API Usage Examples
curl --request POST "https://gptproto.com/v1/chat/completions" \
--header "Authorization: Bearer $GPTPROTO_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "doubao-seed-2-0-code-preview-260215",
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}'Doubao Seed 2.0 Code Preview 260215 pricing
Chat, coding agents & document work. Priced per 1M tokens — input, cached input and output are billed separately. GPTProto is 20% below official rates.
Your usage
Bytedance · ≈ 148M tokens/mo (48M cached)
OpenRouter
List + 5.5% credit fee
$69.29
per month
Input (non-cached)$15.6578
Cache read$4.6993
Output$48.93
Bytedance
Direct from Bytedance (list price)
$65.67
per month
Input (non-cached)$14.8416
Cache read$4.4544
Output$46.38
BEST VALUE
GPTProto
20% off official
$52.54
per month
After discount$52.54
Effective$52.54
Monthly cost by source
OpenRouter
$69.29
Bytedance
$65.67
GPTProto
$52.54
Save $13.14 / month
on GPTProto vs Bytedance (−20%)
Annual savings ≈ $157.66 · pay as you go
OpenRouter costs include its ~5.5% credit purchase fee. GPTProto applies a per-model discount (10–30% off) and your bonus credits are also spent at discounted rates — savings compound. Estimates assume a 60% cache hit rate.