Free Tier Terms
Last updated: November 5, 2026
1. What the free tier is
IteraCompute offers shared free model capacity only to eligible accounts under the current Auto access rules. Registration alone does not grant ongoing free access. See the Free page for the cutoff, retained recharge benefits and valid-plan eligibility. These Free Tier Terms, our Terms of Service and Acceptable Use Policy also apply.
2. Fair use and rate limits
- Free provides 30M tokens/month and 128K context. $10 cumulative net recharge unlocks 100M/month and 128K context; $50 unlocks 300M/month and 256K context. All three tiers allow one outstanding request per account on shared capacity that may be slow. These are recharge thresholds, not monthly fees.
Before the promotion ends, email verification unlocks the full 30M monthly Free allowance immediately. After the cutoff, free Auto access is limited to eligible existing recharge users and plan subscribers. Free, Starter and Pro each allow one queued or running request per account and use shared capacity that may be slow, shared across all keys and Auto. There is no daily token cap, and no call-count or UTC-date upgrade requirement. Monthly usage includes input and output; context limits, shared-capacity queues and abuse review still apply.
No. Purchased Auto tokens and monthly shared free benefits have separate quotas and usage ledgers. Plan Auto uses priority scheduling and its purchased period and contract limits. Requests use plan Auto first; uncovered requests use shared free benefits only while eligible, on shared capacity with possible queues and slower responses. Buying or renewing a plan does not reset shared free usage. When a plan expires, only users with qualifying pre-cutoff recharge retain shared free access.
- All API keys share input and output usage, including reasoning. Context includes input and requested maximum output. Allowances reset at 00:00 UTC on the first of each month and do not roll over. Requests reserve their maximum usage, then settle actual usage; requests exceeding remaining allowances are rejected without automatic paid overage.
- Free accounts may queue during busy periods. Recharge tiers receive priority with waiting time considered. Capacity is shared and best-effort; queue length and waiting time are bounded, and full or timed-out queues return HTTP 429 with Retry-After. Infrastructure failures may return HTTP 503.
- Recharge thresholds use completed USD principal less refunds, excluding fees and promotional grants. Recharge remains spendable API balance. Spending does not lower the tier; refunds may change it. Upgrades retain usage already consumed this month.
- No uptime SLA: free capacity carries no uptime, latency or support-response commitment. Production workloads should use serverless paid usage where offered, or reserved / dedicated capacity.
3. Abuse and multi-account limits
Device association, registration density, request timing and verification results may require additional verification. A shared IP alone never confirms an association: offices, campuses and households may share a network. Passing a human check alone does not prove separate ownership. Only after review confirms one subject is collecting multiple trials do those accounts share one free monthly allowance and one outstanding request on shared capacity that may be slow across all keys and Auto. Contact support for review or appeal.
- Abuse may lead to suspension: bulk registration, automated farming, quota resale, scraping, or other behavior that degrades shared capacity may result in rate-limit reduction, key revocation, account suspension or termination.
- Multiple-account limit circumvention prohibited: creating or coordinating multiple accounts, keys or devices to evade per-account or per-key limits is prohibited and treated as abuse.
- One natural person or entity is expected to operate within its published free quota; contact us if you need higher evaluation capacity.
4. Availability changes and paid overflow
Free models may change as capacity and upstream licensing allow. Unrecharged users' future model access, context limits and free quotas are not guaranteed. Recharged users retain the tier benefits defined below. Usage beyond the monthly allowance is rejected without automatic paid overage.
For eligible pre-cutoff recharge users, lifetime benefits mean retaining the monthly token allowance, context limit and queue priority of the Starter or Pro tier they have reached, including after a free-model upgrade or replacement. Spending the balance does not lower the tier; refunds may change it and abuse rules still apply. This does not freeze a model name, weights or precision, or promise unlimited usage, dedicated capacity or permanent service availability.
For users who recharged before the cutoff, cumulative net recharge of $10 qualifies for Starter: 100M tokens/month and 128K context. At $50, Pro provides 300M tokens/month and 256K context. Both receive queue priority. Recharging above $50 does not automatically add free-model benefits. Recharge remains spendable API balance; these thresholds are not monthly fees. Only principal from orders fulfilled before the cutoff counts; later recharges cannot raise these tiers. Refunds still reduce the qualifying net principal.
Model precision and quantization depend on the actual deployment and may change. A model name does not guarantee full precision or identical results across deployments. Try your own representative tasks before recharging; check correctness, tool calls and response time against your needs.
Auto runs on shared spare GPU capacity. Demand currently exceeds our available spare resources, so queues, slower responses and temporary unavailability are possible. Recharge tiers receive queue priority, but do not reserve GPUs or guarantee throughput, latency or an SLA. Thank you for understanding.
5. Relationship to other terms
In case of conflict between these Free Tier Terms and the general Terms of Service for free capacity, these Free Tier Terms prevail for free capacity. Enterprise agreements prevail for the reserved or dedicated services they cover.