Free / Budget Mainstream models Direct connect ★ 3.9 / 5

RightCode Review: Pricing & Comparison

Coding-focused, top up from ¥1, clear documentation, Sonnet as low as ¥0.9/M

Last verified: 2026-07-04 · Visit official site →

Getting started for just ¥1

RightCode’s minimum top-up threshold is ¥1.

That number matters. ¥1 means:

  • Testing cost is essentially zero
  • You don’t need to pre-judge whether “this platform is worth spending tens of yuan on”
  • You can top up ¥1 on several platforms at once and directly compare latency, availability, and model quality

RightCode uses this extremely low bar to invite developers to judge it by evidence rather than by marketing copy.

Pricing: the real cost of Sonnet 4.6

RightCode’s disclosed price for Sonnet 4.6 is roughly ¥0.9 per million input tokens (about ¥4.5 per million output tokens).

Converted into real usage cost:

  • A code review with 2000 input tokens + 500 output tokens: about ¥0.0018 + ¥0.00225 ≈ ¥0.004
  • Running 1,000 such reviews a day: roughly ¥4/day, about ¥120/month

This price range is affordable for individual developers and independent teams, especially given RightCode’s focus on optimizing for coding scenarios.

Why go with a coding-focused platform

The practical difference between a general-purpose relay station and a coding-focused one:

General-purpose relay stations: cover every scenario, with generic documentation and examples like “write a poem” or “translate this passage”

Coding-focused (like RightCode):

  • Integration examples use real coding scenarios (Claude Code configuration, Cursor setup, API integration)
  • Node selection prioritizes the usage characteristics of coding tools (low latency over high throughput)
  • Issue feedback and technical support are more aligned with developer needs

For engineers who deeply integrate AI tools into their development workflow, a dedicated platform’s documentation quality is usually noticeably better than a general-purpose relay station’s.

Connecting Claude Code

# Method 1: environment variables
export ANTHROPIC_API_KEY="your RightCode API Key"
export ANTHROPIC_BASE_URL="https://api.rightcode.ai"  # check the official site for the actual address

claude "help me review this Python code"

# Method 2: claude CLI arguments
claude --api-key "your Key" --base-url "https://api.rightcode.ai" "..."

RightCode’s documentation includes dedicated guidance for various Claude Code configuration scenarios, cutting down on trial-and-error time.

Who it fits

  • Developers who want a low-cost way to test coding-focused AI relay stations
  • Users doing code work primarily with Claude Sonnet
  • Independent developers who are price-sensitive but demanding about coding tools

Information verified 2026-07-04. Pricing is subject to RightCode’s official site in real time.


Related Reviews

  • Inworld Router: 200+ models at 0% markup, deeply optimized for gaming/entertainment AI scenarios, intelligent routing by request complexity
  • MoleAPI: a single API unifying GPT-4o/Claude/Gemini, <50ms direct-connect latency, OpenAI format compatible, free credit for new signups
  • GGWK1: aggregates the three major OpenAI/Claude/Gemini families, exchange rate ¥0.6-1/USD, domestic direct connect
  • hvoy.ai: a relay-station directory and comparison hub, not a relay station itself — helps you find the right relay station

Quick facts

Pricing modelPay-as-you-go; ¥1 minimum top-up; Sonnet 4.6 roughly ¥0.9 per million input tokens
Model coverageFull Claude lineup plus mainstream coding models, dedicated coverage for coding scenarios
Latency / SLADomestic direct connect, low latency
Mainland direct connectDirect connect
Best forDevelopers
Referral programNo public affiliate program found.

Pros

  • ¥1 minimum top-up: an extremely low entry bar, good for developers who want to try before deciding
  • Coding-focused positioning with clear documentation and integration examples targeted at code scenarios
  • Sonnet 4.6 as low as ¥0.9 per million tokens — strong price competitiveness

Cons

  • Low platform visibility, with few independent reviews or community discussions
  • Narrow positioning means no clear advantage outside coding scenarios
  • Long-term stability still needs ongoing verification

Compare more AI API relays

See the full comparison board — filter by price tier, model coverage, and mainland direct-connect status.

Back to the comparison board →