BestRelay pay-as-you-go for Gemini CLI at $0.2778 input
BestRelay forwards each request to the named model with no silent substitution
BestRelay is an independent API relay that forwards every request to the model provider under the exact model name the caller wrote. The model you name is the model that answers, and nothing is quietly swapped for a cheaper tier. The curated line-up holds 20 public models, each listed under its own name with four prices where applicable: input, output, cache write, and cache read. When a provider retires a model identifier, BestRelay delists it so the catalogue stays current. This design means a developer who selects Claude Sonnet 5.5 receives Claude Sonnet 5.5, and a developer who selects GPT-6.1 Sol receives GPT-6.1 Sol, with the same certainty for every other model on the list.
Claude models are served only to the official Claude Code and Claude Desktop clients, version 2.1.285 or newer. They do not work in Cursor, Cherry Studio, Cline, OpenCode, any SDK, or cURL. Those tools, like Codex, pair only with GPT, DeepSeek, Kimi, GLM, Qwen, and Grok. Gemini models use only their native protocol through Gemini CLI or direct generateContent calls and are not OpenAI-compatible. A client needs two settings: the address and a key created under API keys in the dashboard. An account can hold several keys, each can be voided at any time, and every call appears in the usage records with its model, tokens, and charge.
BestRelay charges once per call from the tokens the provider reports at rate card prices
Billing on BestRelay is prepaid pay-as-you-go with no monthly fee, no subscription, and no minimum spend. Each call is charged once, after it ends, from the tokens the provider reports, at the rate card prices. Nothing is held in advance. Requests the provider rejects are recorded at zero, and when the provider cannot be reached nothing is charged. The user-written text of requests is kept for 30 days to review abuse and settle billing questions; system prompts and model replies are not stored.
Concrete rates from the sheet illustrate the structure. For Claude Sonnet 5.5 the prices per 1,000,000 tokens are input $1.39, output $7.01, cache write $1.74, and cache read $0.0944. The official list price for the same model is input $2, output $10, and cache read $0.1. For GPT-6.1 Sol the prices are input $0.2083, output $1.11, and cache read $0.0431, while the official list price is input $2, output $10, and cache read $0.1. For Gemini 2.5 Flash the prices are input $0.2778, output $2.08, cache write $0.2778, and cache read $0.0264. These figures are the basis for every charge BestRelay applies.
BestRelay worked examples show daily and monthly cost differences for Sonnet 5.5 and GPT-6.1 Sol
For example, a day of 500,000 input and 100,000 output tokens on Claude Sonnet 5.5 costs $1.40 on BestRelay, and 22 such days cost $30.71. With 350,000 of the input read from cache the day costs $0.94. At the official list price the same day is $2.00, the 22 days $44.00, and the cached day $1.33; the difference on the day is $0.60 and on the 22 days $13.29. For example, a day of 500,000 input and 100,000 output tokens on GPT-6.1 Sol costs $0.22 on BestRelay, and 22 such days cost $4.74. With 350,000 of the input read from cache the day costs $0.16. At the official list price the same day is $2.00, the 22 days $44.00, and the cached day $1.33; the difference on the day is $1.78 and on the 22 days $39.26. The free credit alone covers about 1.6 million GPT-6.1 Sol input tokens.
Other models on the sheet follow the same pattern. Claude Fable 5 is priced at input $4.17, output $20.97, cache write $5.14, and cache read $0.3472, against an official list of input $10, output $50, and cache read $1. Claude Opus 5.5 is input $1.74, output $8.13, cache write $2.01, and cache read $0.0778, with an official list of input $4, output $20, and cache read $0.2. DeepSeek V4 Pro lists input $1.53, output $4.58, and cache read $0.0514. Kimi K3 shows input $1.39, output $7.01, and cache read $0.1389. Each entry lets a developer estimate spend before the first call.
BestRelay tops up through Stripe in fixed amounts and refunds unused credit within 13 days
Top-ups on BestRelay go through Stripe checkout in these amounts: $1.39, $6.94, $13.89, $27.78, $69.44, and $138.89. Each new account opens with $0.35 of credit. Unused credit can be refunded on request within 13 days of the top-up, less what was consumed and any payment-processor fees. Gift credit and commission cannot be refunded. The referral program pays 18% of the top-ups of people who joined through your link, and 4% of the top-ups of the people they invited. Commission can be moved into the balance, or withdrawn to Alipay from $20.83. As an example, on an invited member's top-up of $13.89, the two commissions are $2.50 and $0.5556.
Limits are straightforward: 120 requests a minute on one key, and 8 calls in flight on one account. These caps apply uniformly across the line-up. The usage records show every call with its model, tokens, and charge, so reconciliation is direct. No monthly fee exists, and no period passes are sold; the only statement on that subject is that there is no monthly fee.
BestRelay keeps request text for 30 days and stores no system prompts or model replies
Privacy on BestRelay means the user-written text of requests is kept for 30 days to review abuse and settle billing questions. System prompts and model replies are not stored. This retention window is the same for every model on the relay, whether it is Claude Haiku 4.5 at input $0.4167, output $2.01, cache write $0.4861, and cache read $0.0333, or Grok 4.7 at input $0.625, output $1.94, and cache read $0.1389, or GLM-5.3 at the same input $0.625, output $1.94, and cache read $0.1389. The dashboard shows keys, usage records, and the balance without exposing the content of conversations.
Connecting a client takes the address and a key from the dashboard; details are in the docs. The service delivers the model you name, bills once per call at the published rates, and returns the provider's tokens as the basis for the charge. Try BestRelay and see the difference in your next coding session.