Gemma 3 27B IT
prime/google/gemma-3-27b-it · family gemma · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$0.16
Blended $/1M (3:1)
$0.119
Input $/1M
$0.3
Output $/1M
$0.42
1M in + 1M out
—
Cache read $/1M
#1474 of 8,066
Cheapest rank
- Provider
- Prime Inference (
prime) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 117,964 tokens
- Capabilities
- tools text image
Same model, other providers
“Gemma 3 27B IT” is offered by 10 providers — cheapest-effective first. Deep Infra is the cheapest at $0.10 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Deep Infra | $0.08 | $0.16 | $0.10 | 131k |
| Kilo Gateway | $0.08 | $0.16 | $0.10 | 131k |
| Hugging Face | $0.08 | $0.16 | $0.10 | 131k |
| Novita AI | $0.119 | $0.2 | $0.14 | 98k |
| Cortecs | $0.099 | $0.299 | $0.15 | 131k |
| Prime Inference (this) | $0.119 | $0.3 | $0.16 | 131k |
| OpenRouter | $0.08 | $0.45 | $0.17 | 131k |
| Merge Gateway | $0.08 | $0.45 | $0.17 | 131k |
| Amazon Bedrock | $0.23 | $0.38 | $0.27 | 131k |
| NanoGPT | $0.2992 | $0.2992 | $0.30 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Prime Inference 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-3-27b-it","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):