Home/Models/Gemini 3.8 Flash
MODEL DOSSIER / ENGLISH

Gemini 3.8 Flash

gemini-3.8-flash

Googletext2026-09-02

Gemini 3.8 Flash is a text model from Google. The snapshot records a release date of 2026-09-02. Context window: 1.04858M tokens. Maximum output: 65.536K tokens. Input: text, images, video, audio, PDF. Output: text. Capabilities recorded: reasoning, tool calls.

Directory snapshot 2026-10-26 · Chinese dossier: 完整中文页

Context1.04858M
Max output65.536K
Inputtext, images, video, audio, PDF
Outputtext
Official input—
Official output—
Capabilitiesreasoning, tool calls
Release2026-09-02

Official list price

CNY / 1M TOKENS

The snapshot does not record an official list price for this model. We do not estimate one. Ask the provider or read the relay's own pricing page before budgeting.

Relay coverage

NONE IN SNAPSHOT

None of the sites in our current public snapshot listed this model ID. That does not mean no relay offers it; it means we have no listing to show. If you find one, the detection page can test it.

How to verify this model on a relay

THREE STEPS
  1. Send a short request to the relay and read the model field in the response. It must match the ID you sent; a different ID is a mapping, not necessarily a substitution.
  2. Run the same prompt against a known-good endpoint and compare prompt-token counts. A large, repeatable gap points at a different tokenizer or a different backend.
  3. Run the seven checks. Billing, context retention, error shape, parameter compliance, tools, and streaming each produce evidence you can quote.

Same publisher

Google

Questions

FAQ

What is the context window of Gemini 3.8 Flash?

The snapshot records 1,048,576 tokens.

How much does Gemini 3.8 Flash cost?

The snapshot records no official price. No relay price is recorded either.

Is a relay really serving Gemini 3.8 Flash?

A model ID in a response is not proof. The seven-check detection compares tokenizer ratios, billing, error shape, parameter compliance, tools, and streaming against the advertised family. Run it on a key you can afford to spend, and treat one run as a spot check, not 24/7 monitoring.

Specifications and prices come from the 2026-10-26 public directory snapshot. We do not publish IQ scores or structured-output claims for models where we have no reliable data.