Back
Google: Gemma 3 27B
Gemini
Input: text
Input: image
Output: text
Released: Mar 12, 2025•Updated: Mar 28, 2025
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2
131,072 Token Context
Process and analyze large documents and conversations.
Advanced Coding
Improved capabilities in front-end development and full-stack updates.
Agentic Workflows
Autonomously navigate multi-step processes with improved reliability.
Vision Capabilities
Process and understand images alongside text inputs.
Available On
| Provider | Model ID | Context | Max Output | Input Cost | Output Cost | Throughput | Latency |
|---|---|---|---|---|---|---|---|
| DeepInfra | deepInfra | 131K | 16K | $0.10/M | $0.20/M | 28.3 t/s | 961 ms |
| InoCloud | inoCloud | 131K | 16K | $0.10/M | $0.20/M | 16.5 t/s | 1190 ms |
| Nebius | nebiusAiStudio | 110K | - | $0.10/M | $0.30/M | 62.1 t/s | 648 ms |
| Kluster | klusterAi | 64K | 8K | $0.10/M | $0.35/M | 68.4 t/s | 1639 ms |
| Parasail | parasail | 131K | 131K | $0.10/M | $0.40/M | 63.6 t/s | 930 ms |
| Novita | novitaAi | 32K | 32K | $0.12/M | $0.20/M | 34.3 t/s | 1619 ms |
| InferenceNet | inferenceNet | 128K | 8K | $0.15/M | $0.30/M | 16.8 t/s | 1955 ms |
| NCompass | nCompass | 33K | 33K | $0.30/M | $0.30/M | 42.9 t/s | 863 ms |
Standard Pricing
Input Tokens
$0.0000001
per 1K tokens
Output Tokens
$0.0000002
per 1K tokens
Image Processing
$0.0000256
per image