o4-mini
vercel/openai/o4-mini · family o-mini · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
$1.93
Blended $/1M (3:1)
$1.1
Input $/1M
$4.4
Output $/1M
$5.50
1M in + 1M out
$0.275 −75%
Cache read $/1M
#5500 of 8,539
Cheapest rank
- Provider
- Vercel AI Gateway (
vercel) - Kind
- text (outputs text)
- Context
- 200,000 tokens
- Max output
- 100,000 tokens
- Capabilities
- tools reasoning text image pdf
Same model, other providers
“o4-mini” is offered by 11 providers — cheapest-effective first. Poe is the cheapest at $1.74 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Poe | $0.99 | $4 | $1.74 | 200k |
| Vercel AI Gateway (this) | $1.1 | $4.4 | $1.93 | 200k |
| Jiekou.AI | $1.1 | $4.4 | $1.93 | 200k |
| Impossibl | $1.1 | $4.4 | $1.93 | 200k |
| OpenAI | $1.1 | $4.4 | $1.93 | 200k |
| Azure Cognitive Services | $1.1 | $4.4 | $1.93 | 200k |
| Azure | $1.1 | $4.4 | $1.93 | 200k |
| Cloudflare AI Gateway | $1.1 | $4.4 | $1.93 | 200k |
| NEAR AI Cloud | $1.1 | $4.4 | $1.93 | 200k |
| Abacus | $1.1 | $4.4 | $1.93 | 200k |
| AIHubMix | $1.1 | $4.4 | $1.93 | 200k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Vercel AI Gateway and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"openai/o4-mini","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):