togethercomputer/MoA-1-Turbo
- togethercomputer/Refuel-Llm-V2
- togethercomputer/Refuel-Llm-V2-Small
fetch: false
titleConvo: true
titleModel: "togethercomputer/llama-2-7b-chat"
summarize: false
summaryModel: "togethercomputer/llama-2-7b-chat"
forcePrompt: false
modelDisplayLabel: "together.ai"
# Unify
# Model list: https://unify.ai/chat
- name: "Unify"
apiKey: "${UNIFY_API_KEY}"
baseURL: "https://api.unify.ai/v0/"
models:
default:
- chatgpt-4o-latest@openai
- claude-3-haiku@anthropic
- claude-3-haiku@aws-bedrock
- claude-3-haiku@vertex-ai
- claude-3-opus@anthropic
- claude-3-opus@aws-bedrock
- claude-3-opus@vertex-ai
- claude-3-sonnet@anthropic
- claude-3-sonnet@aws-bedrock
- claude-3.5-haiku@anthropic
- claude-3.5-haiku@aws-bedrock
- claude-3.5-haiku@replicate
- claude-3.5-haiku@vertex-ai
- claude-3.5-sonnet-20240620@anthropic
- claude-3.5-sonnet-20240620@aws-bedrock
- claude-3.5-sonnet-20240620@vertex-ai
- claude-3.5-sonnet@anthropic
- claude-3.5-sonnet@aws-bedrock
- claude-3.5-sonnet@replicate
- claude-3.5-sonnet@vertex-ai
- claude-3.7-sonnet@anthropic
- claude-3.7-sonnet@aws-bedrock
- claude-3.7-sonnet@replicate
- claude-3.7-sonnet@vertex-ai
- command-r-plus@aws-bedrock
- deepseek-r1@aws-bedrock
- deepseek-r1@deepinfra
- deepseek-r1@deepseek
- deepseek-r1@fireworks-ai
- deepseek-r1@replicate
- deepseek-r1@together-ai
- deepseek-v3-0324@deepinfra
- deepseek-v3-0324@fireworks-ai
- deepseek-v3@deepinfra
- deepseek-v3@deepseek
- deepseek-v3@fireworks-ai
- deepseek-v3@replicate
- deepseek-v3@together-ai
- gemini-1.5-flash-002@vertex-ai
- gemini-1.5-flash@vertex-ai
- gemini-1.5-pro-002@vertex-ai
- gemini-1.5-pro@vertex-ai
- gemini-2.0-flash-lite@vertex-ai
- gemini-2.0-flash@vertex-ai
- gemini-2.5-flash@vertex-ai
- gemini-2.5-pro@vertex-ai
- gemma-2-27b-it@together-ai
- gemma-2-9b-it@groq
- gemma-3-12b-it@deepinfra
- gemma-3-27b-it@deepinfra
- gemma-3-4b-it@deepinfra
- gpt-3.5-turbo@openai
- gpt-4-turbo@openai
- gpt-4.1-mini@openai
- gpt-4.1-nano@openai
- gpt-4.1@openai
- gpt-4.5-preview@openai
- gpt-4@openai
- gpt-4o-2024-05-13@openai
- gpt-4o-2024-08-06@openai
- gpt-4o-2024-11-20@openai
- gpt-4o-mini-search-preview@openai
- gpt-4o-mini@openai
- gpt-4o-search-preview@openai
- gpt-4o@openai
- grok-2-vision@xai
- grok-2@xai
- grok-3-fast@xai
- grok-3-mini-fast@xai
- grok-3-mini@xai
- grok-3@xai
- llama-3-70b-chat@aws-bedrock
- llama-3-70b-chat@deepinfra
- llama-3-70b-chat@groq
- llama-3-70b-chat@replicate
- llama-3-8b-chat@aws-bedrock
- llama-3-8b-chat@deepinfra
- llama-3-8b-chat@groq
- llama-3-8b-chat@replicate
- llama-3.1-405b-chat@aws-bedrock
- llama-3.1-405b-chat@deepinfra
- llama-3.1-405b-chat@fireworks-ai
- llama-3.1-405b-chat@replicate
- llama-3.1-405b-chat@together-ai
- llama-3.1-405b-chat@vertex-ai
- llama-3.1-70b-chat@aws-bedrock
- llama-3.1-70b-chat@deepinfra
- llama-3.1-70b-chat@fireworks-ai
- llama-3.1-70b-chat@together-ai
