Simple, transparent pricing

Just 1%

We charge 1% on top of the model provider's batch processing price. No subscriptions, no platform fees, no hidden costs. You only pay for what you use.

1

Provider charges you

Standard batch API pricing from OpenAI, Anthropic, Google, etc.

2

Convoy adds 1%

A flat 1% fee on the batch processing cost. That's it.

3

You save up to 50%

Batch processing is already up to 50% cheaper than real-time API calls.

Batch processing prices per model

Prices shown per 1M tokens. Convoy fee is calculated as 1% of the combined input + output cost.

ProviderModelInput / 1MOutput / 1MConvoy Fee / 1M
OpenAIGPT-4o$2.50$10.00$0.125
OpenAIGPT-4o mini$0.15$0.60$0.0075
OpenAIGPT-4.1$2.00$8.00$0.100
OpenAIGPT-4.1 mini$0.40$1.60$0.020
OpenAIGPT-4.1 nano$0.10$0.40$0.005
OpenAIo3$2.00$8.00$0.100
OpenAIo3 mini$1.10$4.40$0.055
OpenAIo4 mini$1.10$4.40$0.055
AnthropicClaude Sonnet 4$3.00$15.00$0.180
AnthropicClaude Haiku 3.5$0.80$4.00$0.048
AnthropicClaude Opus 4$15.00$75.00$0.900
GoogleGemini 2.5 Pro$1.25$10.00$0.113
GoogleGemini 2.5 Flash$0.15$0.60$0.0075
GoogleGemini 2.0 Flash$0.10$0.40$0.005

Prices reflect batch API rates from each provider. Convoy fee = 1% of (input + output cost).

Ready to start saving?

Get started in minutes. No credit card required.

Try Convoy