Gemini CLI comparison

Gemini CLI Proxy Providers

This page collects providers that list Google or Gemini model access and may be relevant when testing Gemini CLI, Gemini API keys, or Google-compatible routing. Verify the exact Gemini model name, authentication method, and Base URL behavior before putting a provider into daily coding work.

gemini cli 中转站 gemini cli proxy gemini api 中转站 gemini cli base url

Quick filters

By model

Site list(16)

kukuai logo

kukuai

Public model pricing is shown per million tokens. Examples include gpt-5.4-mini at ¥0.1950 input / ¥0.8325 output, gpt-5.3-codex at ¥0.3300 input / ¥3.3000 output, claude-sonnet-4-6 at ¥0.8580 input / ¥3.9600 output, and gemini-3.1-pro at ¥1.5400 input / ¥9.2400 output. The packages page lists seven one-time plans priced at ¥6.8, ¥13.6, ¥68, ¥136, ¥272, ¥340, and ¥680, including ¥8, ¥15, ¥80, ¥149, ¥300, ¥374, and ¥800 in site credit respectively. The first six are valid for 30 days, while the ¥680 plan is valid for 90 days; official-equivalent credit varies by model.

$0.01 ≈ $1¥6.850
DeepKey logo

DeepKey

Top-ups are settled at ¥1 = $1 credit, with a ¥5 minimum. Model usage is charged by group multipliers or fixed prices. The comparable cost is recorded from the gpt group, mainly Pro accounts, at 0.2x, or about ¥0.20 per $1 list-price usage. Stable groups recorded here include: gpt 0.2x, gpt-enterprise 0.6x, gpt-azure 1.2x, gpt-image 0.1x; cx2cc 0.2x; gemini 0.3x, gemini-t3 1.8x; claude 0.4x, claude-anti 0.3x, claude-copilot 0.5x, claude-free 0.25x, claude-pro 1.2x, claude-ai / claude-api 3x, claude-aws-platform 2.2x, claude-max 1.8x, claude-max-any-client 1.6x, claude-kiro 0.45x, and claude-windsurf 0.35x. Limited-time, special-price, discount, sale, and out-of-stock-prone groups are excluded.

28.93K$0.02 ≈ $1¥515
FoxCode logo

FoxCode

Usage cards do not expire; the purchase page shows 100M credits for ¥35, 500M for ¥135, 1B for ¥265, and 2B for ¥468. Different model/channel conversion ranges are shown: official CC full-power ¥0.98-2.8 = $1, Turbo ¥1.3-3.5 = $1, Super special CC ¥0.492-1.4 = $1, Ultra special CC ¥0.246-0.7 = $1, Codex channel CC ¥0.123-0.35 = $1, AWS special CC ¥0.03-0.087 = $1, Gemini official ¥0.123-0.35 = $1, Codex full-power official ¥0.123-0.35 = $1, and GPT-Image official ¥0.05-0.07 per image.

177.65K$0.03 ≈ $1¥358
SSSAiCode logo

SSSAiCode

PayGO plans charge against USD credit and the balance never expires. Top-up tiers include ¥100 for $100, ¥200 for $200, ¥500 for $500, ¥1000 for $1000, and ¥5000 for $5000, so the credited balance is about ¥1 = $1. Actual usage cost depends on the provider-group multiplier: the default Codex Team/Plus mixed PayGO pool is 0.4x, so $1 of list-price usage deducts about $0.4 credit, or about ¥0.4 effective cost; the pure Pro pool is 1.2x. Claude monthly plans include ¥249/mo, ¥498/mo, ¥1000/mo, and ¥2000/mo tiers with daily and weekly quota resets. Overseas Invoice support only.

52.21K$0.05 ≈ $1¥1006
APIKey logo

APIKey

Top-ups credit the account at ¥1 = $1 platform credit and the balance never expires. Actual usage cost depends on the group multiplier: the screenshot shows Codex Pro (Codex-only) at 0.6x and Codex Pro (external-use edition) at 0.7x. With the Codex-only channel, $1 of list-price usage deducts about $0.6 credit, or about ¥0.60 effective cost. Official prices are converted with $1 = ¥7; top-up tiers include ¥30, ¥50, ¥100, up to ¥5000.

260.43K$0.08 ≈ $1¥303
Ai Go Code logo

Ai Go Code

The OpenAI / Codex provider cards show Codex at ¥0.7 per $1 and Codex Pro at ¥0.9 per $1. Usage-based flexible credits include a new-user ¥5 for $5 tier and ¥50 for $50 and above, with credits valid until used. Subscription plans: Standard ¥399/4 weeks with $110 weekly credit, Premium ¥899/4 weeks with $260 weekly credit, Professional ¥1799/4 weeks with $530 weekly credit, and an Enterprise plan at ¥9999/4 weeks that requires contacting support.

102.28K$0.1 ≈ $1¥5

Related guides

Related topics

FAQ

Common questions

What should I check before using Gemini CLI with a proxy?

Confirm whether the provider supports Google or Gemini models, whether it expects a Gemini API key or an OpenAI-compatible key, the exact Base URL path, model names, streaming behavior, and any special headers.

Does Gemini CLI use the same setup as Claude Code or Codex?

No. Gemini CLI has its own authentication flow. Google documents sign-in with Google, Gemini API key, and Vertex AI paths, while Claude Code and Codex use different environment variables and protocols.

Why do some AI API aggregators appear on this page?

Aggregators can appear here when their public data lists Google or Gemini model access. Treat the page as a compatibility shortlist, then verify Gemini CLI behavior directly with a small test.