Together AI
Open-model inference and fine-tuning at frontier speed.
Full Together AI record →Head to head
Together AI (Together AI) and Fireworks AI (Fireworks AI) both sit in Infrastructure & Serving. Every value below comes from the latest crawl of the vendors' own pages.
| Attribute | Together AI Together AI | Fireworks AI Fireworks AI |
|---|---|---|
| Segment | Infrastructure & Serving | Infrastructure & Serving |
| Version | 2025 | 2025 |
| Entry cost | Per-token, from $0.06/M | Per-token usage |
| Pricing tiers | — | — |
| Model stack | Llama · Qwen | Llama · Qwen |
| Context window | — | — |
| Public API | ||
| Routes models | ||
| Changes / 30d | 0 | 0 |
| Origin | Global | Global |
| Capabilities | Serverless inference, Fine-tuning, GPU clusters | Fast serving, FireAttention, Fine-tuning |
Open-model inference and fine-tuning at frontier speed.
Full Together AI record →Low-latency serving for open models and custom fine-tunes.
Full Fireworks AI record →