Model Metadata
- name
- GLM-5
- description
- General GLM flagship for coding, analysis, and tool-heavy engineering workflows
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; temperature: Yes; top_p: Yes; top_k: Yes
- limit
- context: 204,800; output: 131,072
- weights
- label: Hugging Face; url: https://huggingface.co/zai-org/GLM-5
Provider Variants 11
amazon-bedrock zai.glm-5
Context 202,752 · Output 131,072
- name
- GLM-5
- description
- General GLM flagship for coding, analysis, and tool-heavy engineering workflows
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No; service_tier: flex, priority
- limit
- context: 202,752; output: 131,072
- id
- zai.glm-5
- canonical id
- zhipuai/glm-5
- type
- chat
- last updated
- 2026-03-18
- api
- converse: base_url: https://bedrock-runtime.${AWS_REGION}.amazonaws.com; sdk: aisdk: @ai-sdk/amazon-bedrock; opencodeai: @opencode/ai/providers/amazon-bedrock; capabilities: tools: strict: Yes; updates: No; chat-completions: base_url: https://bedrock-mantle.${AWS_REGION}.api.aws/v1; sdk: aisdk: @ai-sdk/amazon-bedrock/mantle; opencodeai: @opencode/ai/providers/amazon-bedrock/mantle/chat; capabilities: tools: updates: No
deepinfra zai-org/GLM-5
Context 202,752 · Output 16,384
- name
- GLM-5
- description
- Flagship GLM model for hybrid reasoning, coding, and agentic engineering
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; cache: implicit: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No; prompt_cache_key: Yes; service_tier: flex
- limit
- context: 202,752; output: 16,384
- id
- zai-org/GLM-5
- canonical id
- zhipuai/glm-5
- type
- chat
- knowledge
- 2025-12
- last updated
- 2026-02-12
- status
- deprecated
- api
- chat-completions: base_url: https://api.deepinfra.com/v1/openai; sdk: aisdk: @ai-sdk/deepinfra; opencodeai: @opencode/ai/providers/deepinfra; compatibility: reasoning_field: reasoning_content; capabilities: tools: updates: No
Google zai-org/glm-5-maas
Context 200,000 · Output 128,000
- name
- GLM-5
- description
- General GLM flagship for coding, analysis, and tool-heavy engineering workflows
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; cache: implicit: min_tokens: 4,096; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 200,000; output: 128,000
- id
- zai-org/glm-5-maas
- canonical id
- zhipuai/glm-5
- type
- chat
- last updated
- 2026-02-12
- status
- deprecated
- api
- chat-completions: base_url: https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/google-vertex/chat; compatibility: reasoning_field: reasoning_content; capabilities: tools: updates: No
huggingface zai-org/GLM-5
Context 202,752 · Output 131,072
- name
- GLM-5
- description
- Flagship GLM model for hybrid reasoning, coding, and agentic engineering
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 202,752; output: 131,072
- id
- zai-org/GLM-5
- canonical id
- zhipuai/glm-5
- type
- chat
- last updated
- 2026-02-12
- api
- chat-completions: base_url: https://router.huggingface.co/v1; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/openai-compatible; compatibility: reasoning_field: reasoning_content; max_tokens_field: max_tokens; capabilities: tools: updates: No; responses: base_url: https://router.huggingface.co/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai-compatible/responses; capabilities: tools: updates: No
opencode glm-5
Context 204,800 · Output 131,072
- name
- GLM-5
- description
- Flagship GLM model for hybrid reasoning, coding, and agentic engineering
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; cache: implicit: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: Yes; effort_updates: No
- limit
- context: 204,800; output: 131,072
- id
- glm-5
- canonical id
- zhipuai/glm-5
- type
- chat
- knowledge
- 2025-04
- last updated
- 2026-02-12
- api
- chat-completions: base_url: https://opencode.ai/inference/openai/v1; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/openai-compatible; compatibility: reasoning_field: reasoning_content; capabilities: tools: choice: auto; updates: No
opencode glm-5-free
Context 204,800 · Output 131,072
- name
- GLM-5 Free
- description
- Legacy model retained for compatibility with older integrations
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: Yes; effort_updates: No
- limit
- context: 204,800; output: 131,072
- id
- glm-5-free
- canonical id
- zhipuai/glm-5
- type
- chat
- knowledge
- 2025-04
- last updated
- 2026-02-12
- status
- deprecated
- api
- chat-completions: base_url: https://opencode.ai/inference/openai/v1; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/openai-compatible; compatibility: reasoning_field: reasoning_content; capabilities: tools: choice: auto; updates: No
OpenRouter z-ai/glm-5
Context 205,824 · Output 131,072
Amp's provider snapshot overrides input/output limits and image support for this serving path. Other fields use models.dev.
