jishie

Gemini 2.5 Pro

zenmux/google/gemini-2.5-pro · in: pdf, image, text, audio, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning pdf image text audio video.

$3.44
Blended $/1M (3:1)
$1.25
Input $/1M
$10
Output $/1M
$11.25
1M in + 1M out
$0.31 −75%
Cache read $/1M
#5949 of 7,712
Cheapest rank
Provider
ZenMux (zenmux)
Kind
text (outputs text)
Context
1,048,000 tokens
Max output
64,000 tokens
Capabilities
tools reasoning pdf image text audio video

Same model, other providers

“Gemini 2.5 Pro” is offered by 25 providers — cheapest-effective first. This one (ZenMux) is the cheapest.

ProviderInputOutputBlendedContext
ZenMux (this)$1.25$10$3.441M
Perplexity Agent$1.25$10$3.441M
NanoGPT$1.25$10$3.441M
NEAR AI Cloud$1.25$10$3.441M
Databricks$1.25$10$3.441M
Kilo Gateway$1.25$10$3.441M
Abacus$1.25$10$3.441M
OpenRouter$1.25$10$3.441M
Auriko$1.25$10$3.441M
Impossibl$1.25$10$3.441M
Google$1.25$10$3.441M
FrogBot$1.25$10$3.441M
Vercel AI Gateway$1.25$10$3.441M

Call it

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

Most providers are OpenAI-compatible — point base_url at ZenMux and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-2.5-pro","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all ZenMux models · model index · JSON