Question 1

What is Gemma 4 31B?

Accepted Answer

Gemma 4 31B is a model from Google Gemini AI, released on Apr 2, 2026. Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.

Question 2

How much does Gemma 4 31B cost?

Accepted Answer

On the Respan gateway, input starts at $0.09 per 1M tokens on OpenRouter, and output starts at $0.34 per 1M tokens on OpenRouter, after gateway discounts. Averaged across 10 providers, it costs $0.17 per 1M input tokens and $0.44 per 1M output tokens.

Question 3

Which providers serve Gemma 4 31B on Respan?

Accepted Answer

10 providers serve Gemma 4 31B: OpenRouter, Featherless, Novita, FriendliAI, Parasail, DeepInfra, and 1 more. TogetherAI requires your own provider API key (BYOK).

Question 4

What is Gemma 4 31B's context window?

Accepted Answer

Gemma 4 31B accepts up to 262K tokens of context on its largest provider route.

Question 5

How do I use Gemma 4 31B with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "gemma-4-31b-it". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Gemma 4 31B?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 34 tokens per second, and the lowest response latency was 0.4 seconds on Parasail. Speed varies with request size and provider.

Provider	Context	Input	Output
OpenRouter`openrouter/google/gemma-4-31b-it`	262K	$0.09/M	$0.34/M
Featherless`featherless_ai/google/gemma-4-31B-it`	33K	$0.12/M	$0.36/M
NovitaSave 10%`novita/google/gemma-4-31b-it`	262K	$0.13/M	$0.36/M
FriendliAI`friendliai/google/gemma-4-31B-it`	262K	$0.14/M	$0.40/M
Parasail`parasail/google/gemma-4-31B`	262K	$0.15/M	$0.40/M
Parasail`parasail/google/gemma-4-31b-it`	262K	$0.15/M	$0.40/M
Parasail`parasail/google/gemma-4-31B-it`	262K	$0.15/M	$0.40/M
Parasail`parasail/parasail-gemma-4-31b-it`	262K	$0.15/M	$0.40/M
DeepInfra`deepinfra/google/gemma-4-31B-it`	262K	$0.20/M	$0.40/M
TogetherAIBYOK only`together_ai/google/gemma-4-31B-it`	262K	$0.39/M	$0.97/M

Gemma 4 31B

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Time to first token

Response latency

Apps

Gemma 4 31B FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.