synthetic
    /Dev
    • Back to app
    Usage-based pricing
    • Usage & Billing
    API Documentation
    API
    • Overview
    • Getting Started
    • Models
    Agents
    • Octofriend by Synthetic
    • Claude Code
    • Crush
    • Opencode
    • GitHub Copilot
    • OpenClaw
    • Xcode Intelligence
    OpenAI Reference
    • /models
    • /chat/completions
    • /completions
    • /embeddings
    Anthropic Reference
    • /messages
    • /messages/count_tokens
    Synthetic Reference
    • /quotas
    • /search

    Available Models

    Subscriptions

    Always-On, LoRA, and Embeddings models are included in every subscription.

    Always-On Models

    These models are included in all subscriptions. Per-token pricing is also available with usage-based billing.

    Model Details

    More information about each model is available via the /openai/v1/models endpoint.

    ModelProviderContext lengthStatus
    hf:MiniMaxAI/MiniMax-M2.5 Synthetic187k tokens✓ Included
    hf:moonshotai/Kimi-K2.5 Synthetic256k tokens✓ Included
    hf:nvidia/Kimi-K2.5-NVFP4 Synthetic256k tokens✓ Included
    hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 Synthetic256k tokens✓ Included
    hf:zai-org/GLM-4.7 Synthetic198k tokens✓ Included
    hf:zai-org/GLM-4.7-Flash Synthetic192k tokens✓ Included
    hf:zai-org/GLM-5 Synthetic192k tokens✓ Included
    hf:deepseek-ai/DeepSeek-V3.2 Fireworks159k tokens✓ Included
    hf:MiniMaxAI/MiniMax-M2.1 Fireworks192k tokens✓ Included
    hf:moonshotai/Kimi-K2-Instruct-0905 Fireworks256k tokens✓ Included
    hf:moonshotai/Kimi-K2-Thinking Fireworks256k tokens✓ Included
    hf:openai/gpt-oss-120b Fireworks128k tokens✓ Included
    hf:deepseek-ai/DeepSeek-R1-0528 Together AI128k tokens✓ Included
    hf:deepseek-ai/DeepSeek-V3 Together AI128k tokens✓ Included
    hf:meta-llama/Llama-3.3-70B-Instruct Together AI128k tokens✓ Included
    hf:Qwen/Qwen3-235B-A22B-Thinking-2507 Together AI256k tokens✓ Included
    hf:Qwen/Qwen3-Coder-480B-A35B-Instruct Together AI256k tokens✓ Included
    hf:Qwen/Qwen3.5-397B-A17B Together AI256k tokens✓ Included

    LoRA Models

    What's a LoRA?

    Low-rank adapters — called "LoRAs" — are small, efficient fine-tunes that run on top of existing models. They can modify a model to be much more effective at specific tasks.

    We support LoRAs for the following base models:

    ModelProviderContext lengthStatus
    meta-llama/Llama-3.2-1B-Instruct Together AI128k tokens✓ Included
    meta-llama/Llama-3.2-3B-Instruct Together AI128k tokens✓ Included
    meta-llama/Meta-Llama-3.1-8B-Instruct Together AI128k tokens✓ Included
    meta-llama/Meta-Llama-3.1-70B-Instruct Together AI128k tokens✓ Included

    Embedding Models

    Embedding models convert text into numerical vectors for search, clustering, and other applications.

    There's no additional charge for using embeddings, and embeddings requests don't count against your subscription rate limit.

    ModelProviderContext lengthStatus
    hf:nomic-ai/nomic-embed-text-v1.5 Fireworks8k tokens✓ Included

    Getting Started

    Ready to start using our models? Check out:

    • Getting Started Guide - Your first API call
    • chat/completions - Most popular endpoint for conversations

    Need help choosing the right model? Join our Discord community for recommendations!