Skip to main content

​
Chat Completions Pricing

Pay per token for chat completions.
ModelInput TokensOutput Tokens
tzafon.sm-1$0.20 / 1M tokens$0.30 / 1M tokens
tzafon.northstar-cua-fast$0.30 / 1M tokens$0.50 / 1M tokens
See Chat Completions API for usage details and code examples.

​
Compute Pricing

Pay only for what you use, billed per second.

​
Pricing Tiers

As your usage grows, you automatically qualify for lower rates.
TierQualificationCPUMemory
Tier 1Default$0.38/core-hr$0.095/GiB-hr
Tier 2$2k lifetime spend$0.30/core-hr$0.076/GiB-hr
Tier 3$10k lifetime spend$0.23/core-hr$0.057/GiB-hr
Tier 4$25k lifetime spend$0.15/core-hr$0.038/GiB-hr
Tier 5Contact usCustomCustom
Normal workloads are equivalent to circa $0.075/hr of browser usage (Tier 1). Tier upgrades are automatic and apply to all future usage.

​
Minimum Allocation

  • 0.125 cores minimum per container

​
How Billing Works

  • CPU: Based on actual core usage (2 cores at 100% = 2 core-seconds/second)
  • Memory: Based on actual memory used, not allocated
  • Granularity: Per-second billing

​
Tips to Optimize Costs

Always call terminate() when finished to stop billing. Use context managers for automatic cleanup.
with client.create(kind="browser") as computer:
    # Your automation
    pass  # Auto-terminates

​
Questions?

Instances automatically terminate after a configurable period inactivity to prevent unexpected charges.
No setup fees, no monthly minimums. Pay only for what you use.
Contact us at support@tzafon.com for pricing questions.