- llama-3.1-70b-chat@vertex-ai
- llama-3.1-8b-chat@aws-bedrock
- llama-3.1-8b-chat@deepinfra
- llama-3.1-8b-chat@fireworks-ai
- llama-3.1-8b-chat@groq
- llama-3.1-8b-chat@together-ai
- llama-3.1-8b-chat@vertex-ai
- llama-3.1-nemotron-70b-chat@deepinfra
- llama-3.2-11b-chat@deepinfra
- llama-3.2-11b-chat@together-ai
- llama-3.2-11b-chat@vertex-ai
- llama-3.2-1b-chat@aws-bedrock
- llama-3.2-1b-chat@deepinfra
- llama-3.2-3b-chat@aws-bedrock
- llama-3.2-3b-chat@deepinfra
- llama-3.2-3b-chat@together-ai
- llama-3.2-90b-chat@deepinfra
- llama-3.2-90b-chat@together-ai
- llama-3.2-90b-chat@vertex-ai
- llama-3.3-70b-chat@aws-bedrock
- llama-3.3-70b-chat@deepinfra
- llama-3.3-70b-chat@fireworks-ai
- llama-3.3-70b-chat@groq
- llama-3.3-70b-chat@together-ai
- llama-3.3-70b-chat@vertex-ai
- llama-4-maverick-instruct@deepinfra
- llama-4-maverick-instruct@fireworks-ai
- llama-4-maverick-instruct@groq
- llama-4-maverick-instruct@replicate
- llama-4-maverick-instruct@together-ai
- llama-4-maverick-instruct@vertex-ai
- llama-4-scout-instruct@deepinfra
- llama-4-scout-instruct@fireworks-ai
- llama-4-scout-instruct@groq
- llama-4-scout-instruct@replicate
- llama-4-scout-instruct@together-ai
- llama-4-scout-instruct@vertex-ai
- ministral-3b@mistral-ai
- ministral-8b@mistral-ai
- mistral-7b-instruct-v0.3@deepinfra
- mistral-7b-instruct-v0.3@together-ai
- mistral-large@mistral-ai
- mistral-large@vertex-ai
- mistral-nemo@deepinfra
- mistral-nemo@mistral-ai
- mistral-nemo@vertex-ai
- mistral-small@deepinfra
- mistral-small@mistral-ai
- mistral-small@together-ai
- mistral-small@vertex-ai
- mixtral-8x22b-instruct-v0.1@fireworks-ai
- mixtral-8x7b-instruct-v0.1@deepinfra
- o1-mini@openai
- o1-pro@openai
- o1@openai
- o3-mini@openai
- o3@openai
- o4-mini@openai
- qwen-2-72b-instruct@together-ai
- qwen-2.5-72b-instruct@deepinfra
- qwen-2.5-72b-instruct@fireworks-ai
- qwen-2.5-72b-instruct@together-ai
- qwen-2.5-7b-instruct@deepinfra
- qwen-2.5-7b-instruct@together-ai
- qwen-2.5-coder-32b-instruct@deepinfra
- qwen-2.5-coder-32b-instruct@together-ai
- qwen-3-235b-a22b-instruct@deepinfra
- qwen-3-235b-a22b-instruct@fireworks-ai
- qwen-3-235b-a22b-instruct@together-ai
- qwen-3-30b-a3b-instruct@deepinfra
- qwen-3-30b-a3b-instruct@fireworks-ai
- qwen-qwq-32b@deepinfra
- qwen-qwq-32b@fireworks-ai
- qwen-qwq-32b@groq
- qwen-qwq-32b@together-ai
fetch: false
titleConvo: true
titleModel: "gpt-4o-mini@openai"
dropParams:
- "stop"
- "user"
- "frequency_penalty"
- "presence_penalty"
# xAI
# https://x.ai/api
- name: "xai"
apiKey: "${XAI_API_KEY}"
baseURL: "https://api.x.ai/v1"
models:
default:
- grok-2-1212
- grok-2-vision-1212
- grok-3-beta
- grok-3-mini-beta
- grok-beta
- grok-vision-beta
fetch: false
titleConvo: true
titleMethod: "completion"
titleModel: "grok-beta"
summarize: false
summaryModel: "grok-beta"
forcePrompt: false
modelDisplayLabel: "Grok"