Gemma 4 12B IT
kitani/google/gemma-4-12b-it · family gemma · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.09
Blended $/1M (3:1)
$0.045
Input $/1M
$0.23
Output $/1M
$0.28
1M in + 1M out
$0.0225 −50%
Cache read $/1M
#919 of 9,563
Cheapest rank
- Provider
- Kitani (
kitani) - Kind
- text (outputs text)
- Context
- 8,192 tokens
- Max output
- 4,096 tokens
- Capabilities
- tools text
Same model, other providers
“Gemma 4 12B IT” is offered by 2 providers — cheapest-effective first. This one (Kitani) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Kitani (this) | $0.045 | $0.23 | $0.09 | 8k |
| SiliconFlow | $0.1 | $0.3 | $0.15 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Kitani 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-4-12b-it","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):