Gemini 3.8 Flash
google/gemini-3.8-flashCopy model IDReads text and images, writes text, and can think before it answers.
2
providers
35.2K
tokens through FluxA, last 90 days
Quick start
OpenAI chat completionsCopy request
curl https://router.fluxapay.xyz/llm/v1/chat/completions \
-H "Authorization: Bearer $MONETIZE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"google/gemini-3.8-flash","messages":[{"role":"user","content":"Hello"}]}'No provider in the path, so each call goes to the cheapest provider serving this format.
Providers and prices
Per 1M tokens, in USDCalls without a provider in the path go to the cheapest provider.
| Provider | Input | Output | Cache read | Cache write 5m | Route |
|---|---|---|---|---|---|
| AIHubMix | $0.75 | $3.75 | $0.07 | — | Default route |
| UnifyLLM | $0.82 | $4.12 | $0.08 | $0.04 | /llm/unify-llm/v1/... |
Capabilities
- Input
- Text, Vision
- Output
- Text
- Thinking
- Supported
- Formats
- OpenAI chat completions