Together AI API Pricing
Together AI models from Together AI. Platform for running and fine-tuning open source models. Requesty routes to 6 Together AI models starting at $0.15 per 1M input tokens with context windows up to 1.0M tokens. One API key and an OpenAI-compatible SDK. Provider rates plus 5% on pay as you go, or 0% with your own keys.
Flagship model
deepseek-v4.1-flash-1017Intelligence Index
32.5
All Together AI models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
| 1.0M | — | $0.30 | $1.20 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 131K | $1.25 | $4.25 | 👁🧠🔧⚡ | N/A | |
| 1.0M | — | $0.30 | $1.20 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 131K | $0.15 | $0.50 | 👁🧠🔧⚡ | N/A | |
| 1.0M | 1.0M | $1.40 | $4.40 | 👁🧠🔧⚡ | 75 | |
| 1.0M | 1.0M | $1.32 | $3.96 | 🧠🔧⚡ | 69 |
About Together AI on Requesty
How many Together AI models are available through Requesty?
Requesty routes to 6 Together AI models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Together AI model?
The cheapest Together AI model starts at $0.15 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Together AI pricing?
No. Requesty passes through exactly what Together AI charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 600+ models.
Is my data used to train Together AI models?
Together AI's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Together AI models hosted?
Together AI models are hosted in 🇺🇸 US. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the Together AI rows in the models explorer.