jishie

o4-mini

nearai/openai/o4-mini · family o-mini · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.

$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
#5115 of 7,708
Cheapest rank
Provider
NEAR AI Cloud (nearai)
Kind
text (outputs text)
Context
200,000 tokens
Max output
100,000 tokens
Capabilities
tools reasoning text image

Same model, other providers

“o4-mini” is offered by 16 providers — cheapest-effective first. Poe is the cheapest at $1.74 blended.

ProviderInputOutputBlendedContext
Poe$0.99$4$1.74200k
NEAR AI Cloud (this)$1.1$4.4$1.93200k
Kilo Gateway$1.1$4.4$1.93200k
Abacus$1.1$4.4$1.93200k
OpenRouter$1.1$4.4$1.93200k
Azure$1.1$4.4$1.93200k
Azure Cognitive Services$1.1$4.4$1.93200k
Impossibl$1.1$4.4$1.93200k
Cloudflare AI Gateway$1.1$4.4$1.93200k
Jiekou.AI$1.1$4.4$1.93200k
Vercel AI Gateway$1.1$4.4$1.93200k
Eden AI$1.1$4.4$1.93200k
DevPass (LLM Gateway)$1.1$4.4$1.93200k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at NEAR AI Cloud 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):

← all NEAR AI Cloud models · model index · JSON