LLM Cost Calculator

Together AI API Pricing 2025

Best prices for the latest open-source and frontier models. Supports Kimi K2.5, DeepSeek V4 Pro, Qwen3.5, and Llama 4 via serverless inference.

Get Together AI API access →

Together AI Model Pricing

Prices in USD per 1M tokens

ModelInput / 1MOutput / 1MContext
Kimi K2.5 (Together)
Latest Moonshot AI model; strong code & reasoning
$0.5$2.8128,000
Qwen3.5 397B (Together)
Alibaba's latest large MoE; strong multilingual
$0.6$3.6128,000
Llama 3.3 70B (Together)
Reliable open-source 70B; can also be self-hosted
$0.88$0.88128,000
DeepSeek V4 Pro (Together)
Latest DeepSeek via Together AI serverless
$2.1$4.4128,000

Estimated Monthly Cost (70% input / 30% output split)

Model1M tokens/mo10M tokens/mo100M tokens/mo1B tokens/mo
Kimi K2.5 (Together)$1.19$11.90$119$1,190
Qwen3.5 397B (Together)$1.50$15.00$150$1,500
Llama 3.3 70B (Together)$0.880$8.80$88.00$880
DeepSeek V4 Pro (Together)$2.79$27.90$279$2,790

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. Best prices for the latest open-source and frontier models. Supports Kimi K2.5, DeepSeek V4 Pro, Qwen3.5, and Llama 4 via serverless inference.

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.