gemini-3.8-flash) is the multimodal text model Google put out on September 2, 2026, taking text, image, video and audio input. APIYI has both the Gemini native and OpenAI-compatible endpoints open, and ran 150 paired test cases across both protocols before launch, using gemini-3.7-flash as the reference.
Gemini 3.8 Flash is live on APIYI: model name
gemini-3.8-flash, available in the default and svip groups. Deep thinking is on by default and thinking tokens bill as output, so lower the thinking tier or turn it off for latency- and cost-sensitive paths (see “Thinking control” below).Why it stands out
Half the price of 3.6 Flash
$0.75 in / $3.75 out per 1M tokens — half of 3.6 Flash ($1.50 / $7.50), and line-for-line identical to 3.7 Flash, so migrating from 3.7 costs nothing.
150 pre-launch test cases
Fired simultaneously against 3.7 Flash across both protocols: core capability, reasoning, parallel tool calling and image/video understanding all line up, with no regression unique to 3.8.
Both endpoints, no friction
Gemini native format (official SDK, no Google API key needed) and OpenAI-compatible format (just change base_url) are both open.
Near-zero migration cost
From 3.7 Flash it is a one-line model name change: request shape, parameters and response fields are unchanged, with one field-set difference and zero type changes measured.
Model information
Measured capability matrix
Results from APIYI testing on September 2, 2026 — 150 case logs and 198 calls, with every case fired simultaneously againstgemini-3.7-flash to rule out time-of-day effects:
Pricing
Line-for-line identical to
gemini-3.7-flash, so migrating from 3.7 changes nothing about your costs; against 3.6 Flash ($1.50 / $7.50) it is a straight halving.
On pricing: thinking tokens bill as output — that is the most direct reason to manage the thinking tier. Google has not published official pricing for 3.8 Flash; for reference, the $0.75 / $3.75 currently in effect for 3.7 Flash is Google’s own limited-time promotional rate, stated as valid through December 31, 2026. APIYI prices match the provider line for line, with discounts coming through top-up bonuses — see top-up promotions.
Thinking control
Deep thinking is on by default: even a “1+1” prompt burns a few hundred thinking tokens first. Measured across the three tiers (same question, native endpoint):Examples
Gemini native format (recommended, broader tool support)
OpenAI-compatible format (no changes to existing code)
Migration guide
Coming from gemini-3.7-flash
Coming from gemini-3.7-flash
Change the model name, nothing else. Request shape, parameters and response fields tested unchanged; response field sets differ in one group with zero type changes, so clients need no adaptation. Pricing is identical, so your existing budget carries over.
Coming from gemini-3.6-flash
Coming from gemini-3.6-flash
The price is cut in half (input $1.50 → $0.75, output $7.50 → $3.75), but one thing must change:
thinkingLevel: "minimal" is no longer supported and the native endpoint returns 400 — switch to thinkingConfig: {"thinkingBudget": 0}. On the OpenAI-compatible endpoint, reasoning_effort: "minimal" will not error but is silently ignored while thinking still bills, so fix that too.What is the context limit?
What is the context limit?
Not published by Google, and we will not infer it from 3.7’s number. A long-context lookup task with a 14.5K-character prefix passed in testing. If you lean heavily on long context, ramp on a slice of traffic first, confirm the boundary, then cut over. This page will be updated once official specs land.
Does the native endpoint need a Google API key?
Does the native endpoint need a Google API key?
No. Put your APIYI key (starting with
sk-) straight into the x-goog-api-key header; with the official google-genai SDK just point base_url at https://api.apiyi.com.Which capabilities are native-only?
Which capabilities are native-only?
Code execution, URL context,
safetySettings, and strict handling of stopSequences and seed are available only on the Gemini native endpoint. The OpenAI-compatible endpoint covers the usual ground (chat / streaming / function calling / JSON Schema / vision), but stop and seed tested as having no effect there.