GLM-5.3
Summary
GLM-5.3 is an open-weight language model from Zhipu AI (Z.ai), released on 14 Aug 2026. It accepts text and generates text, with a 1M-token context window and up to 131K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.90 per million input tokens and $4 per million output tokens (DeepInfra), across 14 providers we track.
Flagship GLM model for long-horizon coding, agents, and complex project delivery
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Zhipu AI (Z.ai) |
|---|---|
| Release date | 14 Aug 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | glm-5.3 [Hugging Face] |
| Parameters | 753B [Hugging Face] |
| Context window | 1M (1,000,000 tokens) [models.dev] |
| Max output | 131K tokens [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | zai-org/GLM-5.3 [Hugging Face] |
GLM-5.3 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| NVIDIA NIM z-ai/glm-5.3 | Free | Free | – | 1M | models.dev, 4 Oct 2026 |
| DeepInfra zai-org/GLM-5.3 | $0.90 | $4 | $0.20 | 1M | models.dev, 4 Oct 2026 |
| FriendliAI zai-org/GLM-5.3 | $1.26 | $3.96 | $0.23 | 1M | models.dev, 4 Oct 2026 |
| Z.ai API glm-5.3 | $1.40 | $4.40 | $0.26 | 1M | models.dev, 4 Oct 2026 |
| Mistral API zai-glm-5-3 | $1.40 | $4.40 | $0.14 | 1M | models.dev, 4 Oct 2026 |
| Cloudflare Workers AI @cf/zai-org/glm-5.3 | $1.40 | $4.40 | $0.26 | 1M | models.dev, 4 Oct 2026 |
| Fireworks AI accounts/fireworks/models/glm-5p3 | $1.40 | $4.40 | $0.26 | 1M | models.dev, 4 Oct 2026 |
| Hugging Face Inference Providers zai-org/GLM-5.3 | $1.40 | $4.40 | – | 1M | models.dev, 4 Oct 2026 |
| Baseten zai-org/GLM-5.3 | $1.40 | $4.40 | $0.14 | 1M | models.dev, 4 Oct 2026 |
| SiliconFlow zai-org/GLM-5.3 | $1.40 | $4.40 | $0.26 | 1M | models.dev, 4 Oct 2026 |
| Fireworks AI accounts/fireworks/routers/glm-latest | $1.40 | $4.40 | $0.26 | 1M | models.dev, 4 Oct 2026 |
| Nebius AI Studio zai-org/GLM-5.3 | $1.40 | $4.40 | $1.40 | 1M | models.dev, 4 Oct 2026 |
| Together AI zai-org/GLM-5.3 | $1.40 | $4.40 | $0.26 | 1M | models.dev, 4 Oct 2026 |
| OpenRouter z-ai/glm-5.3 | $1.40 | $4.40 | $0.14 | 1M | OpenRouter, 4 Oct 2026 |
| Vercel AI Gateway zai/glm-5.3 | $1.40 | $4.40 | $0.14 | 1M | models.dev, 4 Oct 2026 |
| Fireworks AI accounts/fireworks/routers/glm-5p3-fast | $2.10 | $6.60 | $0.39 | 1M | models.dev, 4 Oct 2026 |
| Fireworks AI accounts/fireworks/routers/glm-fast-latest | $2.10 | $6.60 | $0.39 | 1M | models.dev, 4 Oct 2026 |
| Baseten zai-org/GLM-5.3-Fast | $2.10 | $6.60 | – | 1M | models.dev, 4 Oct 2026 |
| Vercel AI Gateway zai/glm-5.3-fast | $2.10 | $6.60 | $0.21 | 1M | models.dev, 4 Oct 2026 |
Frequently asked questions
What is the context window of GLM-5.3?
GLM-5.3 has a context window of 1,000,000 tokens (1M) and can generate up to 131,072 tokens in a single response, according to models.dev.
How much does the GLM-5.3 API cost?
Through Z.ai API, GLM-5.3 costs $1.40 per million input tokens and $4.40 per million output tokens. The lowest listed price is $0.90 input / $4 output through DeepInfra. Prices last verified 4 Oct 2026.
Is GLM-5.3 open source?
GLM-5.3 is an open-weight model: its weights are published on Hugging Face as zai-org/GLM-5.3 under the glm-5.3 license. Check the license terms before commercial use.
When was GLM-5.3 released?
Zhipu AI (Z.ai) released GLM-5.3 on 14 Aug 2026, according to models.dev.
Which providers offer GLM-5.3?
We track GLM-5.3 on 14 providers: NVIDIA NIM, DeepInfra, FriendliAI, Z.ai API, Mistral API, Cloudflare Workers AI, Fireworks AI, Hugging Face Inference Providers, Baseten, SiliconFlow, Nebius AI Studio, Together AI, OpenRouter, Vercel AI Gateway.
Change history
No changes detected since we started tracking this model. We re-check every source daily.
Sources
- https://openrouter.ai/z-ai/glm-5.3
- https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-5.3.toml
- https://huggingface.co/zai-org/GLM-5.3
- https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/z-ai/glm-5.3.toml
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/zai-org/GLM-5.3.toml
- https://github.com/sst/models.dev/blob/dev/providers/friendli/models/zai-org/GLM-5.3.toml
- https://github.com/sst/models.dev/blob/dev/providers/mistral/models/zai-glm-5-3.toml
- https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/zai-org/glm-5.3.toml
- https://github.com/sst/models.dev/blob/dev/providers/fireworks-ai/models/accounts/fireworks/models/glm-5p3.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/zai-org/GLM-5.3.toml
- https://github.com/sst/models.dev/blob/dev/providers/baseten/models/zai-org/GLM-5.3.toml
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/zai-org/GLM-5.3.toml
- https://github.com/sst/models.dev/blob/dev/providers/fireworks-ai/models/accounts/fireworks/routers/glm-latest.toml
- https://github.com/sst/models.dev/blob/dev/providers/nebius/models/zai-org/GLM-5.3.toml
- https://github.com/sst/models.dev/blob/dev/providers/togetherai/models/zai-org/GLM-5.3.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/zai/glm-5.3.toml
- https://github.com/sst/models.dev/blob/dev/providers/fireworks-ai/models/accounts/fireworks/routers/glm-5p3-fast.toml
- https://github.com/sst/models.dev/blob/dev/providers/fireworks-ai/models/accounts/fireworks/routers/glm-fast-latest.toml
- https://github.com/sst/models.dev/blob/dev/providers/baseten/models/zai-org/GLM-5.3-Fast.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/zai/glm-5.3-fast.toml