jishie

Gemma 3 27B

stackit/google/gemma-3-27b-it · family gemma · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: text image.

$0.59
Blended $/1M (3:1)
$0.53
Input $/1M
$0.76
Output $/1M
$1.29
1M in + 1M out
—
Cache read $/1M
#3199 of 7,708
Cheapest rank
Provider
STACKIT (stackit)
Kind
text (outputs text)
Context
37,000 tokens
Max output
4,096 tokens
Capabilities
text image

Same model, other providers

“Gemma 3 27B” is offered by 4 providers — cheapest-effective first. EmpirioLabs AI is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
EmpirioLabs AIfreefree$0.00128k
NovitaAI$0.119$0.2$0.1498k
GreenPT$0.342$0.684$0.4340k
STACKIT (this)$0.53$0.76$0.5937k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"google/gemma-3-27b-it","messages":[{"role":"user","content":"hello"}]}'

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

← all STACKIT models · model index · JSON