GLM 5.2 API

GLM 5.2 is a large language model by Z.ai, available on the Venice API as zai-org-glm-5-2. Private and end-to-end encrypted variants are available.GLM-5.2 is the next-generation large language model developed by Zhiyuan AI, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports large context windows for processing extensive text and detailed analysis with fast inference speed.

GLM 5.2 API pricing

Model ID	Variant	Privacy	Price
`zai-org-glm-5-2`	Standard	Private	$1.40 input /$ 4.40 output per 1M tokens
`e2ee-glm-5-2-p`	E2EE	End-to-end encrypted	$1.75 input /$ 5.75 output per 1M tokens

GLM 5.2 specifications

Spec	Value
Provider	Z.ai
Released	Jun 16, 2026
Privacy	Private, End-to-end encrypted
Open weights	Yes
Context window	1M tokens
Max output	128K tokens
Reasoning effort	none, high, max
Served precision	FP8

How to use the GLM 5.2 API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "zai-org-glm-5-2" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org-glm-5-2",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
    "reasoning_effort": "max"
  }'

GLM 5.2 API FAQ

How much does the GLM 5.2 API cost?

1.40 per 1M input tokens and

4.40 per 1M output tokens, with cached input at

0.26 per 1M. The E2EE variant costs

1.75 input and $5.75 output. Prices are in USD and can be paid in DIEM at parity.

What is the GLM 5.2 model ID?

Use zai-org-glm-5-2 as the model parameter. Other variants: e2ee-glm-5-2-p (E2EE).

Is the GLM 5.2 API private?

The Standard variant is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training. The E2EE variant is end-to-end encrypted: prompts are encrypted on your device and decrypted only inside an attested hardware enclave, so neither Venice nor the GPU provider can read them.

What is the context window of GLM 5.2?

1M tokens of context, with up to 128K output tokens per response.

What does GLM 5.2 support?

GLM 5.2 supports function calling, structured outputs, reasoning, web search and prompt caching. Reasoning effort is adjustable with reasoning_effort: none, high and max (default max).

Which endpoint does the GLM 5.2 API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

GLM 5.3 API: $1.75 input /$ 5.50 output per 1M tokens
GLM 5.1 API: $1.54 input /$ 4.84 output per 1M tokens
GLM 5 API: $1.00 input /$ 3.20 output per 1M tokens
GLM 4.7 API: $0.55 input /$ 2.65 output per 1M tokens
GLM 4.6 API: $0.43 input /$ 1.75 output per 1M tokens
Inkling API: $1.25 input /$ 5.06 output per 1M tokens
DeepSeek V4 Pro API: $1.65 input /$ 3.30 output per 1M tokens
GPT-5.4 Mini API: $0.94 input /$ 5.63 output per 1M tokens
Gemini 3.6 Flash API: $0.94 input /$ 4.69 output per 1M tokens

Explore

By modality