GLM 5.3
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
glm-5.3Released 18 Aug 2026 (Aug 2026)Pricing
List prices at Z.ai, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.40 | $4.40 | |
| Cached input 81% off input | $0.26 | 81% off input | |
| Cache write, 5 minutes | $0.00 |
What it costs a month
At Z.ai list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$647
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$557
- Coding agent1,000 requests a day, 40K in / 2K out, cached$986
- Overnight batch20,000 requests a day, 4K in / 0.4K out$4,416
Where to run it
25 hosts serve GLM 5.3. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Z.aiLab API glm-5.3 | $1.40 / $4.40 | glm-5.3 | |
CLF AI GatewayCloud glm-5.3 | $0.56 / $1.76 −60% vs headline | glm-5.3 | |
GMI CloudInference GLM-5.3 | $0.70 / $2.20 −50% vs headline | GLM-5.3 | |
W&B InferenceInference GLM-5.3 | $0.75 / $3.00 −39% vs headline | GLM-5.3 | |
SailCloud GLM-5.3 | $0.98 / $3.08 −30% vs headline | GLM-5.3 | |
SCX.aiCloud GLM-5.3 | $0.98 / $3.08 −30% vs headline | GLM-5.3 | |
ai&Cloud glm-5.3 | $1.00 / $4.00 −19% vs headline | glm-5.3 | |
Kyma APICloud glm-5.3 | $1.18 / $3.70 −16% vs headline | glm-5.3 | |
AIHubMixGateway glm-5.3 | $1.13 / $3.94 −15% vs headline | glm-5.3 | |
BigModel (Zhipu AI)Cloud glm-5.3 | $1.14 / $4.00 −14% vs headline | glm-5.3 | |
FriendliAIInference GLM-5.3 | $1.26 / $3.96 −10% vs headline | GLM-5.3 | |
CoralBricksCloud glm-5.3 | $1.12 / $4.40 −10% vs headline | glm-5.3 | |
DatabricksCloud databricks-glm-5-3 | $1.40 / $4.40 | databricks-glm-5-3 | |
StreamLakeCloud GLM-5.3 | $1.40 / $4.40 | GLM-5.3 | |
EmpirioLabs AICloud glm-5-3 | $1.40 / $4.40 | glm-5-3 | |
OpenCode GoCloud glm-5.3 | $1.40 / $4.40 | glm-5.3 | |
Tencent TokenHubCloud glm-5.3 | $1.40 / $4.40 | glm-5.3 | |
BasetenInference GLM-5.3 | $1.40 / $4.40 | GLM-5.3 | |
Nebius AI StudioInference GLM-5.3 | $1.40 / $4.40 | GLM-5.3 | |
Together AIInference GLM-5.3 | $1.40 / $4.40 | GLM-5.3 | |
Novita AIInference glm-5.3 | $1.40 / $4.40 | glm-5.3 | |
Fireworks AIInference glm-5p3 | $1.40 / $4.40 | glm-5p3 | |
PerplexityGateway glm-5.3 | $1.40 / $4.40 | glm-5.3 | |
| $1.68 / $5.28 +20% vs headline | global.zai.glm-5.3 | ||
Inference APIsGateway GLM-5.3 | $1.82 / $5.72 +30% vs headline | GLM-5.3 |
Show 3 more listings: regions, snapshots and variantsHide regional listings
| Fireworks AI | |||||||
| Alias glm-5p3 | $1.40 / $4.40 | glm-5p3 | |||||
| Amazon Bedrock | |||||||
| us us.zai.glm-5.3 | $1.85 / $5.81 +32% vs headline | us.zai.glm-5.3 | |||||
| Inference APIs | |||||||
| Alias glm-5.3 | $1.82 / $5.72 +30% vs headline | glm-5.3 | |||||
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
- Features
- Prompt caching
- Open weights
- License: otherRuns in about 1808 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
- CLF AI Gateway60% lessglm-5.3$0.56 / $1.76
- GMI Cloud50% lessGLM-5.3$0.70 / $2.20
- W&B Inference39% lessGLM-5.3$0.75 / $3.00
- Sail30% lessGLM-5.3$0.98 / $3.08
- SCX.ai30% lessGLM-5.3$0.98 / $3.08
Smaller Zhipu AI models
- 12% less
Other frontier labs
- 7% less
- 30% less
- 42% less
- 91% less
Open-weight picks
- 1% less
- 20% less
- 63% less
- 68% 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-5.3",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GLM 5.3 cost?
On Z.ai, GLM 5.3 costs $1.40 per million input tokens and $4.40 per million output tokens. Cached input costs $0.26 per million tokens. The cheapest host is CLF AI Gateway, at $0.56 per million input tokens and $1.76 per million output tokens.
Which APIs offer GLM 5.3?
GLM 5.3 runs on 25 APIs: Z.ai, CLF AI Gateway, GMI Cloud, W&B Inference, Sail, SCX.ai, ai&, Kyma API, AIHubMix and 16 more.
What is GLM 5.3's context window?
1M tokens, with up to 128K tokens in one reply.
Is GLM 5.3 being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of GLM 5.3?
No. GLM 5.3 is the newest model in its line.
What are cheaper alternatives to GLM 5.3?
Models that cost less and keep most of what it can do: GLM 5v Turbo on Z.ai (12% less), GPT-6.1 Terra on OpenAI (7% less), Gemini 3.8 Flash on Google AI Studio (30% less) and Qwen4 Max on Together AI (1% less). GLM 5.3 itself costs 60% less on CLF AI Gateway. Savings are on a mix of 3 input tokens to 1 output token.
When was GLM 5.3 released?
Zhipu AI released it on 18 Aug 2026.
What is GLM 5.3's API model id?
Use glm-5.3 with Z.ai. Other hosts use their own ids: GLM-5.3 on GMI Cloud, GLM-5.3 on W&B Inference, GLM-5.3 on Sail, GLM-5.3 on SCX.ai.
Sources
- Baseten pricing
- FriendliAI pricing
- GMI Cloud pricing
- Inference APIs pricing
- Nebius AI Studio pricing
- Sail pricing
- SCX.ai pricing
- StreamLake pricing
- Together AI pricing
- W&B Inference pricing
- Databricks pricing
- EmpirioLabs AI pricing
- ai& pricing
- AIHubMix pricing
- BigModel (Zhipu AI) pricing
- CLF AI Gateway pricing
- CoralBricks pricing
- Novita AI pricing
- OpenCode Go pricing
- Perplexity pricing
- Tencent TokenHub pricing
- Z.ai pricing
- Fireworks AI pricing
- Amazon Bedrock pricing
- LiteLLM model map
Raw catalog entry for glm-5.3 on Z.ai
{
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-7,
"input_cost_per_token": 0.0000014,
"litellm_provider": "zai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.0000044,
"source": "https://docs.z.ai/guides/overview/pricing",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
}