Start free →

Compare

Side by side.

Pick up to three companies to compare current plans and recent moves.

Together AI

Together AI charges based on usage for various services like serverless inference, dedicated inference, GPU clusters, sandbox compute, and fine-tuning, with prices varying by model, hardware, and duration.

Serverless Inference (Kimi K3)$3.00per 1M input tokens
  • Output: $15.00 per 1M tokens
  • Cached output: $0.30 per 1M tokens
Serverless Inference (Ternary Bonsai 27B)$0.00per 1M input tokens
    Dedicated Inference (NVIDIA HGX H100)$5.49per gpu per hour
    • Guaranteed performance
    • Support for custom models
    • Autoscaling & traffic spike handling
    GPU Clusters (NVIDIA HGX H100)$3.99per GPU per hour
    • On-demand pay as you go
    Sandbox (Per vCPU)$0.0446per hour
    • Customize VM sandboxes
    Post-Training (NVIDIA HGX B200)$9.00per GPU per hour
    • On-demand training infrastructure
    • Promotion valid until 12/14/2026

    Captured Oct 21, 2026 from the public pricing page.

    Recent changes

    P0 Together AI Updates Fine-Tuning and Inference Pricing, Introduces New Models and Post-Training Service

    Fireworks AI

    Fireworks AI offers usage-based pricing for serverless inference and training, with on-demand deployments billed per GPU second or hour.

    Serverless Inference (Embeddings up to 150M)$0.008per 1M input tokens
    • Pay per token
    • Zero setup
    • No cold starts
    • Usage-based billing
    Serverless Inference (Embeddings 150M - 350M)$0.016per 1M input tokens
    • Pay per token
    • Zero setup
    • No cold starts
    • Usage-based billing
    Serverless Inference (Qwen3 8B)$0.1per 1M input tokens
    • Pay per token
    • Zero setup
    • No cold starts
    • Usage-based billing
    Managed Training (Models up to 16B parameters)$0.50per 1M training tokens (LoRA SFT)
    • Supervised and preference fine tuning
    • Minimal setup
    On Demand Deployments (H100 80 GB GPU)$8.00per hour
    • Pay per GPU second
    • No extra charges for start-up times
    • Faster speeds
    • Higher rate limits
    On Demand Deployments (B300 288 GB GPU)$15.00per hour
    • Pay per GPU second
    • No extra charges for start-up times
    • Faster speeds
    • Higher rate limits

    Captured Oct 21, 2026 from the public pricing page.

    Recent changes

    P0 Fireworks AI updates pricing model from postpaid to prepaid and introduces new model pricing