Together AI API Pricing 2026
Together AI provides serverless inference for a range of open-weight models. Model availability and pricing depend on the selected deployment and provider rate card.
Pricing data updated 2026-11-02. Provider rate card: www.together.ai/pricing.
Get Together AI API access →Together AI Model Pricing
Prices in USD per 1M tokens
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
Kimi K2.5 (Together) Latest Moonshot AI model; strong code & reasoning | $0.5 | $2.8 | 128,000 |
DeepSeek V4 Pro (Together) Latest DeepSeek via Together AI serverless | $2.1 | $4.4 | 128,000 |
Qwen3.5 397B (Together) Alibaba's latest large MoE; strong multilingual | $0.6 | $3.6 | 128,000 |
Llama 3.3 70B (Together) Reliable open-source 70B; can also be self-hosted | $0.88 | $0.88 | 128,000 |
How to read these estimates
The monthly table assumes 70% input tokens and 30% output tokens. It is a consistent comparison baseline, not a prediction of your workload. Actual bills can also include cached-input discounts, batch pricing, tool calls, minimum charges, regional differences, retries, and taxes.
The linked source is the provider's pricing documentation. Catalog rates may include third-party prices. Verify the current rate card and model availability before committing to a budget.
Estimated Monthly Cost (70% input / 30% output split)
| Model | 1M tokens/mo | 10M tokens/mo | 100M tokens/mo | 1B tokens/mo |
|---|---|---|---|---|
| Kimi K2.5 (Together) | $1.19 | $11.90 | $119 | $1,190 |
| DeepSeek V4 Pro (Together) | $2.79 | $27.90 | $279 | $2,790 |
| Qwen3.5 397B (Together) | $1.50 | $15.00 | $150 | $1,500 |
| Llama 3.3 70B (Together) | $0.880 | $8.80 | $88.00 | $880 |
Frequently Asked Questions
How much does Together AI LLM API cost?
Together AI offers 4 models ranging from $0.500/1M to $2.10/1M input tokens. Together AI provides serverless inference for a range of open-weight models. Model availability and pricing depend on the selected deployment and provider rate card.
Is Together AI cheaper than self-hosting?
For low-volume workloads (under 100M tokens/month), cloud APIs like Together AI are almost always cheaper than purchasing and maintaining GPU hardware. Use our calculator to find the exact break-even point for your usage.