Input
- Official Google
- $0.75
- Here (−50%)
- $0.375
gemini-3.8-flash
Gemini 3.8 Flash API — price per token
Gemini 3.8 Flash is Google's current GA Flash model, available through the native Gemini API with streaming and authoritative token usage.
Pricing per 1M tokens
| Rate | Official Google | Here (−50%) |
|---|---|---|
| Input | $0.75 | $0.375 |
| Cached input | $0.075 | $0.0375 |
| Output | $3.75 | $1.875 |
Cached input
- Official Google
- $0.075
- Here (−50%)
- $0.0375
Output
- Official Google
- $3.75
- Here (−50%)
- $1.875
Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: 1M tokens. Max output: 64K tokens.
Best for
- Text generation and long-context analysis on the current GA Flash generation.
- Incremental SSE responses with terminal authoritative usage.
- Cost-sensitive production traffic during the promotional rate period.
Good to know
- Thinking levels low, medium and high are the official contract and selectable via reasoning_effort; minimal is not supported by this model.
- Function calling, JSON structured output, image/audio/video/PDF input, implicit prompt caching and Google Search grounding are published on the same surface as Gemini 3.7 Flash.
- Promotional official rates run through 2026-12-31; the engine automatically switches to $1.50 input, $0.15 cached input and $7.50 output on 2027-01-01.
How to use Gemini 3.8 Flash
Create a free account, generate one key, and point any Gemini-compatible tool at https://router.apitoken.sale with model ID gemini-3.8-flash — the native /v1beta/models/gemini-3.8-flash:generateContent surface works, authenticated with x-goog-api-key. Eligible new accounts include $5 of platform bonus credit — enough to test the model before topping up. Existing integrations on the legacy host https://gemini.api.apitoken.sale keep working.
Frequently asked questions
What model ID should clients use?
Always use gemini-3.8-flash. apiToken.sale keeps any private upstream routing name internal and returns only this public ID.
How much does Gemini 3.8 Flash cost?
Through 2026 the official promotional rate is $0.75 per 1M input tokens, $0.075 cached input and $3.75 output. The flat 50% apiToken.sale B2C discount makes that $0.375, $0.0375 and $1.875.
Which capabilities are currently published?
Text, image, audio (inline WAV), video (inline MP4) and PDF input, function calling, JSON structured output, implicit prompt caching, Google Search grounding, countTokens and incremental SSE streaming, plus explicit thinking levels low, medium and high through reasoning_effort.
Run Gemini 3.8 Flash on the native Gemini API at a flat 50% off — instant key, prepaid balance, card or crypto.