AI API Pricing

Compare AI API pricing by model and workload

AI API cost depends on the model, input and output tokens, cached tokens, and billing plan. Use the live LivRouter catalog for current rates, then compare providers on the same workload instead of choosing from a single input-price number.

Maintained by LivRouter. Reviewed . Prices and availability can change; verify the live catalog before deployment.

A consistent way to compare API costs

  1. Use the same model task, prompt, expected input size, and output length for every provider.
  2. Calculate input, output, and cached-token charges separately using each provider's stated units.
  3. Add subscription or platform fees. A lower token rate does not necessarily mean a lower total bill.
  4. Check context limits, tool support, rate limits, and the exact model ID before switching production traffic.

For token-priced models, estimate cost as (input tokens × input rate + output tokens × output rate + cached tokens × cached rate) ÷ 1,000,000 when rates are quoted per million tokens. Request-priced models use their published per-call rate instead.

Current lower listed input rates

Rates are drawn from the same model catalog as the live pricing table. This is not a quality ranking; output and cached-token rates also affect total cost.

ModelProviderLowest listed input ratePlan
Claude Haiku 5 5Anthropic$0.007 / 1M input tokensMax Claude Kiro
Minimax M3.1 FlashMiniMax$0.008 / 1M input tokensMax MiniMax
Mimo v2.6 FlashXiaomi$0.0224 / 1M input tokensMax Mimo
GLM 5.3 FlashZ.ai$0.024 / 1M input tokensMax Glm
Minimax M3MiniMax$0.024 / 1M input tokensMax MiniMax
Qwen3.8 FlashAlibaba$0.024 / 1M input tokensMax Qwen
DeepSeek v4 FlashDeepSeek$0.0315 / 1M input tokensMax Deepseek
DeepSeek v4.1 FlashDeepSeek$0.0315 / 1M input tokensMax Deepseek

Rates are LivRouter catalog rates, not a claim that LivRouter is cheaper than every provider. Compare like-for-like model versions, plan eligibility, and all token categories.

Source: LivRouter model catalog. Checked .

Model rates and plan fees are different

The model directory lists token or per-request usage prices. Plans and billing explains subscription fees, included credits, renewal, and how plan rates apply. Review both before estimating monthly spend.

Open the live model pricing catalog