TokenSpend
All models

Google

Gemini 3.8 Flash

images

Model id

google/gemini-3.8-flash
Try in playgroundGet API key
Input
$0.75
per M tokens
Output
$3.75
per M tokens
Cache read
$0.075
per M tokens
Context
1,048.576K
tokens

Registry contract

Capabilities

Protocols
3
Chat · Responses · Messages · streaming
Tools
None
Not supported
JSON Schema
None
Not supported
Vision
Yes
Chat · Responses · Messages
Reasoning
None
No public control
Output limit
65,536
tokens
Input limit
1,048,576
tokens

canonical google/gemini-3.8-flash · revision google/gemini-3.8-flash · aliases gemini-3.8-flash

Provider list price

Pricing

Input$0.75 / M tokens
Output$3.75 / M tokens
Cache read$0.075 / M tokens
RoutingFree

Provider list price. BYOK bills your provider; managed credits draw down at these rates. No markup or request fee. Every request is metered per engineer and joined to shipped work.

Registry 2026-09-15.1 · effective 9/15/2026 · Gemini API pricing

First request

Run it

Python · TokenSpend SDK

from tokenspend import TokenSpend

client = TokenSpend()
resp = client.chat.completions.create(
    model="google/gemini-3.8-flash",
    messages=[{"role": "user", "content": "hello"}],
)

TypeScript · TokenSpend SDK

import { TokenSpend } from "@tokenspend/sdk";

const client = new TokenSpend();
const resp = await client.chat.completions.create({
  model: "google/gemini-3.8-flash",
  messages: [{ role: "user", content: "hello" }]
});

curl

curl https://api.tokenspend.dev/v1/chat/completions \
  -H "content-type: application/json" \
  -H "Authorization: Bearer $TOKENSPEND_API_KEY" \
  -d '{"model":"google/gemini-3.8-flash","messages":[{"role":"user","content":"hello"}]}'

Claude Code integration

export ANTHROPIC_BASE_URL=https://api.tokenspend.dev
export ANTHROPIC_API_KEY=$TOKENSPEND_API_KEY
export ANTHROPIC_MODEL=google/gemini-3.8-flash

One request shape reaches every model. Claude Code connects as an integration with two environment variables. Prompts are not stored unless you enable request logging.