Gemma 4 31B IT Ultra
gemma-4-31B-it-UltraPricing
List prices at DeepInfra, in US dollars per million tokens.
| Tier | Input / 1M | Output / 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
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.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
DeepInfraInference gemma-4-31B-it-Ultra | $0.27 / $0.76 | gemma-4-31B-it-Ultra |
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 LicenseRuntimes: 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
- 49% less
- 49% less
- 33% less
Open-weight picks
- 6% less
- 11% less
- 33% less
- 34% less
Call it
Using DeepInfra's API.
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"
}