jishie

Gemma 3 4B IT

nvidia/google/gemma-3-4b-it · family gemma · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
—
Cache read $/1M
#124 of 7,708
Cheapest rank
Provider
Nvidia (nvidia)
Kind
text (outputs text)
Context
131,072 tokens
Max output
16,384 tokens
Capabilities
tools text image

Same model, other providers

“Gemma 3 4B IT” is offered by 7 providers — cheapest-effective first. This one (Nvidia) is the cheapest.

ProviderInputOutputBlendedContext
Nvidia (this)freefree$0.00131k
Amazon Bedrock$0.04$0.08$0.05131k
Deep Infra$0.05$0.1$0.06131k
Kilo Gateway$0.05$0.1$0.06131k
OpenRouter$0.05$0.1$0.06131k
Hugging Face$0.05$0.1$0.06131k
NanoGPT$0.2006$0.2006$0.20128k

Call it

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

Most providers are OpenAI-compatible — point base_url at Nvidia 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-3-4b-it","messages":[{"role":"user","content":"hello"}]}'

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

← all Nvidia models · model index · JSON