← All Models
Gemini 3.8 Flash
Google's Gemini 3.8 Flash for long-running coding, agents, and complex workflows. Text, image, audio, video, and PDF input; text output; 1M context and up to 65,536 output tokens including thinking. Adjustable low, medium, or high thinking.
Web Search
Web Fetch
Code Execution
Specifications
| Provider | |
| Category | Text |
| Context window | 1.0M tokens |
Pricing (Starter tier)
97.50 credits / 1M input tokens
487.50 credits / 1M output tokens
Introductory rates through December 31, 2026
Higher tiers get volume discounts. See tiers
Quick Start
curl -N https://query.genx.sh/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gemini-3.8-flash","messages":[{"role":"user","content":"Review this module."}],"reasoning_effort":"high","stream":true}'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
prompt |
string | required | — | Input text prompt |
system_prompt |
string | optional | — | System instructions |
max_tokens |
number | optional | — | 1 to 65536 output tokens including thinking |
reasoning_effort |
string | optional | medium |
low, medium, or high; minimal is not supported |
tools |
array | optional | — | Built-in web_search, web_fetch, or code_execution |
Availability
Gemini 3.8 Flash is available in the GenX Pro App and via the GenX Router API.