impulse

Gemma 4 12B IT

Open weights
API id gemma-4-12B-it
Input / 1M
$0.30
at Sail
Output / 1M
$2.00
at Sail
Context window
16K
tokens
Max output
16K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Sail, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.30$2.00
Cached input
50% off input
$0.15
Flex
83% off
$0.05$1.00

What it costs a month

At Sail list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$227
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$180
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$354
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,200
Use your own numbers

Where to run it

1 host serve Gemma 4 12B IT. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
SailCloud
gemma-4-12B-it
$0.30 / $2.00

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Features
Prompt caching
Open weights
License: Gemma License
Runtimes: Ollama, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Sail.

Smaller Google models

No cheaper Google model keeps its key capabilities.

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    36% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    72% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    72% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    64% less

Open-weight picks

  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    6% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    12% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    28% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    33% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedGemma 4 12B ITLatest$0.30 / $2.00
  2. Mar 2025Gemma 3 12B IT$0.05 / $0.10

Call it

Using Sail's API.

Python
from litellm import completion

response = completion(
    model="sail/gemma-4-12B-it",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Gemma 4 12B IT cost?

On Sail, Gemma 4 12B IT costs $0.30 per million input tokens and $2.00 per million output tokens. Cached input costs $0.15 per million tokens.

Which APIs offer Gemma 4 12B IT?

Gemma 4 12B IT runs on 1 API: Sail.

What is Gemma 4 12B IT's context window?

16K tokens, with up to 16K tokens in one reply.

Is Gemma 4 12B IT being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Gemma 4 12B IT?

No. Gemma 4 12B IT is the newest model in its line.

What are cheaper alternatives to Gemma 4 12B IT?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (36% less), Claude Haiku 5.5 on Anthropic (72% less) and Kimi K2.7 Code on CLF AI Gateway (6% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Gemma 4 12B IT's API model id?

Use gemma-4-12B-it with Sail.

Sources

Raw catalog entry for gemma-4-12B-it on Sail
{
  "max_input_tokens": 16384,
  "max_output_tokens": 16384,
  "input_cost_per_token": 3e-7,
  "output_cost_per_token": 0.000002,
  "cache_read_input_token_cost": 1.5e-7,
  "input_cost_per_token_balanced": 1e-7,
  "output_cost_per_token_balanced": 0.000002,
  "cache_read_input_token_cost_balanced": 7e-8,
  "input_cost_per_token_flex": 5e-8,
  "output_cost_per_token_flex": 0.000001,
  "cache_read_input_token_cost_flex": 2e-8,
  "litellm_provider": "sail",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_tool_choice": true,
  "supports_prompt_caching": true,
  "supports_response_schema": true,
  "supports_reasoning": true,
  "source": "https://docs.sailresearch.com/models"
}