o3
abacus/o3 · family o · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$3.50
Blended $/1M (3:1)
$2
Input $/1M
$8
Output $/1M
$10.00
1M in + 1M out
$0.5 −75%
Cache read $/1M
#6093 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” is offered by 17 providers — cheapest-effective first. Poe is the cheapest at $3.15 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Poe | $1.8 | $7.2 | $3.15 | 200k |
| Abacus (this) | $2 | $8 | $3.50 | 200k |
| NEAR AI Cloud | $2 | $8 | $3.50 | 200k |
| Kilo Gateway | $2 | $8 | $3.50 | 200k |
| 302.AI | $2 | $8 | $3.50 | 200k |
| OpenRouter | $2 | $8 | $3.50 | 200k |
| Azure | $2 | $8 | $3.50 | 200k |
| Azure Cognitive Services | $2 | $8 | $3.50 | 200k |
| Impossibl | $2 | $8 | $3.50 | 200k |
| Cloudflare AI Gateway | $2 | $8 | $3.50 | 200k |
| Vercel AI Gateway | $2 | $8 | $3.50 | 200k |
| Merge Gateway | $2 | $8 | $3.50 | 200k |
| Eden AI | $2 | $8 | $3.50 | 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","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):