aicredits

Add a key

A new key starts empty. Redeem a battery code into it to add tokens.

01aicredits

OpenAI-compatibleAPI access,paid in tokens.

Create a key, redeem a battery code into it, and point any OpenAI client at the base URL. No account needed: your API key is your login.

  • Streaming
  • No account
  • Batteries bound to a key
  • GPT-5.6 Luna0.04× in · 0.24× out
  • GPT-6.1 Sol1× in · 6× out
  • GPT-5.6 Terra0.4× in · 2.4× out
  • GPT-6 Astra2× in · 10× out

02How it works

Three steps. No account.

Your API key is your login. Tokens arrive in batteries that stay bound to the key they charge.

  1. Create or import a key

    It stays on this browser until you clear it. The secret and the name are kept here, never on the server.

  2. Redeem battery codes

    A BAT-… code adds tokens to the key it is redeemed into. Its validity starts at redemption.

  3. Point your client at the API

    Codex, Cursor, the OpenAI SDK, curl: anything that speaks the OpenAI Chat Completions API.

See the integration

03Connect

Point any OpenAI client here.

OpenAI-compatible · streaming supported · only whitelisted models are served.

API base URL
https://api.aicredits.cc/v1
  • POST/v1/chat/completions
  • GET/v1/models
  • GET/v1/pricing
  • AUTHAuthorization: Bearer sk-…

Codex CLI defaults to the Responses API; this gateway speaks Chat Completions, so keep wire_api = "chat". Rotate a key instead of creating a new one to keep its batteries.

config.toml
# ~/.codex/config.toml
model = "gpt-6.1-sol"
model_provider = "aicredits"

[model_providers.aicredits]
name = "aicredits"
base_url = "https://api.aicredits.cc/v1"
env_key = "AICREDITS_API_KEY"
wire_api = "chat"

# then:  export AICREDITS_API_KEY=sk-...   &&  codex

04Multipliers

1 token = the cost of 1 input token on gpt-6.1-sol.

What a request costs, per model. Pricing v4; a price change ships as a new version, never retroactively.

GPT-5.6 Luna

gpt-5.6-luna
0.04×per input token
Cached input
0×
Output
0.24×

$0.20 · $0.02 · $1.20 / 1M

1M tokens buys 25,000,000 input or 4,166,667 output

GPT-6.1 Sol

base
gpt-6.1-sol
1×per input token
Cached input
0.1×
Output
6×

$5.00 · $0.50 · $30.00 / 1M

1M tokens buys 1,000,000 input or 166,667 output

GPT-5.6 Terra

gpt-5.6-terra
0.4×per input token
Cached input
0.04×
Output
2.4×

$2.00 · $0.20 · $12.00 / 1M

1M tokens buys 2,500,000 input or 416,667 output

GPT-6 Astra

gpt-6-astra
2×per input token
Cached input
0.2×
Output
10×

$10.00 · $1.00 · $50.00 / 1M

1M tokens buys 500,000 input or 100,000 output

A request costs

ceil( input × kin + cached × kcache + output × kout )

For example

1,000 input + 200 output on gpt-6.1-sol=2,200 tokens

Reasoning counts as output, as the provider bills it. With no usage reported the charge is estimated and rounded down.

aicredits