Apply your own routing policies, reduce token costs automatically, and see every routing decision in real time with Merge Gateway.
What GLM-5.2 costs to run
| Vendor | Input / 1M tokens | Output / 1M tokens | Zero data retention |
| --- | ---: | ---: | --- |
| Baseten | $1.50 | $4.50 | Yes |
| Fireworks AI | $1.40 | $4.40 | Yes |
| Together AI | $1.40 | $4.40 | Yes |
| Z.AI | $1.05 | $3.30 | No |
Test GLM-5.2
with Gateway’s Simulator
See a prompt's output, token spend, latency, and more with GLM-5.2.
Route requests to GLM-5.2 in minutes
To get started in seconds, add our Gateway Implementation skill to your project, or pick your preferred SDK below. Check out our other quick start skills here.
Install the Merge Gateway SDK
Python
1$ pip install merge-gateway-sdkSend a request
Python
1from merge_gateway import MergeGateway
2
3client = MergeGateway(api_key="YOUR_API_KEY")
4
5response = client.responses.create(
6 model="openai/gpt-5.2",
7 input=[
8 {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
9 {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
10 ],
11)
12
13print(response.output[0].content[0].text)Try a diffrent model
Swap the model string to route to a different provider. No other code changes needed.
Anthropic
1response = client.responses.create(
2 model="anthropic/claude-sonnet-4-20250514",
3 input=[
4 {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5 {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6 ],
7)Point to Gateway
Python
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="YOUR_API_KEY",
5 base_url="https://api-gateway.merge.dev/v1/openai",
6)Send a request
Use the standard chat.completions.create method. No provider prefix needed on the model name.
Python
1response = client.chat.completions.create(
2 model="gpt-5.2",
3 messages=[
4 {"role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5 {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6 ],
7)
8
9print(response.choices[0].message.content)Install packages
1npm install merge-gateway-ai-sdk-provider aiCreate the provider
TypeScript
1import { createMergeGateway } from "merge-gateway-ai-sdk-provider";
2
3const gateway = createMergeGateway({
4 apiKey: "YOUR_API_KEY",
5});Send a request
Use generateText to send a request. Model names use the provider/model format.
TypeScript
1import { generateText } from "ai";
2
3const { text } = await generateText({
4 model: gateway("openai/gpt-4o"),
5 prompt: "Explain the concept of recursion in programming with a simple set of examples.",
6});
7
8console.log(text);If you already have @ai-sdk/openai installed, point it at Gateway with a base URL change:
TypeScript
1import { createOpenAI } from "@ai-sdk/openai";
2
3const gateway = createOpenAI({
4 apiKey: "YOUR_API_KEY",
5 baseURL: "https://api-gateway.merge.dev/v1/ai-sdk",
6});
7
8// All generateText/streamText calls work unchangedInstall the Merge Gateway SDK
Anthropic SDK
1from anthropic import Anthropic
2
3client = Anthropic(
4 api_key="YOUR_API_KEY",
5 base_url="https://api-gateway.merge.dev/v1/anthropic",
6)
7
8message = client.messages.create(
9 model="claude-sonnet-4-20250514",
10 max_tokens=1024,
11 messages=[
12 {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
13 ],
14)
15
16print(message.content[0].text)Explore other models available in Merge Gateway
GLM-5.2 FAQ
Have other questions about GLM-5.2? We've answered a few more below. Note that this was written in July, 2026 and is subject to change.
Heading
What other models does Z.ai offer?
Z.ai's GLM family spans text reasoning flagships, fast tiers, and multimodal models. Here are some other models Z.ai supports:
- GLM-5: the earlier text reasoning flagship, a large Mixture-of-Experts model for complex, long-horizon tasks
- GLM-5.1: the prior update in the GLM-5 line, between GLM-5 and GLM-5.2 in capability
- GLM-5-Turbo: the speed-and-cost-optimized tier of the GLM-5 line for interactive, high-volume workloads
- GLM-4.6: a prior-generation general model, still useful for less demanding tasks
How does GLM-5.2 differ from Z.ai's other models?
