impulse

Gemma 4 31B IT Ultra

Open weights
API id gemma-4-31B-it-Ultra
Input / 1M
$0.27
at DeepInfra
Output / 1M
$0.76
at DeepInfra
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.27$0.76

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$138
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$157
  • Coding agent1,000 requests a day, 40K in / 2K out$370
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$830
Use your own numbers

Where to run it

1 host serve Gemma 4 31B IT Ultra. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
gemma-4-31B-it-Ultra
$0.27 / $0.76

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
TextImages
Produces
Text
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 DeepInfra.

Smaller Google models

No cheaper Google model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    49% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    49% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    33% less

Open-weight picks

  • Qwen3.5 397B A17B
    Alibaba Qwen · on AIHubMix
    $0.164 / $0.986
    Has every key capability
    6% less
  • Muse Glimmer 30B
    Meta · on EmpirioLabs AI
    $0.20 / $0.80
    Has every key capability
    11% less
  • Mistral Small 2603
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    33% less
  • Deepseekv4.1 Flash
    DeepSeek · on Sarvam
    $0.149 / $0.585
    Has every key capability
    34% less

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/gemma-4-31B-it-Ultra",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Gemma 4 31B IT Ultra cost?

On DeepInfra, Gemma 4 31B IT Ultra costs $0.27 per million input tokens and $0.76 per million output tokens.

Which APIs offer Gemma 4 31B IT Ultra?

Gemma 4 31B IT Ultra runs on 1 API: DeepInfra.

What is Gemma 4 31B IT Ultra's context window?

131K tokens, with up to 131K tokens in one reply.

Is Gemma 4 31B IT Ultra being retired?

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

What are cheaper alternatives to Gemma 4 31B IT Ultra?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (49% less), GPT-6 Luna on OpenAI (49% less) and Qwen3.5 397B A17B on AIHubMix (6% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Gemma 4 31B IT Ultra's API model id?

Use gemma-4-31B-it-Ultra with DeepInfra.

Sources

Raw catalog entry for gemma-4-31B-it-Ultra on DeepInfra
{
  "max_output_tokens": 131072,
  "max_input_tokens": 131072,
  "input_cost_per_token": 2.7e-7,
  "output_cost_per_token": 7.6e-7,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_tool_choice": true,
  "supports_response_schema": true,
  "supports_reasoning": true,
  "supports_vision": true,
  "source": "https://deepinfra.com/pricing"
}