Skip to main content

AI Models

Gomus AI comes with pre-configured AI models ready to use. Just sign up, pick a model, and start chatting.

How it works

All AI models in Gomus AI are provided as a managed service. Select your preferred model from the dropdown when creating a Chat Assistant or an Agent, and you're ready to go.

  • Free plan — Access to 20 fast models hosted on Groq infrastructure.
  • Paid plans (Base and above) — Unlock 22 additional models hosted on AWS Bedrock.

Free plan — Groq models

Free users have access to 20 models across multiple categories:

Chat & Reasoning

ModelNotes
Llama 3.3 70BHigh-quality general-purpose
Llama 3.1 8B InstantUltra-fast responses
Llama 4 MaverickLatest Llama 4 generation
Qwen 3 32BMultilingual
Kimi K2Advanced reasoning
Kimi K2 (0905)Advanced reasoning (September update)
GPT OSS 120BLarge open-source GPT
GPT OSS 20BCompact open-source GPT
Allam 2 7BArabic-optimized
Groq CompoundAgentic model with tool use
Groq Compound MiniLightweight agentic model

Vision

ModelNotes
Llama 4 ScoutMultimodal — image + text understanding

Safety & Content Moderation

ModelNotes
Llama Guard 4 12BInput/output safety classification
Llama Prompt Guard 2 22MPrompt injection detection (lightweight)
Llama Prompt Guard 2 86MPrompt injection detection
Safety GPT OSS 20BContent safety analysis

Speech & Audio

ModelType
Whisper Large v3Speech-to-Text
Whisper Large v3 TurboSpeech-to-Text (faster)
Orpheus EnglishText-to-Speech
Orpheus Arabic SaudiText-to-Speech
tip

Groq models have very low credit costs (1 credit per 1K tokens), making them ideal for exploring Gomus AI on the Free plan.

Upgrading to a paid plan unlocks premium models hosted on AWS Bedrock:

Chat & Reasoning

ModelCredit cost (per 1K tokens)
Claude Opus 4.655 input / 275 output
Claude Opus 4.555 input / 275 output
Claude Sonnet 4.633 input / 165 output
Claude Sonnet 4.533 input / 165 output
Claude Sonnet 430 input / 150 output
Claude 3.7 Sonnet30 input / 150 output
Claude 3.5 Sonnet30 input / 150 output
Claude 3 Sonnet30 input / 150 output
Claude Haiku 4.511 input / 55 output
Claude 3 Haiku3 input / 13 output
Amazon Nova Pro11 input / 42 output
Amazon Nova Lite1 input / 4 output
Amazon Nova Micro1 input / 2 output
Amazon Nova 2 Lite5 input / 36 output
Llama 3.2 3B (Bedrock)2 input / 2 output
Llama 3.2 1B (Bedrock)2 input / 2 output
Pixtral Large (Mistral)20 input / 60 output

Embedding

ModelCredit cost (per 1K tokens)
Cohere Embed V42
Cohere Embed Multilingual V31
Amazon Titan Embed Text V22

Rerank

ModelCredit cost (per 1K tokens)
Cohere Rerank V3.520

Video

ModelCredit cost (per 1K tokens)
TwelveLabs Pegasus V1.25 input / 75 output
note

All Bedrock models require a Base plan or higher.

Subscription plans

PlanMonthly CreditsPriceModelsKnowledge BasesDocs per KBMax File Size
Free1,000Free20 Groq models25010 MB
Base100,000$19.90/mo20 Groq + 22 Bedrock1050050 MB
Premium250,000$49.90/mo20 Groq + 22 Bedrock20Unlimited200 MB
Business750,000$149.90/mo20 Groq + 22 BedrockUnlimitedUnlimited500 MB

How credits work

  • Each model has a per-token credit cost (input and output tokens are priced separately).
  • Credits are deducted automatically after each AI call.

Model selection

When creating a Chat Assistant or an Agent, select which model to use from the model dropdown.

note

If you need a specific model not currently available, contact us at [email protected].