GLM 4.5
Z.aiReleased Jul 28, 2025Open weights · MITglm-4.5
- Reasoning
- yes
- Knowledge cutoff
- January 2026
- Context
- 131K tokens
- Max output
- 100k tokens
- Input
- text
- API features
- tools, JSON mode
- Z.ai's API
- yes, as glm-4.5
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Z.ai · cutoff: aiknowledgecutoff.com
Its only host, Z.AI, serves fp8 weights (maker: bf16). Weights and context per host
Open weights under MIT: you can run GLM 4.5 on your own hardware instead of paying per token.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| Z.AIfp8 (bf16) · 128K ctx · 96K out | $0.60 | $2.20 | $0.11 | 23 | 9.35 s | 100% | Oct 23 |
1 provider · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Z.AI | fp8 | 128K | 96K | yes | no | yes |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
GLM 4.5 spec sheet, field by field, with sources
GLM 4.5 spec sheetmaker-declared
What Z.ai declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 131,072 tokens
- Parameters
- 358,337,791,296≈ 358.3B
- Active experts
- 8 of 160 active per token
- Weight precision
- bfloat16
- License
- MIT — open weights, permissivecurated · read 2026-09-07Scope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the maker≈ January 2026 third-party estimate — not the maker's figurecurated
- Modalities
- text
- Max output (official)
- to verify
- Release date
- to verify≈ July 28, 2025 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
Also declared in the weights
- Architecture class
- Glm4MoeForCausalLM
- Layers
- 92
- Vocabulary
- 151,552 tokens
- Weights first published
- July 20, 2025
- Weights last updated
- August 11, 2025
- Languages declared
- English · Chinese
- Paper
- arXiv:2508.06471
zai-org/GLM-4.5 · config.json @ cbb2c7c · read 2026-10-08 · 6 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Z.AI | $1.70 | $5.90 | $4.60 |
What each host bills for 1,000 requests of a representative job