Starter
$10.00 /mo
Monthly per workspace
- Included scope
- Bounded five-hour/weekly chat usage
RunInfra
● Identity checkedHosted open-model inference for agents · Official-source review 2026-10-09
RunInfra provides hosted open models through OpenAI- and Anthropic-compatible APIs. It offers prepaid token billing and workspace coding plans, with session-aware caching and separately reported cached-token usage.
- Category
- Hosted open-model inference for agents
- Free access
- $1 introductory Model API test credit. Paid coding plans include limited, slower Standby at limits; no independent ongoing free subscription established.
- API access
- OpenAI chat completions and Anthropic Messages compatibility; coding-agent setup CLI. Chat plans cover eligible workspace keys; image/audio remain pay as you go.
Is RunInfra right for you?
A good fit for
Relevant to developers measuring open-model compatibility and real billed usage for their own workloads.
Before you choose
Top-ups start at $5 and expire after one year. Coding Starter $10/month: $1.11/5h and $2.77/week; Pro $29: $3.23/$8.08; Team $99: $10.98/$27.46. Both windows must have room; monthly usage estimates do not roll over. Standby caps $0.20/$0.58/$1.98 daily and can pause. Nemotron 3.5 input/cached/output $0.05/$0.01/$0.15 per million tokens; other model rates differ and promotions expire. Cache hits are best effort and displayed speed/cache statistics are provider measurements. Enterprise SLA/compliance terms differ from self-serve. No key, setup or inference request tested.
Workflow and handoff
Inspect model limits and retention terms, test non-sensitive SDK requests, and set credit caps before enabling fallback spending.
Pricing and practical limits
Top-ups start at $5 and expire after one year. Coding Starter $10/month: $1.11/5h and $2.77/week; Pro $29: $3.23/$8.08; Team $99: $10.98/$27.46. Both windows must have room; monthly usage estimates do not roll over. Standby caps $0.20/$0.58/$1.98 daily and can pause. Nemotron 3.5 input/cached/output $0.05/$0.01/$0.15 per million tokens; other model rates differ and promotions expire. Cache hits are best effort and displayed speed/cache statistics are provider measurements. Enterprise SLA/compliance terms differ from self-serve. No key, setup or inference request tested.
Review method
Official product evidence reviewed on 2026-10-09; product artwork inspected visually. No hands-on vendor application test was performed. Application performance, security claims and plan enforcement were not independently tested.
What it can do
Features & capabilities
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Product workflow | RunInfra provides hosted open models through OpenAI- and Anthropic-compatible APIs. It offers prepaid token billing and workspace coding plans, with session-aware caching and separately reported cached-token usage. | Facts sourced | 2026-10-09 |
| Pricing and restrictions | Top-ups start at $5 and expire after one year. Coding Starter $10/month: $1.11/5h and $2.77/week; Pro $29: $3.23/$8.08; Team $99: $10.98/$27.46. Both windows must have room; monthly usage estimates do not roll over. Standby caps $0.20/$0.58/$1.98 daily and can pause. Nemotron 3.5 input/cached/output $0.05/$0.01/$0.15 per million tokens; other model rates differ and promotions expire. Cache hits are best effort and displayed speed/cache statistics are provider measurements. Enterprise SLA/compliance terms differ from self-serve. No key, setup or inference request tested. | Facts sourced | 2026-10-09 |
Understand the total cost
RunInfra pricing & plans
Pro
$29.00 /mo
Monthly per workspace
- Included scope
- Higher bounded chat usage
Team
$99.00 /mo
Monthly per workspace
- Included scope
- Shared bounded chat usage
Prepaid Model APIs
Not listed
Top-ups from $5; one-year expiry
- Included scope
- Per-token billing; model-dependent rates
Alternatives to RunInfra
View all ↗
Token HarborToken Harbor exposes several model providers through one OpenAI-compatible API with free routes and paid usage passes. Users choose model IDs, review usage allowances and decide whether calls pause or continue from a paid balance at the pass limit.
Explore tool
DialDial gives agents phone numbers and voice or messaging access through a unified API. It offers self-hosted and managed call modes, signed webhooks and SDK/MCP integration.
Explore tool
AurikoAuriko provides an OpenAI-compatible model gateway with provider routing, fallback, key orchestration and cost analytics. It supports user-supplied or platform keys and configurable objectives such as cost, latency and data policy.
Explore toolThe practical questions
Frequently asked questions
Was the application hands-on tested?
No. This listing is based on dated official-source evidence and a visual artwork check. Unconfirmed costs and restrictions are identified explicitly.
What is RunInfra used for?
RunInfra provides hosted open models through OpenAI- and Anthropic-compatible APIs. It offers prepaid token billing and workspace coding plans, with session-aware caching and separately reported cached-token usage.
Does RunInfra have a free plan?
$1 introductory Model API test credit. Paid coding plans include limited, slower Standby at limits; no independent ongoing free subscription established.. This record does not confirm an ongoing free plan.
How much does RunInfra cost?
The listed monthly price is $10.00 USD at monthly billing. See the plan cards for entitlements, billing commitments and seat minimums.
Can I use RunInfra through an API?
OpenAI chat completions and Anthropic Messages compatibility; coding-agent setup CLI. Chat plans cover eligible workspace keys; image/audio remain pay as you go.. API access and subscription access may have different terms; consult the linked sources.
What should I check before choosing it?
Top-ups start at $5 and expire after one year. Coding Starter $10/month: $1.11/5h and $2.77/week; Pro $29: $3.23/$8.08; Team $99: $10.98/$27.46. Both windows must have room; monthly usage estimates do not roll over. Standby caps $0.20/$0.58/$1.98 daily and can pause. Nemotron 3.5 input/cached/output $0.05/$0.01/$0.15 per million tokens; other model rates differ and promotions expire. Cache hits are best effort and displayed speed/cache statistics are provider measurements. Enterprise SLA/compliance terms differ from self-serve. No key, setup or inference request tested.
Price history
No retained pricing changes yet. A current price alone does not establish a historical trend.
How this profile is supported
Official product information
Current official product source read individually; product artwork inspected visually.
Read original source ↗Pricing review
Official pricing and billing restrictions read individually.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.