Pricing
All prices are pay-per-use with no minimums, commitments, or hidden fees.Inference
ASG supports a wide range of AI models. Pricing varies by model:| Model | Input | Output |
|---|---|---|
| openai/gpt-4o-mini | $0.15/1M tokens | $0.60/1M tokens |
| openai/gpt-4.1 | $2.00/1M tokens | $8.00/1M tokens |
| openai/gpt-5.2 | $3.00/1M tokens | $15.00/1M tokens |
| anthropic/claude-sonnet-4 | $3.00/1M tokens | $15.00/1M tokens |
| google/gemini-2.5-pro | $1.25/1M tokens | $10.00/1M tokens |
| deepseek/deepseek-r1 | $0.55/1M tokens | $2.19/1M tokens |
Exact pricing depends on the upstream model provider. Use the Quote to see the exact cost before execution.
Sandbox
| Resource | Rate |
|---|---|
| Execution time | $0.0001/sec |
| Package install | Included |
Serverless
Coming Soon — Serverless execution is on the roadmap. See Roadmap.
GPU
Coming Soon — GPU provisioning is on the roadmap. See Roadmap.
Pricing FAQ
Are there any hidden fees?
Are there any hidden fees?
What's the minimum spend?
What's the minimum spend?
No minimum spend. Pay only for what you use.
How do I know the price before running?
How do I know the price before running?
Every tool call returns a Quote with the exact price before any payment is required.