jishie

Gemma 3 12B

neon/gemma-3-12b · family gemma · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.

$0.24
Blended $/1M (3:1)
$0.15
Input $/1M
$0.5
Output $/1M
$0.65
1M in + 1M out
—
Cache read $/1M
#1871 of 7,712
Cheapest rank
Provider
Neon (neon)
Kind
text (outputs text)
Context
131,072 tokens
Max output
8,192 tokens
Capabilities
tools text image

Same model, other providers

“Gemma 3 12B” is offered by 3 providers — cheapest-effective first. NovitaAI is the cheapest at $0.06 blended.

ProviderInputOutputBlendedContext
NovitaAI$0.05$0.1$0.06131k
Merge Gateway$0.09$0.29$0.14128k
Neon (this)$0.15$0.5$0.24131k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gemma-3-12b","messages":[{"role":"user","content":"hello"}]}'

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

← all Neon models · model index · JSON