glm-5.2Zhipu GLM-5.2 — a reasoning model with strong function-calling / tool-use, served via the OpenAI-compatible chat-completions endpoint. Supports prompt caching, with cache hits billed at $0.26 / 1M input tokens.
View complete API reference with all parameters and examples.
View complete API reference with streaming, thinking, and more.
Billing: Cost = (input_tokens * input_price + output_tokens * output_price) / 1,000,000
Strong multi-step reasoning
Reliable function calling for agents
Call via /v1/chat/completions
Cache hits billed at $0.26 / 1M input — same as official
GLM-5.2 is a Large Language Model API provided by Zhipu. Zhipu GLM-5.2 — a reasoning model with strong function-calling / tool-use, served via the OpenAI-compatible chat-completions endpoint. Supports prompt caching, with cache hits billed at $0.26 / 1M input tokens. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: Input: $1.26, Output: $3.96 per 1M tokens.
Build intelligent conversational systems to automatically answer user queries and improve service efficiency.
Automatically write articles, emails, ad copy, and other text content to boost productivity.
Assist with code writing, debugging, and code review to accelerate software development.
Understand and analyze unstructured data, extract key insights, and generate summary reports.
GLM-5.2 is available through APIMODELS at: Input: $1.26, Output: $3.96 per 1M tokens. Billing is pay-as-you-go — you only pay for what you generate.
Sign up at APIMODELS, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
APIMODELS offers the same GLM-5.2 model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.
$1.26 per 1M input and $3.96 per 1M output — both 10% below the official $1.40 / $4.40. Cached input is $0.26, matching official exactly (lowered from $0.28 on 26 Aug 2026), so no tier here is priced above Z.ai. Because agent traffic sends most of its input through cache (we measure 83% in production), weighting all three tiers by real usage puts the blended bill about 5% under official. We quote that blended figure rather than the headline 10%, which no real workload actually gets.
5.2 is more affordable ($1.26 / $3.96 against $1.33 / $4.18) and fits shorter, high-volume, price-sensitive work. 5.3 is the newer generation with better coding and token efficiency and a 1M-token context, aimed at multi-step agents and codebase-wide changes. Both sit on the same OpenAI-compatible endpoint, so you can build on 5.2 and switch the model field when a task needs 5.3.
Yes — tool use is what this model is good at. We tested a nested schema with an enum on our own channel: it returned a standard tool_calls structure with directly parseable arguments, and streaming behaved normally. It is a reasoning model, which suits agent orchestration and structured output.
POST https://api.apimodels.app/v1/chat/completions with model set to "glm-5.2", plain OpenAI shape. openai-python and openai-node need only a base_url change, and clients like Cursor and Cline work the same way. /v1/responses is supported too — the gateway bridges it to chat-completions. Add stream:true for streaming.
Prompt caching. A repeated system prompt and conversation history bill at $0.26 per 1M input tokens instead of $1.26 once cached — about a 4.8x difference. In production we see 84% of input tokens landing on the cached tier, so for long conversations and agent loops the effective rate is far below the headline price.
On APIMODELS, GLM-5.2 runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Reasoning, Tool Calling, OpenAI-compatible, Prompt Cache, and you can weigh it on price and capability against other Large Language Model models, then switch by changing a single model-name string — no new account or integration. Browse every Large Language Model option with live pricing at apimodels.app/models.
GLM-5.2 supports: Reasoning, Tool Calling, OpenAI-compatible, Prompt Cache. See the APIMODELS docs for full parameters and call examples.
Yes. APIMODELS exposes GLM-5.2 through a single unified API and one key — no separate provider accounts, and no need to handle each provider's regional network access yourself.
We support Stripe (Visa, Mastercard, and other international cards) and Alipay. Credits are available instantly after payment.