GLM-5.3-Flash
by Z.ai (Zhipu AI)Chat
Native multimodal GLM model for efficient coding and long-horizon agent tasks
- Context
- 1.05M tokens
- Max output
- 131,072 tokens
- Parameters
- 321B total, 18B active
- Released
- 2026-08-26
- Weights
- Open
- Licence
- mit
zhipuai/glm-5-3-flash · also seen as z-ai/glm-5.3-flash, zai-org/GLM-5.3-Flash, coding-glm-5.3-flash-free, ox-alpha, +31 more
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-08-26
- Weights
- Opennot gated
- License
- mit
- Input
- Text, Image, Video, PDF
- Output
- Text
- Context window
- 1,048,576 max across endpoints
- Max output
- 131,072
- Providers
- 74 + 26 gateways, not counted as providers
- Epoch Capabilities Index
- 153.2 ± 2.2 against price
- Direct price range
- $0.099–$0.450 in · $0.35–$1.50 out per 1M tokens · 55 of 74 providers have a comparable price
More details
- Last updated
- 2026-09-30
- Knowledge cutoff
- Weights link
- Hugging Face · zai-org/GLM-5.3-Flash
- Parameters
- 321B total, 18B active
- Developer country
- China
- Training compute
- 3.2×10²⁴ FLOP
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel tools
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messages
- Assistant prefillunknown
- Temperature
- Streaming
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.099 in / $0.35 out per 1M tokens at IteraCompute on every data refresh since then.
Tracked from 19 Oct 2026, the earliest refresh this model's headline price can be rebuilt from. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs GLM-5.3-Flash |
|---|---|---|---|---|---|
| Qwen 3.5 9B (Q4_K_M)Alibaba (Qwen) | $0.0667 | $0.05 | $0.15 | 262K | +0% |
| DiffusionGemmaGoogle | $0.0667 | $0.05 | $0.15 | 262K | +0% |
| Nemotron 3.5 Content SafetyNVIDIA | $0.0667 | $0.05 | $0.15 | 128K | +0% |
| Hy-MT2-1.8BTencent | $0.0662 | $0.044 | $0.177 | 8.2K | −1% cheaper |
| Tencent Hy-MT2-LiteTencent | $0.0662 | $0.044 | $0.177 | 8K | −1% cheaper |
| Phi-4Microsoft | $0.0653 | $0.056 | $0.112 | 16.4K | −2% cheaper |
| Laguna XS 2.1Poolside | $0.07 | $0.06 | $0.12 | 262K | +5% |
| Qwen3.5 FlashAlibaba (Qwen) | $0.0705 | $0.0282 | $0.282 | 1M | +6% |
More from Z.ai (Zhipu AI)
Newest Z.ai (Zhipu AI) models in the catalogue. All Z.ai (Zhipu AI) models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Apex Flash 1 | 2026-10-05 | 1.05M | $0.15 via NanoGPT |
| Apex Flash 1 Abliterated | 2026-10-05 | 1.05M | $0.15 via NanoGPT |
| GLM 5.3 Uncensored | 2026-09-26 | 1.05M | $1.25 via NanoGPT |
| GLM 5.3 Prime | 2026-09-23 | 1M | from $2.80 |
| GLM 5.3 Flash Cybersecurity | 2026-09-19 | 1.05M | $0.15 via NanoGPT |
| GLM 5.3 FlashX | 2026-09-18 | 1.05M | from $0.37 |
| GLM-5.3 | 2026-08-14 | 1.05M | from $0.75 |
| GLM 5.3 Flash Uncensored | 2026-07-29 | 1.05M | $0.20 via NanoGPT |