submodel
GLM 4.5 FP8
Canonical ID:
submodel/zai-org/GLM-4.5-FP8
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
Overview
- Provider
-
submodel
- Family
- glm-4.5-fp8
- Release date
- 2025-07-28
- Last updated
- 2025-07-28
- Input modalities
- text
- Output modalities
- text
Pricing and Limits
Token pricing
- Input
- $0.2/1M
- Output
- $0.8/1M
- Cached input
- N/A
Context and output
- Context window
- 131,072
- Max output tokens
- 131,072
- Qualified ID
- submodel/zai-org/GLM-4.5-FP8
Model Summary
GLM 4.5 FP8 is a model listing in the submodel provider catalog. It is categorized under the glm-4.5-fp8 family.
The model supports text modalities across input/output paths. Reported context capacity is 131,072. Pricing is listed at $0.2/1M input and $0.8/1M output.
More From submodel
Related models from the same provider catalog.
DeepSeek R1 0528
submodel/deepseek-ai/DeepSeek-R1-0528
DeepSeek V3 0324
submodel/deepseek-ai/DeepSeek-V3-0324
DeepSeek V3.1
submodel/deepseek-ai/DeepSeek-V3.1
GLM 4.5 Air
submodel/zai-org/GLM-4.5-Air
GPT OSS 120B
submodel/openai/gpt-oss-120b
Qwen3 235B A22B Instruct 2507
submodel/Qwen/Qwen3-235B-A22B-Instruct-2507
Qwen3 235B A22B Thinking 2507
submodel/Qwen/Qwen3-235B-A22B-Thinking-2507
Qwen3 Coder 480B A35B Instruct
submodel/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
Same Family: glm-4.5-fp8
Comparable models in the same family across providers.
| Model | Provider | Context | Input | Output | Flags |
|---|---|---|---|---|---|
|
GLM 4.5 FP8
chutes/zai-org/GLM-4.5-FP8
|
|
131,072 | $0.3/1M | $1.2/1M |
Reasoning
Tools
|