RightCode: the short verdict
Bottom line: RightCode is worth testing when your workflow is coding-heavy and the low entry cost matters more than broad model coverage. Treat the 96.0% uptime figure as an author-reported snapshot, not an SLA.
What I checked
The useful question is not whether RightCode lists Claude and Codex, but whether its price, model coverage, and observed reliability fit a repeatable coding workflow. The figures below come from the recorded review data; the provider has not supplied independent verification here.
Reliability and limits
The page records 96.0% uptime and a 100,000-token context limit. These are useful comparison signals, but there is no stated monitoring window, regional test matrix, or model-specific SLA, so they should not be read as a guarantee.
| Item | Details |
|---|---|
| safety score | ⭐⭐⭐ (3/5) |
| monthly fee | $0 |
| Uptime | 96.0% |
| Max context | 100000 tokens |
| Models supported | Claude Code, OpenAI Codex, Claude 3.5 Sonnet |
Pricing
$0/mo · Free trial. The headline advantage is the low minimum commitment: the recorded note lists GPT-5.5/Codex at ¥1 input and ¥6 output per 1M tokens. Check the provider page before paying because relay pricing and availability can change.
Who should use it?
RightCode is a reasonable trial for a solo developer who mainly needs coding models, wants to start with a small top-up, and can tolerate a narrower catalogue. It is a weaker fit if you need broad GPT/Gemini coverage, a published SLA, or a mature refund policy.
FAQ
Is RightCode a general-purpose model marketplace? No. The recorded catalogue is coding-focused, with Claude Code, OpenAI Codex, and Claude 3.5 Sonnet listed.
Can I treat the uptime number as a guarantee? No. It is an author-reported figure without a published monitoring method or SLA.
What should I verify before funding an account? Confirm the current model list, input/output prices, minimum top-up, refund terms, and whether the endpoint works from your intended network.
What is the main alternative? OpenRouter is the broader comparison point when model variety and provider choice matter more than the lowest starting cost.
Pros & Cons
✅ Lowest price for Codex among all relays, GPT-5.5 at ¥1(input)6(output)/1M tokens — excellent value, Minimal top-up requirement: ¥1+, Fast API response, well-documented ❌ Claude groups may occasionally mix channels, No refund policy on some plans, Limited to coding-focused models
Alternatives
Data provenance: any figures from hands-on checks are author-reported and tested on the recorded date. Independent verification is unavailable unless a source is linked.
