Zai Glm 5.2
zai-glm-5-2Pricing
List prices at Mistral AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.40 | $4.40 | |
| Cached input 90% off input | $0.14 | 90% off input |
What it costs a month
At Mistral AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$637
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$528
- Coding agent1,000 requests a day, 40K in / 2K out, cached$886
- Overnight batch20,000 requests a day, 4K in / 0.4K out$4,416
Where to run it
1 host serve Zai Glm 5.2. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Mistral AILab API zai-glm-5-2 | $1.40 / $4.40 | zai-glm-5-2 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Effort settings the source lists
- noneminimallowmediumhighxhighmax
- Features
- Assistant prefillPrompt caching
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Mistral AI.
Smaller Mistral AI models
- 89% less
- 88% less
- 88% less
Other frontier labs
- 7% less
- 30% less
- 42% less
- 91% less
Open-weight picks
- 20% less
- 60% less
- 63% less
- 68% less
Model line
Newer and older versions, at each lab's own price.
- UndatedZai Glm 5.3Latest$1.40 / $4.40
- UndatedZai Glm 5.2This page$1.40 / $4.40
- UndatedZai Glm 5$1.40 / $4.40
Call it
Using Mistral AI's API.
from litellm import completion
response = completion(
model="mistral/zai-glm-5-2",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Zai Glm 5.2 cost?
On Mistral AI, Zai Glm 5.2 costs $1.40 per million input tokens and $4.40 per million output tokens. Cached input costs $0.14 per million tokens.
Which APIs offer Zai Glm 5.2?
Zai Glm 5.2 runs on 1 API: Mistral AI.
What is Zai Glm 5.2's context window?
1M tokens, with up to 131K tokens in one reply.
Is Zai Glm 5.2 being retired?
It has been retired: Mistral AI retired it on 31 Oct 2026.
Is there a newer version of Zai Glm 5.2?
Yes. Zai Glm 5.3 is the newest model in this line.
What are cheaper alternatives to Zai Glm 5.2?
Models that cost less and keep most of what it can do: Zai Glm 5.3 Flash on Mistral AI (89% less), GPT-6.1 Terra on OpenAI (7% less), Gemini 3.8 Flash on Google AI Studio (30% less) and Inkling on DeepInfra (20% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Zai Glm 5.2's API model id?
Use zai-glm-5-2 with Mistral AI.
Sources
Raw catalog entry for zai-glm-5-2 on Mistral AI
{
"cache_read_input_token_cost": 1.4e-7,
"deprecation_date": "2026-10-31",
"deprecation_source": "https://docs.mistral.ai/getting-started/models/models_overview",
"input_cost_per_token": 0.0000014,
"litellm_provider": "mistral",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 0.0000044,
"reasoning_effort_levels": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
],
"source": "https://docs.mistral.ai/models/zai-glm-5-2",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
}