← Models

Google · current

Gemma 4 12B IT

Gemma 4 12B IT is attributed to Google in the catalog. It accepts text and image input and produces text output. Reported capabilities include tool calling and structured output.

Compare model

Modalities

Hosted provider token rates

$0.05 / $0.25

USD per 1M input / output tokens · NanoGPT

Context

262K

Released

2026-06-09

Knowledge cutoff

Unknown

No recent lab-operated provider rate is available. Showing the third-party host with the lowest input rate + ¼ output rate. This is one offering, not an average; other providers, modalities, tiers, and fees may differ.

Where to use it

3 observed offerings · token prices in USD per million where available

Estimate your workload cost
SiliconFlow

google/gemma-4-12B-it

current

Input

$0.10

Output

$0.30

Cache

—

Context

262K

Max output

262K
Reasoning
No
Tool calling
Yes
Structured output
Yes
Temperature
Yes

Recent price

Pioneer

google/gemma-4-12B-it

deprecated

Input

$0.25

Output

$0.25

Cache

$0.25

Context

33K

Max output

33K
Reasoning
Yes
Tool calling
Yes
Structured output
Unknown
Temperature
Yes

Historical price

NanoGPT

gemma-4-12b-it

current

Input

$0.05

Output

$0.25

Cache

$0.025

Context

131K

Max output

33K
Reasoning
No
Tool calling
Yes
Structured output
Yes
Temperature
Yes

Recent price

Limits and capabilities reflect each provider’s listed offering. Unknown means support was not reported.

Capabilities and limits

Input
text, image
Output
text
Max output
262K
Weights
Open (source-reported)
Release
2026-06-09
Knowledge cutoff
Unknown
Family
gemma

Tool calling · Structured output · Vision

Provider-specific limits and support can differ.

Plan a model evaluation

Evaluate quality and latency on examples from your intended use before choosing a model.

Explore available evidence

Models to compare

Candidates match reported specifications; they are not tested replacements.

Model and price history

Latest recorded change: source refresh · 2026-10-23

Model changes (3)
  • source refresh · 2026-10-23
    {
      "before": {
        "status": "deprecated",
        "context_tokens": 32768,
        "input_modalities": [
          "text"
        ],
        "max_output_tokens": 32768,
        "supports_reasoning": true,
        "supports_attachments": false,
        "supports_structured_output": false
      },
      "after": {
        "status": "current",
        "context_tokens": 262144,
        "input_modalities": [
          "text",
          "image"
        ],
        "max_output_tokens": 262144,
        "supports_reasoning": false,
        "supports_attachments": true,
        "supports_structured_output": true
      }
    }
  • source refresh · 2026-10-21
    {
      "before": {
        "status": "current",
        "open_weights": false,
        "context_tokens": 262144,
        "max_output_tokens": 262144,
        "supports_reasoning": false,
        "supports_structured_output": true
      },
      "after": {
        "status": "deprecated",
        "open_weights": true,
        "context_tokens": 32768,
        "max_output_tokens": 32768,
        "supports_reasoning": true,
        "supports_structured_output": false
      }
    }
  • source refresh · 2026-10-17
    {
      "before": {
        "input_modalities": [
          "text",
          "image",
          "video",
          "audio"
        ]
      },
      "after": {
        "input_modalities": [
          "text",
          "image"
        ]
      }
    }
Price history (68 observations)
DateProviderInput / output
2026-11-02NanoGPT$0.05 / $0.25
2026-11-02SiliconFlow$0.10 / $0.30
2026-11-01NanoGPT$0.05 / $0.25
2026-11-01SiliconFlow$0.10 / $0.30
2026-10-31NanoGPT$0.05 / $0.25
2026-10-31SiliconFlow$0.10 / $0.30
2026-10-30NanoGPT$0.05 / $0.25
2026-10-30SiliconFlow$0.10 / $0.30
2026-10-29NanoGPT$0.05 / $0.25
2026-10-29SiliconFlow$0.10 / $0.30
2026-10-28NanoGPT$0.05 / $0.25
2026-10-28SiliconFlow$0.10 / $0.30
2026-10-27NanoGPT$0.05 / $0.25
2026-10-27SiliconFlow$0.10 / $0.30
2026-10-27NanoGPT$0.05 / $0.25
2026-10-27SiliconFlow$0.10 / $0.30
2026-10-27NanoGPT$0.05 / $0.25
2026-10-27SiliconFlow$0.10 / $0.30
2026-10-27NanoGPT$0.05 / $0.25
2026-10-27SiliconFlow$0.10 / $0.30
2026-10-26NanoGPT$0.05 / $0.25
2026-10-26SiliconFlow$0.10 / $0.30
2026-10-25NanoGPT$0.05 / $0.25
2026-10-25SiliconFlow$0.10 / $0.30
2026-10-24NanoGPT$0.05 / $0.25
2026-10-24SiliconFlow$0.10 / $0.30
2026-10-24NanoGPT$0.05 / $0.25
2026-10-24SiliconFlow$0.10 / $0.30
2026-10-24NanoGPT$0.05 / $0.25
2026-10-24SiliconFlow$0.10 / $0.30
2026-10-23NanoGPT$0.05 / $0.25
2026-10-23SiliconFlow$0.10 / $0.30
2026-10-23NanoGPT$0.05 / $0.25
2026-10-23SiliconFlow$0.10 / $0.30
2026-10-23NanoGPT$0.05 / $0.25
2026-10-23SiliconFlow$0.10 / $0.30
2026-10-23NanoGPT$0.05 / $0.25
2026-10-23SiliconFlow$0.10 / $0.30
2026-10-23NanoGPT$0.05 / $0.25
2026-10-23SiliconFlow$0.10 / $0.30
2026-10-22NanoGPT$0.05 / $0.25
2026-10-22SiliconFlow$0.10 / $0.30
2026-10-22Pioneer$0.25 / $0.25
2026-10-21NanoGPT$0.05 / $0.25
2026-10-21Pioneer$0.25 / $0.25
2026-10-21SiliconFlow$0.10 / $0.30
2026-10-20NanoGPT$0.05 / $0.25
2026-10-20SiliconFlow$0.10 / $0.30
2026-10-19NanoGPT$0.05 / $0.25
2026-10-19SiliconFlow$0.10 / $0.30
2026-10-18NanoGPT$0.05 / $0.25
2026-10-18SiliconFlow$0.10 / $0.30
2026-10-17NanoGPT$0.05 / $0.25
2026-10-17SiliconFlow$0.10 / $0.30
2026-10-12NanoGPT$0.05 / $0.25
2026-10-12SiliconFlow$0.10 / $0.30
2026-10-12NanoGPT$0.05 / $0.25
2026-10-12SiliconFlow$0.10 / $0.30
2026-10-11NanoGPT$0.05 / $0.25
2026-10-11SiliconFlow$0.10 / $0.30
2026-10-10NanoGPT$0.05 / $0.25
2026-10-10SiliconFlow$0.10 / $0.30
2026-10-09NanoGPT$0.05 / $0.25
2026-10-09SiliconFlow$0.10 / $0.30
2026-10-09SiliconFlow$0.10 / $0.30
2026-10-08SiliconFlow$0.10 / $0.30
2026-10-07SiliconFlow$0.10 / $0.30
2026-09-22SiliconFlow$0.10 / $0.30