gemma-3-it
Developer: Google
Google Gemma 3 IT is an instruction-tuned open model in the Gemma 3 family, designed for efficient text generation and developer-facing applications.
Also known as
Gemma 3 IT by Google is available through 68 API providers on LMSpeed. Compare API pricing from $0.010 to $1998.00 per million input tokens across providers. Free API access is offered by 9 providers. In speed benchmarks, the fastest provider reaches 213 tok/s.
Compare Gemma 3 IT API pricing across 59 providers. Input prices range from $0.010 to $1998.00 per million input. 素墨API offers the lowest rate at $0.010/M. 9 providers offer free API credits or a free tier.
| Provider | Model Variant | Audit | Input ($/M) | Output ($/M) | Speed (t/s) | First token |
|---|---|---|---|---|---|---|
素墨API100% | google/gemma-3-1b-it | — | $0.010 | $0.010 | 176.5 t/s | 0.87 s |
| google/gemma-3-12b-it | — | $0.010 | $0.010 | — | — | |
| google/gemma-3-27b-it | — | $0.010 | $0.010 | — | — | |
| google/gemma-3-4b-it | — | $0.010 | $0.010 | — | — | |
星见雅 API100% | 李/google/gemma-3-12b-it | — | Free | Free | — | — |
| 李/google/gemma-3-27b-it | — | Free | Free | — | — | |
| 英伟达/google/gemma-3-12b-it | — | Free | Free | — | — | |
| 英伟达/google/gemma-3-27b-it | — | Free | Free | — | — | |
| 英伟达/google/gemma-3-4b-it | — | Free | Free | — | — | |
MapleLeaf API100% | google/gemma-3-4b-it | — | $0.017 | $0.068 | — | — |
| google/gemma-3-12b-it | — | $0.030 | $0.100 | — | — | |
| google/gemma-3-27b-it | — | $0.030 | $0.110 | — | — | |
SMLC666 API100% | google/gemma-3-4b-it | — | $0.017 | $0.068 | — | — |
| google/gemma-3-12b-it | — | $0.030 | $0.100 | — | — | |
| google/gemma-3-27b-it | — | $0.490 | $0.710 | — | — | |
| google/gemma-3-12b-it:free | — | $75.00 | $75.00 | — | — | |
| google/gemma-3-27b-it:free | — | $75.00 | $75.00 | — | — | |
| google/gemma-3-4b-it:free | — | $75.00 | $75.00 | — | — | |
钱多多 API100% | gemma-3-12b-it | — | $0.490 | $0.490 | — | — |
| gemma-3-1b-it | — | $0.490 | $0.490 | — | — |
Pricing data from provider public APIs
Compare speed and latency performance across all API providers.
| Provider | Speed | Latency | Tests |
|---|---|---|---|
星见雅 API google/gemma-3-1b-it | 213.18 tok/s | 0.52s | 10 |
google/gemma-3-1b-it | 176.46 tok/s | 0.87s | 5 |
gemma-3-27b-it | 77.96 tok/s | 0.81s | 5 |
google/gemma-3-27b-it | 54.03 tok/s | 0.89s | 5 |
google/gemma-3-27b-it | 53.73 tok/s | 0.57s | 10 |
google/gemma-3-4b-it | 51.71 tok/s | 2.91s | 5 |
google/gemma-3-27b-it | 50.81 tok/s | 0.47s | 15 |
google/gemma-3-27b-it:free | 49.45 tok/s | 3.07s | 5 |
Showing 1-8 of 8 providers
gpt-oss
GPT-OSS is an open-source language model offering advanced reasoning, code generation, and multimodal capabilities.
minimax-m2-5
MiniMax M2.5 is MiniMax's flagship text model for coding and agents, with SOTA-level programming and agentic performance, improved token efficiency, and fast high-TPS API deployment.
deepseek-v3-2
DeepSeek V3.2 is a large language model in the DeepSeek V3 series, offering advanced reasoning, code generation, and multimodal capabilities.
kimi-k2-5
Moonshot Kimi K2.5 is a large language model in the Kimi series, offering advanced reasoning, code generation, and multimodal capabilities.
minimax-m2-7
MiniMax M2.7 is a large language model in the MiniMax series, offering advanced reasoning, code generation, and multimodal capabilities.
kimi-k2-thinking
Moonshot AI Kimi K2 Thinking is a reasoning model in the Kimi series, designed for complex reasoning, problem-solving, and analytical tasks.
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
