Model Overview
Explore Assisters' proprietary AI models
Model Overview
TL;DR
Assisters offers 9 AI models: Chat (128K context), Vision (OCR & image analysis), Code (generation & debugging), Embeddings (100+ languages), Moderation (14 safety categories), Reranking (RAG optimization), Speech-to-Text (100+ languages), Text-to-Speech (300+ voices), and Image Generation. All accessible via OpenAI-compatible API at api.assisters.dev/v1.
Assisters API provides access to our suite of proprietary AI models across multiple categories. All models are served through our unified, OpenAI-compatible API.
Assisters Models: Like Anthropic, OpenAI, and Google, we develop and serve our own proprietary models optimized for performance, safety, and reliability.
Model Categories
Chat
Conversational AI with advanced reasoning and 128K context
Vision
Image understanding, OCR, and visual analysis
Code
Expert code generation, debugging, and refactoring
Embeddings
Multilingual text embeddings for semantic search
Moderation
Content safety with 14 harm categories
Reranking
Improve search quality by reranking results
Speech-to-Text
Transcribe audio in 100+ languages
Text-to-Speech
Natural voice synthesis with 300+ voices
Image Generation
High-quality image generation from text prompts
Model Catalog
| Model | Category | Context | Description |
|---|---|---|---|
assisters-chat-v1 | Chat | 128K | Advanced reasoning and conversation |
assisters-vision-v1 | Vision | 128K | Image analysis, OCR, visual Q&A |
assisters-code-v1 | Code | 128K | Code generation and debugging |
assisters-embed-v1 | Embeddings | 8K | Multilingual embeddings (100+ languages) |
assisters-rerank-v1 | Reranking | - | Document reranking for RAG |
assisters-moderation-v1 | Moderation | 8K | Content safety classification |
assisters-whisper-v1 | Speech-to-Text | - | Audio transcription (100+ languages) |
assisters-tts-v1 | Text-to-Speech | - | Voice synthesis (300+ voices) |
assisters-image-v1 | Image | - | Text-to-image generation |
Pricing
All models are billed per usage. See our pricing page for details.
| Category | Input per 1M tokens | Output per 1M tokens |
|---|---|---|
| Chat | $0.10 | $0.20 |
| Vision | $0.05 | $0.10 |
| Code | $0.10 | $0.20 |
| Embeddings | $0.01 | — |
| Moderation | $0.05 | — |
| Reranking | $0.02 | — |
| Speech-to-Text | $0.006/min | — |
| Text-to-Speech | $15.00/M chars | — |
| Image Generation | $0.020/image | — |
Choosing the Right Model
For Chat & Reasoning
For Search & RAG
For Safety
For Media
Coming Soon
Assisters Video v1
Generate short video clips from text prompts
Assisters Audio v1
Generate music and sound effects
Model Updates
We continuously improve our models:
- Performance improvements are applied automatically
- New models are announced in our changelog
- Deprecations are announced 3+ months in advance
View Changelog
Stay updated on model changes and additions