Gemma 4 31B Instruct
berget/google/gemma-4-31B-it · family gemma · in: audio, image, text, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning audio image text video.
$0.34
Blended $/1M (3:1)
$0.275
Input $/1M
$0.55
Output $/1M
$0.83
1M in + 1M out
—
Cache read $/1M
#2336 of 7,708
Cheapest rank
- Provider
- Berget.AI (
berget) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 8,192 tokens
- Capabilities
- tools reasoning audio image text video
Same model, other providers
“Gemma 4 31B Instruct” is offered by 2 providers — cheapest-effective first. This one (Berget.AI) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Berget.AI (this) | $0.275 | $0.55 | $0.34 | 128k |
| Together AI | $0.39 | $0.97 | $0.53 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Berget.AI 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-4-31B-it","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):