BestRelay relay service setup with Gemini CLI and 20 curated models

BestRelay forwards each request to the model provider under the name you wrote

BestRelay is an independent API relay, and its central promise is plain: the model you name is the model that answers. Each request is forwarded to the model provider under the model name the caller wrote, so nothing is quietly swapped for a cheaper tier. That makes a single BestRelay balance a practical replacement for juggling several provider accounts across Claude, GPT and Gemini. The line-up is curated and holds 20 public models, each listed under its own name with four prices: input, output, cache write and cache read. When a provider retires a model id, BestRelay delists it, so the card does not linger on names that no longer answer.

An account can hold several keys, and each key can be voided at any time. Every call appears in the usage records with its model, tokens and charge, which makes the arithmetic checkable rather than a matter of trust. On privacy, the user-written text of requests is kept for 30 days to review abuse and settle billing questions, while system prompts and model replies are not stored. Connecting a client takes two settings: the address and a key created under API keys in the dashboard. The details live in the BestRelay docs, and the address itself is not printed in this article. Because routing follows the written model name, the same key can carry a Claude request, then a GPT request, then a Gemini request.

BestRelay bills once per finished call from the tokens the provider reports

Billing at BestRelay is prepaid pay-as-you-go. There is no monthly fee, no subscription and no minimum spend. Each call is charged once, after it ends, using the tokens the provider reports and the prices on the rate card. Nothing is held in advance, so an unused balance is not sitting in a holding pattern. Requests the provider rejects are recorded at zero, and when the provider cannot be reached nothing is charged. That is a small courtesy with a large practical effect: a failed call does not quietly eat into the balance you built up for real work.

Each new account opens with $0.35 of credit, which is enough to send a few requests and read the usage records before committing anything further. Top-ups are handled through Stripe checkout in set amounts of $1.39, $6.94, $13.89, $27.78, $69.44 and $138.89. 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, which is worth knowing before you move referral earnings into your balance. The free credit alone covers about 1.6 million GPT-6.1 Sol input tokens, so an opening balance is not a token gesture but a working allowance.

The BestRelay card lists Claude prices per million tokens, line by line

Read the Claude entries as they stand. Claude Fable 5 input $4.17, output $20.97, cache write $5.14, cache read $0.3472, against an official list price of input $10, output $50 and cache read $1. Claude Fable 5.1 input $4.10, output $20.42, cache write $5.00, cache read $0.2083, against an official list price of input $10, output $50 and cache read $0.25. Claude Haiku 4.5 input $0.4167, output $2.01, cache write $0.4861, cache read $0.0333, against an official list price of input $1, output $5 and cache read $0.1. Claude Opus 5 input $2.29, output $11.46, cache write $2.85, cache read $0.1389, against an official list price of input $5, output $25 and cache read $0.5.

Claude Opus 5.5 input $1.74, output $8.13, cache write $2.01, cache read $0.0778, against an official list price of input $4, output $20 and cache read $0.2. Claude Sonnet 5 input $1.32, output $6.67, cache write $1.67, cache read $0.1167, against an official list price of input $2, output $10 and cache read $0.2. Claude Sonnet 5.5 input $1.39, output $7.01, cache write $1.74, cache read $0.0944, against an official list price of input $2, output $10 and cache read $0.1. 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.

The BestRelay card continues through GPT, Gemini and the rest of the line-up

GPT-5.6 Sol input $0.4167, output $2.29, cache read $0.0333, against an official list price of input $4, output $20 and cache read $0.4. GPT-6 Astra input $0.7639, output $3.96, cache read $0.0792, against an official list price of input $10, output $50 and cache read $1. GPT-6.1 Sol input $0.2083, output $1.11, cache read $0.0431, against an official list price of input $2, output $10 and cache read $0.1. Gemini 2.5 Flash input $0.2778, output $2.08, cache write $0.2778, cache read $0.0264. Gemini 3.1 Pro input $1.74, output $9.93, cache write $1.74, cache read $0.1389. Gemini 3.8 Flash input $1.25, output $5.56, cache write $1.25, cache read $0.1236. Gemini 4 Argon input $1.67, output $8.06, cache write $1.67, cache read $0.0847.

DeepSeek V4 Pro input $1.53, output $4.58, cache read $0.0514. Kimi K3 input $1.39, output $7.01, cache read $0.1389. Qwen3.8 Max input $0.8333, output $2.57, cache read $0.1014. Grok 4.6 input $0.625, output $1.81, cache read $0.1389. Grok 4.7 input $0.625, output $1.94, cache read $0.1389. GLM-5.3 input $0.625, output $1.94, cache read $0.1389. 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. Cache reads are priced separately, so a heavy repeated-context workload rewards attention to that column.

BestRelay matches each model to the client it was built for

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. The rule is straightforward, and BestRelay enforces it rather than leaving you to discover it through failed calls. A client needs the address and a key created under API keys in the dashboard, and the details are in the docs.

Referrals are handled in the same plain manner. You earn 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. Keys can be voided at any time, every call sits in the usage records with its model, tokens and charge, and the balance is yours to top up or leave as it stands. BestRelay keeps the arrangement narrow on purpose: one balance, 20 curated models, pay-as-you-go pricing, and the model you name is the model that answers. Try it with the opening credit and read the records yourself.