GLM 5.3 Flash

curl https://a.tokener.ca/v1/chat/completions \  -H "Authorization: Bearer $TOKENER_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "glm-5.3:flash",    "messages": [{"role": "user", "content": "Hello!"}],    "stream": true  }'

import osfrom openai import OpenAI client = OpenAI(    base_url="https://a.tokener.ca/v1",    api_key=os.environ["TOKENER_API_KEY"],) stream = client.chat.completions.create(    model="glm-5.3:flash",    messages=[{"role": "user", "content": "Hello!"}],    stream=True,)for chunk in stream:    print(chunk.choices[0].delta.content or "", end="")

import OpenAI from "openai"; const client = new OpenAI({  baseURL: "https://a.tokener.ca/v1",  apiKey: process.env.TOKENER_API_KEY,}); const stream = await client.chat.completions.create({  model: "glm-5.3:flash",  messages: [{ role: "user", content: "Hello!" }],  stream: true,});for await (const chunk of stream) {  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");}

import { createOpenAICompatible } from "@ai-sdk/openai-compatible";import { streamText } from "ai"; const tokener = createOpenAICompatible({  name: "tokener",  baseURL: "https://a.tokener.ca/v1",  apiKey: process.env.TOKENER_API_KEY,}); const result = streamText({  model: tokener.chatModel("glm-5.3:flash"),  messages: [{ role: "user", content: "Hello!" }],}); for await (const text of result.textStream) {  process.stdout.write(text);}

import osfrom anthropic import Anthropic client = Anthropic(    base_url="https://a.tokener.ca",    api_key=os.environ["TOKENER_API_KEY"],) with client.messages.stream(    model="glm-5.3:flash",    max_tokens=4096,    messages=[{"role": "user", "content": [{"type": "text", "text": "Hello!"}]}],) as stream:    for text in stream.text_stream:        print(text, end="")

# Point Claude Code at Tokener, then start it in your project directory.export ANTHROPIC_BASE_URL=https://a.tokener.ca            # no /v1 — the tool appends itexport ANTHROPIC_AUTH_TOKEN=$TOKENER_API_KEY              # your Tokener API keyexport ANTHROPIC_MODEL=glm-5.3:flash                         # the main modelexport ANTHROPIC_DEFAULT_HAIKU_MODEL=glm-5.3:flash           # background calls — a cheaper model from /models also worksexport ANTHROPIC_SMALL_FAST_MODEL=glm-5.3:flashunset ANTHROPIC_API_KEYclaude