Credits & Billing

Tchavi uses a credit-based billing system — each API request consumes credits based on the model used and the number of tokens processed.

Tchavi uses a credit-based billing system. Each API request consumes credits based on the model used and the number of tokens processed.

How credits are calculated

  • Chat models: Credits = (input_tokens × rate + output_tokens × rate) per 1K tokens
  • Image models: Flat credit cost per image based on resolution
  • TTS (text-to-speech): Credits per 1K characters of input text
  • Transcription (Whisper): Credits per minute of audio
  • Video models: Credits per second of video, varies by resolution (some models add a surcharge when audio is generated)

Response headers

Every API response includes metadata headers:

HeaderDescription
X-Credits-UsedCredits consumed by this request
X-Credits-RemainingYour current credit balance
X-RateLimit-RPM-LimitYour requests-per-minute limit
X-RateLimit-RPM-RemainingRequests remaining in the current minute
X-RateLimit-TPM-LimitYour tokens-per-minute limit
X-RateLimit-TPM-RemainingToken budget remaining in the current minute
X-Request-IdUnique request ID for support/debugging
Retry-AfterSeconds to wait before retrying (on 429 responses)

Example credit calculation. A gpt-4o-mini request with 500 input tokens + 200 output tokens at the Budget tier (e.g. 1 cr/1K input, 2 cr/1K output) costs:

text
(500/1000 × 1) + (200/1000 × 2) = 0.9 credits

→ rounded up to 1 credit. The exact rate for each model is shown in the Models table.

Recharging

Buy credit packs from your billing dashboard using Wave, Orange Money, MTN MoMo, and 30+ mobile money operators. Credits are added instantly after payment.

See also Rate Limits and Error Handling.

On this page