GLM 4.7 Flash
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency.
glm-4.7-flashReleased 19 Jan 2026 (Jan 2026)Where to run it
8 hosts serve GLM 4.7 Flash. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Z.aiLab API glm-4.7-flash | - | glm-4.7-flash | |
CLF AI GatewayCloud glm-4.7-flash | $0.024 / $0.16 | glm-4.7-flash | |
DeepInfraInference GLM-4.7-Flash | $0.06 / $0.40 | GLM-4.7-Flash | |
glm-4.7-flash | $0.0605 / $0.40 | glm-4.7-flash | |
Amazon BedrockCloud zai.glm-4.7-flash | $0.07 / $0.40 Retires 30 Mar 2027 | zai.glm-4.7-flash | Retires 30 Mar 2027 |
GMI CloudInference GLM-4.7-Flash | $0.07 / $0.40 | GLM-4.7-Flash | |
Novita AIInference glm-4.7-flash | $0.07 / $0.40 | glm-4.7-flash | |
Kyma APICloud glm-4.7-flash | $0.081 / $0.54 | glm-4.7-flash |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| Mantle zai.glm-4.7-flash | $0.07 / $0.40 Retires 30 Mar 2027 | zai.glm-4.7-flash | Retires 30 Mar 2027 | ||||
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: MITRuns in about 74.9 GB of GPU memory
Similar models
This model has no listed price, so these are current models with similar capabilities.
Smaller Zhipu AI models
Other frontier labs
Open-weight picks
Model line
Newer and older versions, at each lab's own price.
- Aug 2026GLM 5.3 FlashLatest$0.15 / $0.50
- Jan 2026GLM 4.7 FlashThis pageNot listed
- UndatedGLM 4.5 FlashNot listed
Call it
Using Z.ai's API.
from litellm import completion
response = completion(
model="zai/glm-4.7-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GLM 4.7 Flash cost?
Its lowest listed price is at CLF AI Gateway: $0.024 per million input tokens and $0.16 per million output tokens.
Which APIs offer GLM 4.7 Flash?
GLM 4.7 Flash runs on 8 APIs: Z.ai, CLF AI Gateway, DeepInfra, Cloudflare Workers AI, Amazon Bedrock, GMI Cloud, Novita AI and Kyma API.
What is GLM 4.7 Flash's context window?
200K tokens, with up to 128K tokens in one reply.
Is GLM 4.7 Flash being retired?
Amazon Bedrock retires it on 30 Mar 2027. 7 hosts keep serving it.
Is there a newer version of GLM 4.7 Flash?
Yes. GLM 5.3 Flash is the newest model in this line, released on 26 Aug 2026.
When was GLM 4.7 Flash released?
Zhipu AI released it on 19 Jan 2026.
What is GLM 4.7 Flash's API model id?
Use glm-4.7-flash with Z.ai. Other hosts use their own ids: GLM-4.7-Flash on DeepInfra, zai.glm-4.7-flash on Amazon Bedrock, GLM-4.7-Flash on GMI Cloud.
Sources
- DeepInfra pricing
- GMI Cloud pricing
- CLF AI Gateway pricing
- Novita AI pricing
- Z.ai pricing
- Amazon Bedrock pricing
- LiteLLM model map
Raw catalog entry for glm-4.7-flash on Z.ai
{
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 0,
"input_cost_per_token": 0,
"output_cost_per_token": 0,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
}