GLM 5.3 Flash Uncensored
GLM 5.3 Flash Uncensored is an uncensored fine-tune of the efficient 320B mixture-of-experts reasoning model with provider-dependent vision support, built for unrestricted chat, creative writing, coding, agentic work, tool use, and long-context tasks.
- Reasoning
- Vision
- Tool Calling
- Structured Output
Added Jul 29, 2026
Pricing
Auto routing · per 1M tokens- Input
- $0.20
- Output
- $0.80
- Cache read
- $0.07
Specifications
- Context window
- 1M
- Max output
- 32.8K
- Parameters
- 320B / 18B
- Total / active
Benchmarks
No public benchmark scores for this model yet.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
| $0.20 | $0.80 | $0.07 | N/A | N/A | |
| $0.20 | $0.80 | $0.07 | N/A | N/A | |
| $0.105 | $0.42 | $0.042 | N/A | N/A | |
| $0.20 | $0.524 | $0.0699 | N/A | N/A | |
| $0.21 | $0.525 | $0.0735 | N/A | N/A | |
| $0.831 | $1.66 | $0.155 | N/A | N/A |
Privacy:ZDR, prompts not retainedNo training on prompts
Batch API
Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.