Gemma 3 Chat: pricing, context window and benchmarks
Gemma 3 Chat is a multimodal model from Google DeepMind. It offers a 65,536-token context window, costs $3.74 per million input tokens and $15.14 per million output tokens, and averages 74.5 across the index's benchmark suite.
Pricing
Gemma 3 Chat costs $3.74 per million input tokens and $15.14 per million output tokens. A blended 3:1 input-to-output mix works out to about $6.59 per million tokens. Cached input is listed at $0.43 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.74 | per 1M tokens |
| Output | $15.14 | per 1M tokens |
| Cached input | $0.43 | per 1M tokens |
| Blended 3:1 | $6.59 | estimate per 1M tokens |
| 1M in + 1M out | $18.88 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 79.4 | 200 | 67th | |
| GPQA Diamond | 67.7 | 316 | 47th | |
| SWE-bench Verified | 65.2 | 210 | 65th | |
| HumanEval | 79.2 | 258 | 57th | |
| MATH-500 | 78.7 | 244 | 59th | |
| AIME 2025 | 70.6 | 244 | 59th | |
| LiveCodeBench | 64.6 | 304 | 49th | |
| IFEval | 83.8 | 217 | 64th | |
| TruthfulQA | 76.5 | 292 | 51th | |
| HellaSwag | 84.1 | 276 | 54th | |
| MMMU | 70.2 | 291 | 52th | |
| Arena Elo | 1374.6 | 297 | 51th |
What Gemma 3 Chat is good for
Gemma 3 Chat is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $3.74 per million input tokens (hosted list price) and a 65,536-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $3.74 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
Trade-offs
- No standout weakness in the indexed specifications, but real-world behaviour still needs testing.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 3 Anyscale | Anyscale | 65536 | $3.94 | 74.7 |
| Llama 3 Anyscale Chat | Anyscale | 65536 | $3.67 | 74.6 |
| Gemma 3 Chat | Google DeepMind | 65536 | $3.74 | 74.5 |
| Llama 3 Hyperbolic | Hyperbolic | 65536 | $3.86 | 74.5 |
| Llama 3 Novita | Novita AI | 128000 | $3.70 | 74.4 |
| Seed-OSS Chat | ByteDance | 65536 | $3.49 | 74.4 |
FAQ
How much does Gemma 3 Chat cost?
Gemma 3 Chat is listed at $3.74 per million input tokens and $15.14 per million output tokens. Cached input is $0.43 per million tokens. A blended 3:1 input-to-output mix is about $6.59 per million tokens.
What is the context window of Gemma 3 Chat?
Gemma 3 Chat has a context window of 65,536 tokens and can emit up to 65,536 output tokens per request in this index.
Is Gemma 3 Chat open weights?
Yes. Gemma 3 Chat is listed as an open-weight model under a open weights licence.
How does Gemma 3 Chat score on benchmarks?
Gemma 3 Chat averages 74.5 across the scored benchmarks in this index, ranking #264 of 600 models. Its strongest relative result is Arena Elo at 1374.6.
What is Gemma 3 Chat best for?
Gemma 3 Chat is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $3.74 per million input tokens (hosted list price) and a 65,536-token context window, it is a practical option for teams that want more control than a closed API allows.