Model Overview
Assisters API provides access to 18+ open-source AI models across four categories. All models are served through our unified, OpenAI-compatible API.Free Models Available: We offer completely free models powered by Groq and HuggingFace:
- Chat: Llama 3.3 70B (FREE via Groq)
- Embeddings: BGE-M3 (FREE via HuggingFace)
- Moderation: Llama Guard 3 8B (FREE via Groq)
Model Categories
Chat Models
Generate conversational responses with models like Llama, Mistral, and Qwen
Embedding Models
Create text embeddings for semantic search and similarity
Moderation Models
Detect harmful or inappropriate content
Reranking Models
Improve search quality by reranking results
Quick Comparison
Chat Models
| Model | Provider | Context | Speed | Price |
|---|---|---|---|---|
llama-3.1-8b | Meta | 128K | Fast | $0.10/M |
llama-3.1-70b | Meta | 128K | Medium | $0.90/M |
mistral-7b | Mistral AI | 32K | Fast | $0.10/M |
qwen2-7b | Alibaba | 32K | Fast | $0.10/M |
gemma-2-9b | 8K | Fast | $0.15/M | |
phi-3-mini | Microsoft | 4K | Fastest | $0.08/M |
Embedding Models
| Model | Provider | Dimensions | Max Tokens | Price |
|---|---|---|---|---|
bge-m3 | BAAI (HuggingFace) | 1024 | 8192 | FREE |
e5-large-v2 | Microsoft | 1024 | 512 | $0.01/M |
bge-base-en | BAAI | 768 | 512 | $0.01/M |
jina-embeddings-v2 | Jina AI | 768 | 8192 | $0.02/M |
nomic-embed-text | Nomic AI | 768 | 8192 | $0.01/M |
gte-large | Alibaba | 1024 | 512 | $0.01/M |
Safety Models
| Model | Type | Provider | Price |
|---|---|---|---|
llama-guard-3 | Moderation | Meta | $0.20/M |
shieldgemma | Moderation | $0.15/M | |
bge-reranker-v2 | Reranking | BAAI | $0.05/M |
jina-reranker | Reranking | Jina AI | $0.08/M |
Choosing the Right Model
For Chat Applications
Best Overall
Best Overall
Llama 3.1 70B - Best quality for complex tasks, reasoning, and creative writing. Higher latency and cost, but excellent results.
Best Value
Best Value
Llama 3.1 8B - Great balance of quality and cost. Fast responses, good for most use cases.
Fastest
Fastest
Phi-3 Mini - Lowest latency and cost. Best for simple tasks and high-volume applications.
Long Context
Long Context
Llama 3.1 8B/70B - 128K context window for processing long documents.
For Embeddings
FREE & Best Quality
FREE & Best Quality
BGE-M3 - BAAI’s multilingual embedding model. Best quality, long context (8192 tokens), 100+ languages. Completely free via HuggingFace.
Alternative: E5-large-v2
Alternative: E5-large-v2
E5-large-v2 - Microsoft’s flagship embedding model. Best for accuracy-critical applications.
Long Documents
Long Documents
Jina Embeddings v2 - 8192 token context for embedding entire documents.
For Moderation
Most Accurate
Most Accurate
Llama Guard 3 - Meta’s latest safety model with the best accuracy.
Most Efficient
Most Efficient
ShieldGemma - Google’s efficient safety model, 25% cheaper.
Model Selection Guide
Pricing Tiers
All models are billed per million tokens. Free tier models available!| Category | Price Range | Free Option |
|---|---|---|
| Chat | FREE - $0.90/M | llama-3.3-70b via Groq |
| Embeddings | FREE - $0.02/M | bge-m3 via HuggingFace |
| Moderation | FREE - $0.20/M | llama-guard-3-8b via Groq |
| Reranking | 0.08/M | - |
View Pricing Details
See full pricing breakdown and subscription tiers
Model Updates
We continuously update our model offerings:- New models are added as they become available
- Deprecated models are announced 3+ months in advance
- Performance improvements are applied without version changes
View Changelog
Stay updated on model changes and additions