TokenSpend
All models

Alibaba

Qwen3.8 2.4T A95B

open weights

Model id

qwen/qwen3.8-2.4t-a95b
Try in playgroundGet API key
Input
$2
per M tokens
Output
$6
per M tokens
Cache read
$0.2
per M tokens
Context
256K
tokens

Provider list price

Pricing

Input$2 / M tokens
Output$6 / M tokens
Cache read$0.2 / 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 2026-08-19.1 · effective 8/19/2026 · Private rate card. Source withheld.

First request

Run it

Python · OpenAI SDK

from openai import OpenAI

client = OpenAI(base_url="https://api.tokenspend.dev/v1", api_key=os.environ["TOKENSPEND_API_KEY"])
resp = client.chat.completions.create(
    model="qwen/qwen3.8-2.4t-a95b",
    messages=[{"role": "user", "content": "hello"}],
)

TypeScript · OpenAI SDK

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.tokenspend.dev/v1", apiKey: process.env.TOKENSPEND_API_KEY });
const resp = await client.chat.completions.create({
  model: "qwen/qwen3.8-2.4t-a95b",
  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":"qwen/qwen3.8-2.4t-a95b","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=qwen/qwen3.8-2.4t-a95b

One request shape reaches every model. Claude Code connects as an integration with two environment variables. Request history included; ZDR is one click away.