o3-pro
abacus/o3-pro · family o-pro · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$25.00
Blended $/1M (3:1)
$20
Input $/1M
$40
Output $/1M
$60.00
1M in + 1M out
—
Cache read $/1M
#7541 of 7,708
Cheapest rank
- Provider
- Abacus (
abacus) - Kind
- text (outputs text)
- Context
- 200,000 tokens
- Max output
- 100,000 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“o3-pro” is offered by 6 providers — cheapest-effective first. This one (Abacus) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Abacus (this) | $20 | $40 | $25.00 | 200k |
| Poe | $18 | $72 | $31.50 | 200k |
| Kilo Gateway | $20 | $80 | $35.00 | 200k |
| OpenRouter | $20 | $80 | $35.00 | 200k |
| Eden AI | $20 | $80 | $35.00 | 200k |
| OpenAI | $20 | $80 | $35.00 | 200k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Abacus and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"o3-pro","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):