GLM 4.5
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens.
glm-4.5Released 25 Jul 2025 (Jul 2025)Pricing
List prices at Z.ai, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.60 | $2.20 |
What it costs a month
At Z.ai list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$345
- RAG over documents2,000 requests a day, 8K in / 0.6K out$367
- Coding agent1,000 requests a day, 40K in / 2K out$852
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,968
Where to run it
6 hosts serve GLM 4.5. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Z.aiLab API glm-4.5 | $0.60 / $2.20 | glm-4.5 | |
DeepInfraInference GLM-4.5 | $0.40 / $1.60 −30% vs headline | GLM-4.5 | |
Fireworks AIInference glm-4p5 | $0.55 / $2.19 −4% vs headline | glm-4p5 | |
GMI CloudInference GLM-4.5-FP8 | $0.60 / $2.20 | GLM-4.5-FP8 | |
Novita AIInference glm-4.5 | $0.60 / $2.20 | glm-4.5 | |
Vercel AI GatewayGateway glm-4.5 | $0.60 / $2.20 | glm-4.5 |
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
- Open weights
- License: MITRuns in about 860 GB of GPU memory
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
- DeepInfra30% lessGLM-4.5$0.40 / $1.60
- Fireworks AI4% lessglm-4p5$0.55 / $2.19
Smaller Zhipu AI models
- 90% less
Other frontier labs
- 15% less
- 54% less
- 80% less
- 80% less
Open-weight picks
- 13% less
- 14% less
- 19% less
- 21% less
Model line
Newer and older versions, at each lab's own price.
Call it
Using Z.ai's API.
from litellm import completion
response = completion(
model="zai/glm-4.5",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GLM 4.5 cost?
On Z.ai, GLM 4.5 costs $0.60 per million input tokens and $2.20 per million output tokens. The cheapest host is DeepInfra, at $0.40 per million input tokens and $1.60 per million output tokens.
Which APIs offer GLM 4.5?
GLM 4.5 runs on 6 APIs: Z.ai, DeepInfra, Fireworks AI, GMI Cloud, Novita AI and Vercel AI Gateway.
What is GLM 4.5's context window?
128K tokens, with up to 32K tokens in one reply.
Is GLM 4.5 being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of GLM 4.5?
Yes. GLM 5.3 is the newest model in this line, released on 18 Aug 2026.
What are cheaper alternatives to GLM 4.5?
Models that cost less and keep most of what it can do: GLM 4 32B 128K on Z.ai (90% less), Gemini 3.5 Flash Lite on Google AI Studio (15% less), GPT-5.4 Nano on OpenAI (54% less) and Motif 3 on ai& (13% less). GLM 4.5 itself costs 30% less on DeepInfra. Savings are on a mix of 3 input tokens to 1 output token.
When was GLM 4.5 released?
Zhipu AI released it on 25 Jul 2025.
What is GLM 4.5's API model id?
Use glm-4.5 with Z.ai. Other hosts use their own ids: GLM-4.5 on DeepInfra, glm-4p5 on Fireworks AI, GLM-4.5-FP8 on GMI Cloud.
Sources
Raw catalog entry for glm-4.5 on Z.ai
{
"input_cost_per_token": 6e-7,
"output_cost_per_token": 0.0000022,
"litellm_provider": "zai",
"max_input_tokens": 128000,
"max_output_tokens": 32000,
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
}