GLM-5.2 is the latest text reasoning flagship in the GLM-5 line, updating GLM-5 and GLM-5.1 for complex, long-horizon work.
- Architecture: a large Mixture-of-Experts model that activates a subset of experts per token, keeping inference efficient at flagship scale
- Reasoning focus: tuned for multi-step reasoning, coding, and agentic tool use, the hardest tasks in the lineup
- Position vs GLM-5-Turbo: higher quality at higher cost and latency, where Turbo trades quality for speed
- Position vs GLM-4.6: a generational step up in reasoning over the prior GLM-4 line
Reach for GLM-5.2 when you need Z.ai's strongest reasoning for complex, long-horizon, or agentic tasks rather than a fast, cheap tier.
What models should I consider using alongside GLM-5.2?
No single model is optimal for every task. Here are models worth pairing with GLM-5.2 depending on what your product needs:
- Claude Opus 4.8 for the hardest reasoning or coding tasks where you want a frontier cross-provider option
- Gemini 3.1 Pro for long-context or multimodal reasoning that GLM-5.2 isn't aimed at
- DeepSeek V4 Pro as another strong reasoning model to benchmark against on your problems
- Qwen3 Max as an alternative large general model for cross-provider comparison
- GLM-5-Turbo for the high-volume, interactive steps where flagship reasoning is unnecessary
What are the challenges of using GLM-5.2 in my product?
Like any production LLM, GLM-5.2 comes with tradeoffs worth planning for:
- Reasoning verbosity: flagship reasoning generates more thinking tokens, which raises latency and token counts for simple requests
- Provider dependency: relying only on Z.ai creates fragility during outages or model retirements
- Cost at scale: flagship-tier output pricing compounds quickly at high volume without active budgeting
- Data residency and procurement: Z.ai is a China-based provider, which can raise data-governance or vendor-approval questions for some enterprises
- Task fit: flagship reasoning is overkill for classification or short extraction, so route those to a cheaper tier
Why should I use Merge Gateway to route LLM requests with GLM-5.2 and every other model?
Routing GLM-5.2 through Merge Gateway pairs the model with the infrastructure you'd otherwise build yourself:
- One API, every provider: Call GLM-5.2 and every other major model from a single endpoint and key, switching models with a string change rather than a code change
- Intelligent routing and automatic failover: Merge fails over around Z.ai outages on its own, and routing on cost, latency, or quality can lower spend by 40 to 60% with no code edits
- Cost governance: Cap GLM-5.2 spend with project budgets, and see every request attributed by model, project, and tag in one cross-provider dashboard
- Build Your Own Router: Define "best" for your traffic with curated benchmarks or your own evals, and let the router choose per request and explain why
- Security and compliance controls: Run DLP and prompt injection checks before requests reach Z.ai, and enforce per-project model and region rules centrally
How can I start routing requests to GLM-5.2 via Merge Gateway?
Getting GLM-5.2 running through Merge Gateway takes a few minutes:
1. Create an account and get your API key from the dashboard.
2. Install the Merge Gateway SDK: run pip install merge-gateway-sdk (Python) or npm install merge-gateway-sdk (Node). Alternatively, if you're already using the OpenAI SDK, set base_url = "https://api-gateway.merge.dev/v1/openai" and your existing code works as-is.
3. Make your first request using the provider/model format. For GLM-5.2, the model string is zhipu/glm-5.2 (confirm the exact slug in the dashboard). Swap the model string to route to any other provider without changing anything else.
4. Configure a routing policy in the dashboard to set failover behavior, cost limits, and optimization strategy. Your first policy can be as simple as naming GLM-5.2 as primary with one fallback.
Full setup instructions and SDK references are in the Merge Gateway docs.
Try GLM-5.2 through Merge Gateway
Route, observe, and control AI requests across providers from one API.
