jishie

Gemini-2.5-Flash

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

$0.61
Blended $/1M (3:1)
$0.21
Input $/1M
$1.8
Output $/1M
$2.01
1M in + 1M out
$0.021 −90%
Cache read $/1M
#3245 of 7,708
Cheapest rank
Provider
Poe (poe)
Kind
text (outputs text)
Context
1,065,535 tokens
Max output
65,535 tokens
Capabilities
tools reasoning text image video audio

Same model, other providers

“Gemini-2.5-Flash” is offered by 4 providers — cheapest-effective first. This one (Poe) is the cheapest.

ProviderInputOutputBlendedContext
Poe (this)$0.21$1.8$0.611.1M
Jiekou.AI$0.27$2.25$0.771M
302.AI$0.3$2.5$0.851M
SAP AI Core$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 Poe 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 Poe models · model index · JSON