Same prices as original providers
We pass through provider pricing at cost. No hidden fees, no per-request surcharges. Pay for exactly what you use.
$0
Platform fee
0%
API markup
500+
Models at cost
OpenAI
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| GPT-5.5 | $5.00 | $40.00 |
| GPT-5.4 | $2.50 | $20.00 |
| GPT-5.4 Pro | $30.00 | $180.00 |
| GPT-5.4 Mini | $0.40 | $1.60 |
| GPT-5.4 Nano | $0.10 | $0.40 |
| GPT-4.1 | $2.00 | $8.00 |
| o4-mini | $1.10 | $4.40 |
| o3 | $2.00 | $8.00 |
Anthropic
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| Claude Opus 4.7 | $15.00 | $75.00 |
| Claude Sonnet 4.6 | $3.00 | $15.00 |
| Claude Haiku 4.5 | $1.00 | $5.00 |
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| Gemini 3 Pro | $1.25 | $10.00 |
| Gemini 3 Flash | $0.30 | $2.50 |
| Gemini 3 Flash-Lite | $0.10 | $0.40 |
DeepSeek
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| DeepSeek V3.2 | $0.27 | $1.10 |
| DeepSeek R1.1 | $0.55 | $2.19 |
xAI
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| Grok 4 | $3.00 | $15.00 |
| Grok 4 Mini | $0.30 | $0.50 |
Mistral
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| Mistral Large 3 | $2.00 | $6.00 |
| Mistral Medium 3 | $0.40 | $2.00 |
| Mistral Small 3.2 | $0.10 | $0.30 |
Meta (via Groq, Together, etc.)
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| Llama 4 Behemoth | $0.90 | $2.70 |
| Llama 4 Maverick | $0.20 | $0.60 |
| Llama 4 Scout | $0.10 | $0.30 |
Prices shown per 1 million tokens. Actual costs per request depend on token usage. View all 500+ models →
How billing works
Prepaid credit balance
Fund your account via bank transfer. Credits are added in USD and invoiced in tenge at the current exchange rate.
Per-request deduction
Each API request deducts the exact provider cost from your balance based on input and output tokens consumed.
Real-time monitoring
Track spending per model, per key, and per day in your dashboard. Export usage reports for internal accounting.
Frequently asked questions
How does billing work?
Each API request is billed at the exact rate charged by the underlying provider, measured in tokens. Costs are deducted from your prepaid credit balance in real time. You can monitor usage and costs through the dashboard or the GET /api/v1/credits endpoint.
Is there a markup on API calls?
No. AI Router charges zero markup on API calls. The per-token prices you see are identical to what the providers charge directly. Our business model is based on B2B invoicing and service fees, not hidden API markups.
How do I add credits to my account?
AI Router is a B2B service. Credits are added via bank transfer invoice. Contact us with your desired credit amount, and we will issue an invoice in tenge (KZT). Credits are applied to your account in USD once payment is confirmed.
What happens if I run out of credits?
When your credit balance reaches zero, API requests will return a 402 Payment Required error. Your API keys and configuration remain intact — simply add more credits to resume service immediately.
Are there volume discounts?
For high-volume customers, we offer custom invoicing terms and dedicated support. Reach out via our contact form to discuss your usage needs.
Can I see costs per request?
Yes. Every request generates a generation ID. Use GET /api/v1/generation?id=<id> to see the exact token count, cost, and which provider handled the request. The dashboard also provides real-time usage analytics.
Ready to start?
Create your account and get your first API key in under a minute.