Reviews

Dec 15, 2025 · Pricing & Costs

SparkCode Pricing: Input and Output Token Rates

GPT-4o input costs ¥2 per million tokens on SparkCode, with output at ¥15 per million — roughly 60% cheaper than OpenAI's direct China pricing.

Dec 15, 2025 · Reviews

100% uptime and 454ms measured latency from Beijing — SparkCode is one of the fastest relay stations I've tested for Chinese developers who need.

Dec 15, 2025 · Model Coverage

SparkCode lists 2 models: GPT-4o and Claude 3.5 Sonnet. That’s a tight roster — no Gemini, no Kimi, no GLM, despite what the platform’s broader.

Dec 15, 2025 · Comparisons

SparkCode is 100% uptime for Chinese users versus OpenRouter’s frequent timeouts from mainland China — and on Claude 3.5 Sonnet at 50M tokens.

Dec 10, 2025 · Pricing & Costs

Shenma AI's free plan (0 yuan/month) is its clearest advantage. Its actual cost still matters: DeepSeek V3 input is about ¥2 per million tokens.

Dec 10, 2025 · Reviews

Shenma AI Review 2026 review records dated pricing, supported models, API limits, and author-reported reliability notes for solo developers.

Dec 10, 2025 · Model Coverage

650+ model variants claimed; Claude 4.x and GPT-5.x are the headline models. Model-by-Model Breakdown Shenma AI targets developers who want.

Dec 10, 2025 · Comparisons

Shenma AI claims 650+ model variants and local payment support, but its 94% uptime lags behind OpenRouter's 99.5%+ average — a gap that matters.

Dec 05, 2025 · Pricing & Costs

Claude Code input costs ¥1 per million tokens on RightCode — that is ¥4.95/1M, roughly 1/6 of the direct API price from Anthropic. Pricing.

Dec 05, 2025 · Model Coverage

RightCode Supported Models review records dated pricing, supported models, API limits, and author-reported reliability notes for solo developers.