GPT-4o mini
edenai/openai/gpt-4o-mini · family gpt-mini · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: toolstextimagepdf.
$0.26Blended $/1M (3:1)
$0.15Input $/1M
$0.6Output $/1M
$0.751M in + 1M out
$0.075 −50%Cache read $/1M
#1516 of 5,819Cheapest rank
- Provider
- Eden AI (
edenai) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 16,384 tokens
- Capabilities
- toolstextimagepdf
Same model, other providers
“GPT-4o mini” is offered by 19 providers — cheapest-effective first. This one (Eden AI) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Eden AI (this) | $0.15 | $0.6 | $0.26 | 128k |
| Impossibl | $0.15 | $0.6 | $0.26 | 128k |
| CrossModel | $0.15 | $0.6 | $0.26 | 128k |
| NanoGPT | $0.15 | $0.6 | $0.26 | 128k |
| LLM Gateway | $0.15 | $0.6 | $0.26 | 128k |
| Pioneer | $0.15 | $0.6 | $0.26 | 128k |
| Abacus | $0.15 | $0.6 | $0.26 | 128k |
| Azure Cognitive Services | $0.15 | $0.6 | $0.26 | 128k |
| Azure | $0.15 | $0.6 | $0.26 | 128k |
| Ofox | $0.15 | $0.6 | $0.26 | 128k |
| OrcaRouter | $0.15 | $0.6 | $0.26 | 128k |
| Kilo Gateway | $0.15 | $0.6 | $0.26 | 128k |
| Vercel AI Gateway | $0.15 | $0.6 | $0.26 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Eden AI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"openai/gpt-4o-mini","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):