Duo and Builder are sized for a single dev. For production traffic we negotiate volume rates, custom concurrency and output caps, and monthly invoicing that match how you actually run.
| model | input / 1M | output / 1M | RedRoute rate |
|---|---|---|---|
gpt-5.5 |
$5.00 | $30.00 | 1× |
claude-opus-4-7 |
$5.00 | $25.00 | 1× |
claude-opus-4-8 |
$5.00 | $25.00 | 1× |
claude-fable-5 |
$10.00 | $50.00 | 1.20× |
gpt-4o-audio-preview |
$2.50 | $10.00 | 1× |
gpt-realtime-2025-08-28 |
$4.00 | $16.00 | 1× |
deepseek-v4-flash |
$0.14 | $0.28 | 1.20× |
deepseek-v4-pro |
$0.43 | $0.87 | 1.20× |
MiniMax-M3 |
$0.58 | $2.32 | 1.79× · top-up only |
glm-5.1 |
$0.69 | $3.45 | 1.79× · top-up only |
qwen3.7-max |
$1.66 | $4.97 | 1.79× · top-up only |
deepseek-v3-search |
$4.00 | $16.00 | 1× |
gpt-5-search-api |
$10.00 | $80.00 | 1× |
gpt-4o-search-preview |
$20.00 | $80.00 | 1× |
gpt-4o-search-preview-2025-03-11 |
$20.00 | $80.00 | 1× |
gpt-4o-mini-search-preview |
$1.12 | $4.48 | 1× |
claude-sonnet-4-6 |
$3.00 | $15.00 | 1× |
claude-opus-4-6 |
$5.00 | $25.00 | 1× |
gemini-3.5-flash |
$2.25 | $13.50 | 1× |
gemini-3.1-pro-preview |
$3.00 | $18.00 | 1× |
gpt-image-2 |
$0.05 per image | 1× | |
gpt-image-1-mini |
$0.02 per image | 1× | |
gemini-3-pro-image-preview |
$0.05 per image | 1× | |
gemini-2.5-flash-image |
$0.02 per image | 1× | |
gemini-3.1-flash-image-preview |
$0.02 per image | 1× | |
gpt-4o-mini-tts |
$0.30 per request | 1× | |
gemini-2.5-flash-preview-tts |
$0.75 | $15.00 | 1× |
whisper-1 |
$0.006 per audio minute | 1× | |
Plans and top-ups buy API credit at a discount. Most models burn credit at the official API price; premium routes may burn at a shown multiple.
RedRoute (beta) reserves a worst-case amount per request and refunds the unused portion
when the response completes. Realtime audio tokens on gpt-realtime-2025-08-28 bill at the official $32 / $64 per 1M;
the listed rate covers its text tokens.
| rate limit | 60 requests/min per RedRoute (beta) key |
| session budget | 1h rolling cap as a fraction of plan face value (excludes trial) |
| refunds | no refunds for consumed balance; unredeemed codes can be returned at operator discretion |
| content | coding and agentic workloads only; NSFW / roleplay / jailbreaks blocked |
| upstream incidents | failed upstream calls are not debited; operator may issue make-good top-ups in Discord |
#access for a token and say which plan / top-up you want.