Pricing
Per-model API rates synced with our catalog—reclaimed silicon, vLLM throughput, and OpenAI-compatible routes. Subscription plans and top-ups bill in platform credits below.
Generative AI
USD · live catalog| Model | Provider | Input / 1M tok | Output / 1M tok | Pages / 1K | Endpoint |
|---|---|---|---|---|---|
Qwen3.5 122B A10BFLAGSHIP | Alibaba Cloud | $0.90/1M | $3.50/1M | — | /v1/chat/completions |
Qwen3.6 27B | Alibaba Cloud | $0.35/1M | $1.25/1M | — | /v1/chat/completions |
Qwen3.6 35B A3B | Alibaba Cloud | $0.25/1M | $0.95/1M | — | /v1/chat/completions |
Gemma4 31B | Google DeepMind | $0.45/1M | $1.50/1M | — | /v1/chat/completions |
Qwen3.5 9B | Alibaba Cloud | $0.10/1M | $0.35/1M | — | /v1/chat/completions |
Nemotron 3 Nano Omni 30B A3B | NVIDIA | $0.22/1M | $0.85/1M | — | /v1/chat/completions |
Gemma4 26B A4B | Google DeepMind | $0.20/1M | $0.75/1M | — | /v1/chat/completions |
OCR
USD · live catalog| Model | Provider | Input / 1M tok | Output / 1M tok | Pages / 1K | Endpoint |
|---|---|---|---|---|---|
Chandra OCRFEATURED | Cobble Labs | — | — | $1.25 | /v1/ocr |
GLM-OCR | Zhipu AI | — | — | $1.50 | /v1/ocr |
DeepSeek OCR2 | DeepSeek | — | — | $1.80 | /v1/ocr |
Nemotron OCR v2 | NVIDIA | — | — | $2.00 | /v1/ocr |
Embeddings
USD · live catalog| Model | Provider | Input / 1M tok | Output / 1M tok | Pages / 1K | Endpoint |
|---|---|---|---|---|---|
Nomic Embed 1.5FEATURED | Nomic AI | $0.025/1M | — | — | /v1/embeddings |
Granite Embedding 311M | IBM | $0.030/1M | — | — | /v1/embeddings |
Granite Embedding 97M | IBM | $0.015/1M | — | — | /v1/embeddings |
Qwen3 Embedding 0.6B | Alibaba Cloud | $0.020/1M | — | — | /v1/embeddings |
Qwen3 Embedding 8B | Alibaba Cloud | $0.06/1M | — | — | /v1/embeddings |
Subscriptions & credits
Plans include monthly credits and rate limits. Top-ups never expire.
Credit top-up
Purchase additional credits anytime. Applied immediately; they don't expire.
FAQ
How do monthly credits work?
Each plan includes a monthly credit allowance that renews at your billing cycle end. Credits are added when your subscription renews and expire at the end of that billing period.
What happens to unused credits?
Unused monthly credits expire at the end of your billing cycle and do not carry over. One-time top-up credits never expire.
How is inference cost calculated?
Per-model token, page, and endpoint rates are listed in the tables above. Failed requests are not charged where metering supports it.
Can I change plans?
Yes. Upgrade or downgrade through billing settings in your account. Changes typically take effect on the next cycle per Stripe rules.
What is the concurrent request limit?
It caps how many API requests can run in parallel per key. Higher tiers allow more throughput for bursty workloads.
Questions? Documentation · Platform