Gemma 3 12B IT
nano-gpt/unsloth/gemma-3-12b-it · family unsloth · in: text, pdf → out: text · price provider-declared (via models.dev). Capabilities: text pdf.
$0.27
Blended $/1M (3:1)
$0.272
Input $/1M
$0.272
Output $/1M
$0.54
1M in + 1M out
$0.136 −50%
Cache read $/1M
#2104 of 7,708
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 16,384 tokens
- Capabilities
- text pdf
Same model, other providers
“Gemma 3 12B IT” is offered by 7 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 131k |
| Deep Infra | $0.05 | $0.15 | $0.08 | 131k |
| Kilo Gateway | $0.05 | $0.15 | $0.08 | 131k |
| OpenRouter | $0.05 | $0.15 | $0.08 | 131k |
| Hugging Face | $0.05 | $0.15 | $0.08 | 131k |
| Amazon Bedrock | $0.09 | $0.29 | $0.14 | 131k |
| NanoGPT (this) | $0.272 | $0.272 | $0.27 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NanoGPT and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"unsloth/gemma-3-12b-it","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):