Skip to contentLaunch price until December 31 · 45 days left

Gemini 3.8 Flash API

GoogleText, 1M context, answers up to 64K tokens

Google's fast model for long software engineering tasks, autonomous agents and enterprise workflows. 1M tokens of context, OpenAI's chat format, pay per token.

1M tokensOur priceOfficialSaved
  • Input$0.40$0.75−47%
  • Output$2$3.75−47%
One callTikiAPIOfficial
  • A question500 tokens in, 300 out$0.0008$0.0015
  • A long chat10K in, 1K out$0.006$0.0112
  • A document100K in, 2K out$0.044$0.0825
  • A month of a busy bot50M in, 10M out$40.00$75.00

Official: Google's price for Gemini 3.8 Flash until Dec 31, 2026 ($1.50 / $7.50 from Jan 1, 2027), Gemini API pricing, checked on Nov 14, 2026.

API

Call Gemini 3.8 Flash in code.OpenAI's format: change the base URL and the key.

POST /v1/chat/completions

model
gemini-3.8-flash
messages
The conversation: system, user and assistant turns, as in OpenAI's API. Text and images in user turns.
max_tokens
The longest answer, up to 64,000 tokens. 8,192 when not set.
stream
true for server-sent events as the answer is written.
…
temperature, tools, response_format and the rest go to the model as they are.
curl https://api.tikiapi.com/v1/chat/completions   -H "Authorization: Bearer $TIKIAPI_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "gemini-3.8-flash",
    "messages": [
      {
        "role": "user",
        "content": "Turn this into a JSON object with name, date and amount: Paid Alex Kim $420 on March 3 for design work."
      }
    ],
    "max_tokens": 1024
  }'

Overview

What Gemini 3.8 Flash is good at.Google's most capable Flash model, built for agents and long software tasks.

  • Fast

    Quick answers for live features and big batches.

  • Agents

    Plans and acts across many steps.

  • 1M-token context

    Long documents, logs and code in one call.

  • Pay per token

    Input and output priced per million. No plan.

Use cases

  • Agents

    Workflows that call your tools.

  • Software tasks

    Changes, tests and reviews.

  • Batch work

    Many documents processed fast.

  • Apps and automation

    Gemini inside your product, bot or pipeline.

FAQ

Gemini 3.8 Flash API questions

Something else? Read the docs

How much does the Gemini 3.8 Flash API cost?

$0.40 per million input tokens and $2 per million output tokens. A question of 500 tokens with a 300-token answer costs $0.0008. No subscription, nothing upfront.

Does it work with the OpenAI SDK?

Yes. Point the SDK at https://api.tikiapi.com/v1, use your TikiAPI key and the model id gemini-3.8-flash. The request and the answer have OpenAI's chat completions format, streaming included.

How long can an answer be?

Up to 64,000 tokens, set with max_tokens. Without it the answer is capped at 8,192 tokens.

What if a call fails?

It costs nothing. You pay for the tokens of an answer you get, never for an error.

Try Gemini 3.8 Flash today.

No subscription. Pay per use.