Gemma 3 27B ITOpen weights
Google · released 2025-03-12
No price from the maker itself is on record for Gemma 3 27B IT. The lowest of 17 providers is Deep Infra: $0.08 per 1M input tokens and $0.16 per 1M output tokens (as of 2026-11-12). Context window: 131K tokens, up to 131K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| $0.08 | $0.16 | — | Lowest | Official docs | |
EEden AIdeepinfra/ | $0.08 | $0.16 | — | Official docs | |
| $0.08 | $0.16 | — | Official docs | ||
KKilo Gatewaygoogle/ | $0.08 | $0.16 | — | Official docs | |
| $0.119 | $0.2 | — | Official docs | ||
| $0.12 | $0.2 | — | Official docs | ||
CCortecsgemma-3-27b-it | $0.099 | $0.299 | — | Official docs | |
EEden AInebius/ | $0.1 | $0.3 | $0.1 | Official docs | |
| $0.1 | $0.3 | $0.1 | Official docs | ||
PPrime Inferencegoogle/ | $0.119 | $0.3 | — | Official docs | |
| $0.08 | $0.35 | $0.04 | Official docs | ||
MMerge Gatewaygoogle/ | $0.08 | $0.45 | $0.04 | Official docs |
9 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTunsloth/ | $0.2992 | $0.2992 | $0.1496 | Official docs | |
EEden AIamazon/ | $0.23 | $0.38 | — | Official docs | |
EEden AIamazon/ | $0.23 | $0.38 | — | Official docs | |
| $0.1587 | $0.48668 | $0.07935 | Official docs | ||
EEden AIscaleway/ | $0.287125 | $0.57425 | — | Official docs | |
| $0.23 | $0.38 | — | Deprecated | Official docs | |
| $0.342 | $0.684 | — | Deprecated | Official docs | |
SSTACKITDeprecatedgoogle/ | $0.53 | $0.76 | — | Deprecated | Official docs |
| $0 | $0 | — | Deprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
Price changes
| Date | Provider | Change |
|---|---|---|
| 2026-11-11 | OpenRouter | Output $0.45 → $0.35 |
About
Largest open Gemma 3 instruction model for multilingual text generation and visual understanding
Description from models.dev.
Specs
- Type
- Text
- Context
- 131K
- Max output
- 131K
- Input
- Text, Image
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2024-08
- Open weights
- Yes
- Released
- 2025-03-12
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.