Gemini CLI Proxy Providers

Claude averages 5.9% of official pricing, as low as 4.6% of official pricing; GPT averages 8.3% of official pricing, as low as 3.9% of official pricing; Gemini averages 15.5% of official pricing, as low as 15.5% of official pricing; Grok averages 3.2% of official pricing, as low as 3.2% of official pricing. Models are billed per 1M tokens; top-ups start at ¥6.8, and seven one-time plans range from ¥6.8 to ¥680. The first six are valid for 30 days and the ¥680 plan for 90 days.

Claude averages 14.8% of official pricing, as low as 12% of official pricing; GPT averages 22.3% of official pricing, as low as 8% of official pricing; Gemini averages 25% of official pricing, as low as 25% of official pricing; Grok averages 6% of official pricing, as low as 6% of official pricing. Usage is billed per 1M tokens. Top-ups credit $1 of platform balance per ¥1, with a ¥5 minimum.

Claude averages 1.2% of official pricing, as low as 1.2% of official pricing; GPT averages 0.8% of official pricing, as low as 0.4% of official pricing; Gemini averages 1.8% of official pricing, as low as 1.8% of official pricing; Grok averages 0.6% of official pricing, as low as 0.6% of official pricing; DeepSeek averages 58.8% of official pricing, as low as 58.8% of official pricing; Kimi averages 57.7% of official pricing, as low as 57.7% of official pricing. Usage is billed by token, top-ups start at CNY 10, and subscriptions are also available. The current lowest price comes from the Codex promotional group and may change.

Claude averages 27.7% of official pricing, as low as 16.8%; GPT averages 18% of official pricing, as low as 18%; Gemini averages 18% of official pricing, as low as 18%. The lowest rates use Claude-Trial, GPT dedicated, and Gemini special-rate groups; Claude-Trial may be rate-limited or less stable. Billing is token-based with subscription plans, a ¥20 minimum top-up, and $1 in signup credit.

Claude averages 13.6% of official pricing, as low as 11.4% of official pricing; GPT averages 11.9% of official pricing, as low as 7.1% of official pricing; Gemini averages 14.3% of official pricing, as low as 14.3% of official pricing; Grok averages 14.3% of official pricing, as low as 14.3% of official pricing; DeepSeek averages 36.6% of official pricing, as low as 36.6% of official pricing; Kimi averages 47.6% of official pricing, as low as 47.6% of official pricing. The page converts official pricing at $1 = ¥7. Top-ups credit $1 of platform balance per ¥1, start at ¥50, and balances do not expire.

Claude averages 22% of official pricing, as low as 19.6% of official pricing; GPT averages 15.3% of official pricing, as low as 8.1% of official pricing; Gemini averages 21% of official pricing, as low as 12.7% of official pricing; DeepSeek averages 30.9% of official pricing, as low as 30.9% of official pricing; Kimi averages 76.1% of official pricing, as low as 76.1% of official pricing. Billing uses USD and tokens, with a $5 minimum top-up, no monthly fee or subscription, and non-expiring credits; model discounts adjust with upstream costs.

Claude averages 43.1% of official pricing, as low as 35% of official pricing; GPT averages 40% of official pricing, as low as 10% of official pricing; Gemini averages 63.3% of official pricing, as low as 40% of official pricing; DeepSeek averages 32.2% of official pricing, as low as 31.8% of official pricing; Kimi averages 90% of official pricing, as low as 90% of official pricing. The public model catalog uses token-based billing; top-ups start at $1 and credits do not expire.

Claude averages 24.7% of official pricing, as low as 24% of official pricing; GPT averages 14.2% of official pricing, as low as 7% of official pricing; Gemini averages 80% of official pricing, as low as 80% of official pricing; Grok averages 1.6x official pricing, as low as 1.6x official pricing; DeepSeek averages 33% of official pricing, as low as 33% of official pricing. Usage is billed per token in USD per 1M tokens, with no subscriptions or account tiers, and balances do not expire. Stripe top-ups start at $3 and USDT top-ups at $15.

Claude averages 68.6% of official pricing, as low as 65% of official pricing; GPT averages 65% of official pricing, as low as 65% of official pricing; Gemini averages 63.5% of official pricing, as low as 44% of official pricing; DeepSeek averages 51.5% of official pricing, as low as 50.8% of official pricing; Kimi averages 1x official pricing, minimum 1x. USD top-ups support token-, usage-, request-, image-, or second-based billing, with a $1 minimum top-up.

Claude averages 52.5% of official pricing, as low as 50%; GPT averages 62.5% of official pricing, as low as 50%; Grok averages 100% of official pricing, as low as 100%; Kimi averages 98.1% of official pricing, as low as 98.1%. Codex and Claude Code prefer the public cli2api resource section and fall back to default Level 0 when no valid resource price is available; Gemini, Grok, DeepSeek, and Kimi use default Level 0 rates without cumulative top-up requirements. Other Level 1-3 qualified rates are excluded. Models are billed in USD per 1M tokens. Online top-ups are available at $5, $10, $25, $100, and $500, while manual top-ups support invoices, contracts, large purchases, and custom services.

Claude averages 98% of official pricing, as low as 50%; GPT averages 150% of official pricing, as low as 100%; Gemini averages 53.3% of official pricing, as low as 10%. Models are billed in USD per 1M tokens. PAYGO top-ups start at ¥20 with ¥1 credited as $1 and balances do not expire; monthly plans cost about ¥0.31-¥0.44 per $1 of periodic credit, reset daily, and do not roll over.

The structured reference uses the normal custom top-up rate of ¥0.66 per $1 credit, with a $1 minimum; fixed tiers offer bulk discounts but are excluded from this reference. Models are also billed by group multipliers, including Claude Code 5x, Codex 0.8x, and gemini-cli 1.5x.