Question 1

What is Gemini 3 Flash Preview?

Accepted Answer

Gemini 3 Flash Preview is a model from Google Gemini AI, released on Dec 17, 2025. Gemini 3 Flash is a Google Gemini model for multimodal reasoning, coding, generation, and long-context tasks.

Question 2

How much does Gemini 3 Flash Preview cost?

Accepted Answer

On the Respan gateway, input starts at $0.50 per 1M tokens on every provider, and output starts at $3.00 per 1M tokens on every provider, after gateway discounts.

Question 3

Which providers serve Gemini 3 Flash Preview on Respan?

Accepted Answer

3 providers serve Gemini 3 Flash Preview: Inference.net, OpenRouter, and Perplexity. Perplexity requires your own provider API key (BYOK).

Question 4

What is Gemini 3 Flash Preview's context window?

Accepted Answer

Gemini 3 Flash Preview accepts up to 1.0M tokens of context on its largest provider route.

Question 5

How do I use Gemini 3 Flash Preview 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 "gemini-3-flash-preview". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Gemini 3 Flash Preview?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Inference.net at 14 tokens per second, and the lowest response latency was 1.9 seconds on Inference.net. Speed varies with request size and provider.

Question 7

Where does Gemini 3 Flash Preview rank on the Respan Index?

Accepted Answer

Gemini 3 Flash Preview scores 38.6 out of 100 on the Respan Index v1.1, ranking #49 of 138 models. By category: Coding 11.8, Agents 50.7, Reasoning 34.4, Knowledge & language 66.7, and Human preference 51.3. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does Gemini 3 Flash Preview score on benchmarks?

Accepted Answer

Gemini 3 Flash Preview has 31 published benchmark scores, including SWE-bench Verified 78%, tau2-bench Telecom 91.2%, and GPQA Diamond 90.4%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
Inference.net`inference_net/gemini-3-flash-preview`	1.0M	$0.50/M	$3.00/M
OpenRouter`openrouter/google/gemini-3-flash-preview`	1.0M	$0.50/M	$3.00/M
PerplexityBYOK only`perplexity/google/gemini-3-flash-preview`	1.0M	$0.50/M	$3.00/M

Gemini 3 Flash Preview

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Indexv1.1

Coding5

Apps