AI 模型情报

Gemma 4 31B IT

google/gemma4-31b

出品方： Google · 系列: gemma · 发布 2026-04-02 · 知识截止: 2025-01

$0.400
输入 / 1M token
$1.00
输出 / 1M token
256K
上下文长度
33K
最大输出

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

能力清单

✓ 工具调用✓ 推理✓ 结构化输出✓ 附件✓ 开放权重✓ 温度可调
支持模态: 输入 text, image · 输出 text

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding81
  • Tool calling40/40
  • Structured output20/20
  • Reasoning10/10
  • Context window (100K → 1M)8/20
  • Provider availability3/10
Agents93
  • Tool calling35/35
  • Structured output25/25
  • Reasoning15/15
  • Output token limit15/15
  • Provider availability3/10
JSON / structured output97
  • Structured output / JSON mode50/50
  • Tool calling20/20
  • Temperature control10/10
  • Price-friendly for high-volume17/20
Cost efficiency59
  • Headline price (log-scaled)59/95
  • Has prompt-cache pricing0/5
Long context60
  • Context window (100K → 2M)50/90
  • Has published price for full window10/10
Vision84
  • Accepts image input50/50
  • Context window (10K → 1M)21/30
  • Has published price10/10
  • Provider availability3/10
Production-readiness71
  • Number of independent providers15/40
  • Has published per-token price20/20
  • Context window ≥ 8K15/15
  • No data inconsistencies across providers6/10
  • Official model (not derivative)15/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

ScenarioCostAssumption
RAG answer
per 1,000 RAG answers
$2.50
< $0.01 per request
5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot.
Support ticket triage
per 10,000 tickets
$5.00
< $0.01 per request
1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support.
Data extraction
per 1,000 documents
$1.30
< $0.01 per request
2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines.
Code review
per 1,000 PRs
$4.20
< $0.01 per request
8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads.
Agent step
per 1,000 steps
$5.40
< $0.01 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

定价详情

推荐定价来自 tinfoil · gemma4-31b

$0.400
输入
$1.00
输出

在 3 家渠道可用

服务商服务商模型 ID输入 / 1M输出 / 1M上下文发布日期
Tinfoil
tinfoil
gemma4-31b$0.400$1.00256K2026-04-02
Ollama Cloud
ollama-cloud
gemma4:31bUnknownUnknown262K2026-04-02
NanoGPT
nano-gpt
TEE/gemma4-31b$0.450$1.00262K2026-04-04

各渠道数据存在不一致

  • context_window varies: 256000, 262144
  • modalities varies across offerings

各服务商对此模型的报告值存在差异。上方「核心数据」使用代表性服务商的值；逐项请以下表为准。

Frequently asked questions

How much does Gemma 4 31B IT cost?

Gemma 4 31B IT costs $0.400 per 1M input tokens and $1.00 per 1M output tokens, sourced from tinfoil. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.

What is the context window of Gemma 4 31B IT?

Gemma 4 31B IT has a context window of 256K tokens, with a max output of 33K tokens per reply. This is the total combined size of prompt + completion.

Does Gemma 4 31B IT support tool calling?

Yes. Gemma 4 31B IT supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.

Does Gemma 4 31B IT support structured output / JSON mode?

Yes. Gemma 4 31B IT supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.

Can Gemma 4 31B IT accept image input?

Yes. Gemma 4 31B IT accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check Google's docs for the exact rule.

Is Gemma 4 31B IT open-weight?

Yes. Gemma 4 31B IT's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.

What are the best alternatives to Gemma 4 31B IT?

If Gemma 4 31B IT doesn't fit, consider Gemini 2.5 Pro, Gemini 2.5 Flash, Gemma 4 31B IT. Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

Explore more

More Google models

Capability lists this model is in

See also

最近更新：

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.