Together AI API pricing
by Together AIper 1M tokens
$0.47 / 1M outputQwen3.8 Flash (Together) · the cheapest model
Together AI API costs $0.15–$3.00 per 1M input tokens and $0.47–$15.00 per 1M output tokens. Output tokens cost several times more than input, so long answers drive the bill. Together AI sells API access only; there is no chat subscription.
Cheapest output$0.47Qwen3.8 Flash (Together) · per 1M
Top model$15.00Kimi K3 (Together) · per 1M output
Every model, per 1M tokens
USD list price, before batch or volume discounts| Model | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Kimi K3 (Together) | $3.00 | $15.00 | $0.30 | — |
| Kimi K3.1 Pro (Together) | $2.00 | $10.00 | $0.20 | — |
| GLM-5.3 (Together) | $1.40 | $4.40 | $0.26 | — |
| GLM-5.3 Flash (Together) | $0.15 | $0.50 | $0.03 | — |
| DeepSeek V4 Pro 0813 (Together) | $1.32 | $3.96 | $0.13 | — |
| DeepSeek V4.1 Flash (Together) | $0.30 | $1.20 | $0.006 | — |
| MiniMax M3 (Together) | $0.30 | $1.20 | $0.06 | — |
| MiniMax M3.1 Flash (Together) | $0.15 | $0.60 | $0.015 | — |
| Qwen3.7-Max (Together) | $2.50 | $7.50 | $0.50 | — |
| Qwen3.6-Plus (Together) | $0.50 | $3.00 | — | — |
| Qwen3.8 Flash (Together) | $0.15 | $0.47 | — | — |
| gpt-oss-120B (Together) | $0.15 | $0.60 | — | — |
| NVIDIA Nemotron 3.5 Super VL (Together) | $0.15 | $0.50 | $0.02 | — |
| Muse Spark Open 816B A42B (Together) | $1.25 | $4.25 | $0.15 | — |
What will you pay?
$240.00
per month on Kimi K3 (Together)
Prices from together.ai/pricing How we collect prices Some links are affiliate links; they never change the prices or the order shown. Disclosure