Billing
Pricing
Pay only for what you use — per 1M tokens, no subscriptions.
Pricing
TL;DR
No subscriptions. No monthly limits. Add credits to your wallet and pay per token used.
Simple, Usage-Based Pricing
Pay only for the tokens and requests you use. No subscriptions, no monthly limits, no tiers. Top up your wallet and start building.
Model Pricing
| Model | Category | Input | Output |
|---|---|---|---|
assisters-chat-v1 | Chat | $0.10 / 1M tokens | $0.20 / 1M tokens |
assisters-vision-v1 | Vision | $0.05 / 1M tokens | $0.10 / 1M tokens |
assisters-code-v1 | Code | $0.10 / 1M tokens | $0.20 / 1M tokens |
assisters-embed-v1 | Embeddings | $0.01 / 1M tokens | — |
assisters-rerank-v1 | Reranking | $0.02 / 1M tokens | — |
assisters-moderation-v1 | Moderation | $0.05 / 1M tokens | — |
assisters-whisper-v1 | Speech-to-Text | $0.006 / min audio | — |
assisters-tts-v1 | Text-to-Speech | $15.00 / 1M chars | — |
assisters-image-v1 | Image Generation | $0.020 / image | — |
Embeddings, reranking, and moderation use a unified rate (no separate input/output split).
How Billing Works
- Top up your wallet — minimum $5, no expiry on credits
- Make API requests — credits deducted per request based on token usage
- Monitor usage — real-time dashboard shows spend per model and API key
- Set spending controls — optional monthly spend cap per key
Rate limit: 60 requests per minute (RPM) per API key.
Cost Calculator
# Estimate cost for a chat completion
input_tokens = 1000
output_tokens = 500
input_cost = (input_tokens / 1_000_000) * 0.10 # $0.000100
output_cost = (output_tokens / 1_000_000) * 0.20 # $0.000100
total = input_cost + output_cost # $0.000200
print(f"Cost: ${total:.6f}")