- name
- GLM-5
- description
- General GLM flagship for coding, analysis, and tool-heavy engineering workflows
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 205,824; output: 131,072; input: 74,752
- id
- z-ai/glm-5
- canonical id
- zhipuai/glm-5
- type
- chat
- last updated
- 2026-02-12
- api
- chat-completions: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @openrouter/ai-sdk-provider; opencodeai: @opencode/ai/providers/openrouter; compatibility: reasoning_field: reasoning_content; capabilities: system_updates: Yes; tools: choice: auto, none, required, tool; updates: No; responses: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai-compatible/responses; capabilities: tools: choice: auto, none, required, tool; updates: No; messages: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/anthropic-compatible; capabilities: tools: choice: auto, none, required, tool; updates: No
togetherai zai-org/GLM-5
Context 202,752 · Output 131,072
- name
- GLM-5
- description
- General GLM flagship for coding, analysis, and tool-heavy engineering workflows
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; toggle: Yes; structured_output: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 202,752; output: 131,072
- id
- zai-org/GLM-5
- canonical id
- zhipuai/glm-5
- type
- chat
- last updated
- 2026-02-12
- status
- deprecated
- api
- chat-completions: base_url: https://api.together.xyz/v1; sdk: aisdk: @ai-sdk/togetherai; opencodeai: @opencode/ai/providers/togetherai; compatibility: reasoning_field: reasoning_content; capabilities: tools: updates: No
vercel zai/glm-5
Context 205,900 · Output 131,100
Amp's provider snapshot overrides input/output limits and image support for this serving path. Other fields use models.dev.
- name
- GLM-5
- description
- General GLM flagship for coding, analysis, and tool-heavy engineering workflows
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: none, low, medium, high; cache: implicit: Yes; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 205,900; output: 131,100; input: 74,800
- id
- zai/glm-5
- canonical id
- zhipuai/glm-5
- type
- chat
- last updated
- 2026-02-12
- api
- chat-completions: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/gateway; opencodeai: @opencode/ai/providers/vercel-ai-gateway; capabilities: tools: choice: auto, none, required, tool; updates: No; responses: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/open-responses; opencodeai: @opencode/ai/providers/vercel-ai-gateway/responses; capabilities: tools: choice: auto, none, required, tool; updates: No; messages: base_url: https://ai-gateway.vercel.sh/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/vercel-ai-gateway/messages; capabilities: tools: choice: auto, none, required, tool; updates: No
Z.ai glm-5
Context 204,800 · Output 131,072
- name
- GLM-5
- description
- General GLM flagship for coding, analysis, and tool-heavy engineering workflows
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; default: type: toggle; value: Yes; toggle: Yes; cache: implicit: Yes; temperature: Yes; top_p: Yes; top_k: No; system_updates: No; effort_updates: No
- limit
- context: 204,800; output: 131,072
- id
- glm-5
- canonical id
- zhipuai/glm-5
- type
- chat
- last updated
- 2026-02-12
- api
- chat-completions: base_url: https://api.z.ai/api/paas/v4; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/zai/chat; compatibility: reasoning_field: reasoning_content; max_tokens_field: max_tokens; capabilities: system_updates: Yes; tools: choice: auto; updates: No; messages: base_url: https://api.z.ai/api/anthropic/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/zai-coding-plan/messages; capabilities: tools: choice: auto; updates: No; responses: base_url: https://api.z.ai/api/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/zai-coding-plan/responses; capabilities: tools: choice: auto, none; updates: No
Z.ai glm-5
Context 204,800 · Output 131,072
- name
- GLM-5
- description
- General GLM flagship for coding, analysis, and tool-heavy engineering workflows
- family
- glm
- open weights
- Yes
- release date
- 2026-02-12
- modalities
- input: text; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; default: type: toggle; value: Yes; toggle: Yes; cache: implicit: Yes; temperature: Yes; top_p: Yes; top_k: No; system_updates: No; effort_updates: No
- limit
- context: 204,800; output: 131,072
- id
- glm-5
- canonical id
- zhipuai/glm-5
- type
- chat
- last updated
- 2026-02-12
- api
- chat-completions: base_url: https://open.bigmodel.cn/api/paas/v4; sdk: aisdk: @ai-sdk/openai-compatible; opencodeai: @opencode/ai/providers/zai/chat; compatibility: reasoning_field: reasoning_content; max_tokens_field: max_tokens; capabilities: system_updates: Yes; tools: choice: auto; updates: No; messages: base_url: https://open.bigmodel.cn/api/anthropic/v1; sdk: aisdk: @ai-sdk/anthropic; opencodeai: @opencode/ai/providers/zai-coding-plan/messages; capabilities: tools: choice: auto; updates: No; responses: base_url: https://open.bigmodel.cn/api/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/zai-coding-plan/responses; capabilities: tools: choice: auto, none; updates: No