GLM-5.3

zhipuai/glm-5.3

Maker: Zhipu AI (Z.ai), China
Released: 2026-08-14
Family: glm
Weights: open
Tasks: text.chat, text.reasoning, code
Cheapest offering: OpenRouter, about $0.001224 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
Amazon Bedrock	`global.zai.glm-5.3`	ga	Input: $1.68 Output: $5.28 Cache read: $0.312 Cache write (5 min): $2.1 Since 2026-11-03 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 128,000 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed
Amazon Bedrock	`us.zai.glm-5.3`	ga	Input: $1.848 Output: $5.808 Cache read: $0.3432 Cache write (5 min): $2.31 Since 2026-11-03 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 128,000 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed
Alibaba Cloud Model Studio (DashScope)	`glm-5.3`	ga	Input: $1.1 Output: $3.851 Cache read: $0.275 Cache write (5 min): $0 Since 2026-11-03 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 131,072 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
DeepInfra	`zai-org/GLM-5.3`	ga	Input: $0.9 Output: $4 Cache read: $0.2 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,576 tokens Max output: 131,072 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
Fireworks AI	`accounts/fireworks/models/glm-5p3`	ga	Input: $1.4 Output: $4.4 Cache read: $0.26 Input, priority tier: $1.75 Output, priority tier: $5.5 Cache read, priority tier: $0.325 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,573 tokens Max output: 262,144 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed
Fireworks AI	`accounts/fireworks/routers/glm-5p3-fast`	ga	Input: $2.1 Output: $6.6 Cache read: $0.39 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,572 tokens Max output: 262,144 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed
Fireworks AI	`accounts/fireworks/routers/glm-5p3-spot`	ga	Input: $0.98 Output: $3.08 Cache read: $0.182 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,573 tokens Max output: 262,144 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed
Fireworks AI	`accounts/fireworks/routers/glm-fast-latest`	ga	Input: $2.1 Output: $6.6 Cache read: $0.39 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,572 tokens Max output: 262,144 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
Fireworks AI	`accounts/fireworks/routers/glm-latest`	ga	Input: $1.4 Output: $4.4 Cache read: $0.26 Input, priority tier: $1.75 Output, priority tier: $5.5 Cache read, priority tier: $0.325 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,573 tokens Max output: 262,144 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
Mistral AI	`zai-glm-5-3`	ga	Input: $1.4 Output: $4.4 Cache read: $0.14 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,576 tokens Max output: 131,072 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed
OpenRouter	`z-ai/glm-5.3`	ga	Input: $0.08 Output: $3.6 Cache read: $0.076 Unverified: sources disagree by more than 5%Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,576 tokens Max output: 943,718 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
Together AI	`zai-org/GLM-5.3`	ga	Input: $1.4 Output: $4.4 Cache read: $0.26 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,575 tokens Max output: 262,144 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `parallel_tools` claimed `tool_choice` claimed `prompt_caching` claimed
Zhipu AI (BigModel)	`glm-5.3`	ga	Input: $1.19516 Output: $4.18306 Cache read: $0.29879 Cache write (5 min): $0 Since 2026-11-03 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 131,072 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`curated`	0.950 (estimated)	0.9500	2026-11-02	Curated tier (estimated), Nanner Tech
`epoch:gpqa_diamond`	0.943	0.9091	2026-08-24	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:frontiermath`	0.734	0.6877	2026-08-25	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`lmarena:webdev`	0.508	1622.8099	2026-10-28	LMArena, CC-BY-4.0, normalized by Nanner Tech
`lmarena:agent`	0.058	0.0117	2026-11-02	LMArena, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

accounts/fireworks/models/glm-5p3
accounts/fireworks/routers/glm-5p3-fast
accounts/fireworks/routers/glm-5p3-spot
accounts/fireworks/routers/glm-fast-latest
accounts/fireworks/routers/glm-latest
glm-5.3
glm-5.3 (max)
global.zai.glm-5.3
us.zai.glm-5.3
z-ai/glm-5.3
zai-glm-5-3
zai-org/glm-5.3

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/zhipuai/glm-5.3' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=bedrock,dashscope,deepinfra,fireworks,mistral,openrouter,together,zhipu' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.3 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).