Models
If you’re not sure which model to use, see Recommended models for our picks by use case.Chat
Image
Vision
Video
Audio
Embedding
Rerank
Moderation
Serverless and dedicated endpoints support different sets of models. See the dedicated endpoint model catalog for details.
Rate limits
Serverless models are rate-limited, so they work best when you’re prototyping or evaluating a model, or when your production traffic is variable, bursty, or low enough that per-token pricing is cost-effective. If your traffic is steady, you need higher rate limits, or you want reserved hardware, use a dedicated endpoint.Pricing
Serverless models bill based on usage, with no minimums and no provisioning cost. Per-model rates are in the catalog tables below, and on together.ai/pricing. If you don’t need real-time responses, some models are discounted up to 50% when run with batch workloads.Chat models
Chat model examples
- PDF to chat app: Chat with your PDFs (blogs, textbooks, papers).
- Open deep research notebook: Generate long form reports using a single prompt.
- RAG with reasoning models notebook: RAG with DeepSeek-R1.
- Fine-tuning chat models notebook: Tune language models for conversation.
- Building agents: Agent workflows with language models.
Image models
Use our Images endpoint for image models.Calling image models requires a positive credit balance.
Image model examples
- Blinkshot.io: A realtime AI image playground built with Flux Schnell.
- Logo creator: A logo generator that creates professional logos in seconds using Flux Pro 1.1.
- PicMenu: A menu visualizer that takes a restaurant menu and generates nice images for each dish.
- Flux LoRA inference notebook: Using LoRA fine-tuned image generations models.
- Default pricing: The listed per megapixel prices are for the default number of steps.
- Using more or fewer steps: Costs are adjusted based on the number of steps used only if you go above the default steps. If you use more steps, the cost increases proportionally using the formula below. If you use fewer steps, the cost does not decrease and is based on the default rate.
- MP = (Width × Height ÷ 1,000,000).
- Price per MP = Cost for generating one megapixel at the default steps.
- Steps = The number of steps used for the image generation. This is only factored in if going above default steps.
Gemini 3 Pro Image pricing
Gemini 3 Pro Image offers pricing based on the resolution of the image.- 1080p and 2K: $0.134/image.
- 4K resolution: $0.24/image.
Vision models
If you’re not sure which vision model to use, we currently recommend Qwen3.5 9B (Qwen/Qwen3.5-9B) to get started. For model specific rate limits, navigate here.
Vision model examples
- LlamaOCR: A tool that takes documents (like receipts) and outputs markdown.
- Wireframe to code: A wireframe to app tool that takes in a UI mockup of a site and gives you React code.
- Extracting structured data from images: Extract information from images as JSON.
Video models
Audio models
Use our Audio endpoint for text-to-speech models. For speech-to-text models see Transcription and Translations.
Audio model examples
- PDF to podcast notebook: Generate a NotebookLM style podcast given a PDF.
- Audio podcast agent workflow: Agent workflow to generate audio files given input content.
Embedding models
Embedding model examples
- Contextual RAG: An open source implementation of contextual RAG by Anthropic.
- Code generation agent: An agent workflow to generate and iteratively improve code.
- Multimodal search and image generation: Search for images and generate more similar ones.
- Visualizing embeddings: Visualizing and clustering vector embeddings.
Rerank models
There are currently no rerank models offered via serverless. Rerank models likemixedbread-ai/mxbai-rerank-large-v2 are only available as dedicated endpoints.
Rerank model examples
- Search and reranking: Simple semantic search pipeline improved using a reranker.
- Implementing hybrid search notebook: Implementing semantic + lexical search along with reranking.