jishie

Gemini 2.5 Flash

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

$0.85
Blended $/1M (3:1)
$0.3
Input $/1M
$2.5
Output $/1M
$2.80
1M in + 1M out
$0.07 −77%
Cache read $/1M
#3755 of 7,708
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

Same model, other providers

“Gemini 2.5 Flash” is offered by 27 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Kenarifreefree$0.001M
QiHang$0.09$0.71$0.241M
Cortecs$0.299$2.49$0.851M
ZenMux (this)$0.3$2.5$0.851M
Perplexity Agent$0.3$2.5$0.851M
NanoGPT$0.3$2.5$0.851M
NEAR AI Cloud$0.3$2.5$0.851M
Databricks$0.3$2.5$0.851M
Kilo Gateway$0.3$2.5$0.851M
Abacus$0.3$2.5$0.851M
OpenRouter$0.3$2.5$0.851M
Auriko$0.3$2.5$0.851M
Impossibl$0.3$2.5$0.851M

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-flash","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