Gemma 4 31B
$0.20 per 1M input tokens and $0.40 per 1M output tokens · 262K context · vision, tools, reasoning, JSON, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
What Gemma 4 31B costs per month
Estimated monthly bill for typical workloads. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $106 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $21.00 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $81.60 |
| Content generation 30 long articles a day | $1.44 |
| Classification / extraction 100,000 short items a day | $198 |
Price history
We started tracking Gemma 4 31B on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Where to run Gemma 4 31B: 15 providers
CoreWeave is the cheapest at $0.10 input / $0.34 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.
| Provider | Input / 1M | Output / 1M | Context | Uptime | Notes |
|---|---|---|---|---|---|
| CoreWeave | $0.10 | $0.34 | 262K | 100% | fp4 |
| Chutes | $0.12 | $0.37 | 131K | 99.9% | fp4 |
| Venice | $0.12 | $0.36 | 256K | 98.1% | fp4 |
| DeepInfra | $0.135 | $0.51 | 262K | 99.9% | priority tier, fp4 |
| Crusoe | $0.14 | $0.40 | 262K | 99.8% | bf16 |
| Friendli | $0.14 | $0.40 | 262K | 99.3% | — |
| Novita | $0.14 | $0.40 | 262K | 74.7% | bf16 |
| Parasail | $0.15 | $0.40 | 262K | 98.5% | fp8 |
| DeepInfra | $0.16 | $0.32 | 262K | 95% | flex tier, fp8 |
| DeepInfra | $0.20 | $0.40 | 262K | 99.9% | fp8 |
| DeepInfra | $0.30 | $0.60 | 262K | 99.5% | priority tier, fp8 |
| Io Net | $0.361 | $1.09 | 262K | 99.7% | — |
| SambaNova | $0.38 | $1.15 | 131K | 99.4% | — |
| ModelRun | $0.75 | $1.00 | 262K | 100% | fp4 |
| SiliconFlow | $0.75 | $1.00 | 262K | 99.3% | fp8 |
Cheaper alternatives to Gemma 4 31B
Models with the same tool calling, image input, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| GLM 5.3 Flash Z.ai | $0.041 | $0.12 | 1.05M | visiontoolsreasoningJSONopen weights |
| MiMo-V2.6-Flash Xiaomi | $0.14 | $0.28 | 1.05M | visionaudiotoolsreasoningJSONopen weights |
| DeepSeek V4.1 Flash DeepSeek | $0.049 | $0.375 | 1.05M | visiontoolsreasoningJSONopen weights |
| Ling 3.0 Flash VL inclusionAI | $0.06 | $0.18 | 131K | visiontoolsreasoningJSONopen weights |
| MiMo-V2.5 Xiaomi | $0.119 | $0.238 | 1.05M | visionaudiotoolsreasoningJSONopen weights |
How to pay less for Gemma 4 31B
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $106 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to GLM 5.3 Flash (similar capabilities) | $16.82 | $88.78 (84%) |
| Route to CoreWeave | $64.56 | $41.04 (39%) |
Other workloads: cut-your-bill tool for Gemma 4 31B.
Specifications
| Model ID | google/gemma-4-31b-it |
| Input | image, text, video |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | Yes |
| Open weights | Yes — google/gemma-4-31B-it |
| Released | Apr 2, 2026 |
FAQ
- How much does Gemma 4 31B cost?
- $0.20 per million input tokens and $0.40 per million output tokens. Prices as of Oct 21, 2026.
- What is the context window of Gemma 4 31B?
- 262K tokens, with up to 16K output tokens per response.
- Does Gemma 4 31B support images, tools and structured output?
- Images as input: yes. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.
- What are cheaper alternatives to Gemma 4 31B?
- Models with the same key capabilities for at least 20% less include GLM 5.3 Flash ($0.041 / $0.12), MiMo-V2.6-Flash ($0.14 / $0.28), DeepSeek V4.1 Flash ($0.049 / $0.375).
More from Google: all Google models · how we collect prices