# Vercel Eve GLM 5 is Z.ai's GLM-5 generation model released February 12, 2026, building on the GLM-4.x family with multiple thinking modes, enhanced long-range planning and memory, agentic coding, autonomous tool use, and complex multi-step workflow capabilities, available through AI Gateway with unified API access subject to Z.AI's Terms and Privacy Policies. Status: provisional Last verified: 2026-08-28T16:52:42.000Z ## Evidence - (single_source) Through AI Gateway, GLM 5 is available with unified API access. - supports https://vercel.com/ai-gateway/models/glm-5/about > GLM 5 is Z.ai's GLM-5 generation model released February 12, 2026, featuring multiple thinking modes, enhanced long-range planning and memory, and improved handling of complex multi-step agent tasks. It supports agentic coding and structured data extraction workflows. ... GLM 5 was released February 12, 2026 as Z.ai's GLM-5 generation model, introducing multiple thinking modes and enhanced long-range planning. It builds on the GLM-4.x family, with added focus on agentic coding, autonomous tool use, and complex multi-step workflows. ... . Z.ai highlights structured extraction from documents like contracts and financial reports, and agentic coding workflows where the model autonomously plans, writes, tests, and iterates on code. Through AI Gateway, GLM 5 is available with unified API access, - (single_source) AI Gateway routes Claude Opus 4.1 across Anthropic, Bedrock, and Google Vertex AI, providing a single integration point without separate credentials for each provider. - supports https://vercel.com/ai-gateway/models/claude-opus-4.1 > :** 200,000 - **Maximum output tokens:** 32,000 - **Pricing:** $15.0/1M input ... Claude Opus 4.1 became available on AI Gateway on August 5, 2025, the same day Anthropic released the model. Access it via the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python, with the model string `anthropic/claude-opus-4.1`. Through AI Gateway, you get a unified API, usage and cost tracking, and provider routing across Anthropic, Bedrock, Google Vertex AI, a single integration point without separate credentials for each provider. ... AI Gateway routes Claude Opus 4.1 across Anthropic, Bedrock, Google Vertex AI. Provider availability changes over time, so check the providers panel on this page when planning failover for critical production pipelines. - (single_source) Vercel Observability now supports viewing Agent Runs for eve, the open-source agent framework, in the Vercel dashboard. - supports https://vercel.com/changelog/eve-agent-observability > You can now view [Agent Runs](https://vercel.com/docs/eve/observability) in your Vercel dashboard for [eve](https://eve.dev/), the open-source agent framework. ... The Agent Runs tab appears automatically for every eve project, surfacing trigger, duration, and token usage for each session at a glance. Drill into any run to inspect every turn, model call, and tool call in the conversation. Runtime errors that previously vanished into function logs now correlate to the failing step. ... Open [Agent Runs](https://vercel.com/d?to=%2F%5Bteam%5D%2F%5Bproject%5D%2Fobservability%2Fagent-runs) in your project and read the [documentation](https://vercel.com/docs/eve/observability) to get ... Pick a template, deploy in minutes, and debug every agent session in the Vercel dashboard from the first run. - (single_source) The Agent Runs tab appears automatically for every eve project, surfacing trigger, duration, and token usage for each session at a glance. - supports https://vercel.com/changelog/eve-agent-observability > You can now view [Agent Runs](https://vercel.com/docs/eve/observability) in your Vercel dashboard for [eve](https://eve.dev/), the open-source agent framework. ... The Agent Runs tab appears automatically for every eve project, surfacing trigger, duration, and token usage for each session at a glance. Drill into any run to inspect every turn, model call, and tool call in the conversation. Runtime errors that previously vanished into function logs now correlate to the failing step. ... Open [Agent Runs](https://vercel.com/d?to=%2F%5Bteam%5D%2F%5Bproject%5D%2Fobservability%2Fagent-runs) in your project and read the [documentation](https://vercel.com/docs/eve/observability) to get ... Pick a template, deploy in minutes, and debug every agent session in the Vercel dashboard from the first run. - (single_source) Use of GLM 5 is subject to Z.AI's Terms and Privacy Policies. - supports https://vercel.com/ai-gateway/models/glm-5/providers > # GLM 5 ... GLM 5 is Z.AI's GLM-5 generation model released February 12, 2026, featuring multiple thinking modes, enhanced long-range planning and memory, and improved handling of complex multi-step agent tasks. It supports agentic coding and structured data extraction workflows. Your use is subject to Z.AI's [Terms](https://docs.z.ai/legal-agreement/terms-of-use) & [Privacy](https://docs.z.ai/legal-agreement/privacy-policy) Policies. ... -5) [API](/ ... 5/api) [About](/ai ... glm-5/about) [Providers](/ai-gateway ... models/glm-5/providers) [Throughput](/ ... gateway/models/glm-5/throughput) [Latency](/ ... -gateway/models/glm-5/latency) [Uptime](/ai-gateway/models/glm-5/uptime) [Status](/ai-gateway/models/glm-5/status) [Similar](/ai- ... /models/ ... similar) [FAQ](/ ... models/glm-5/faq) - (single_source) GLM 5 is Z.ai's GLM-5 generation model released February 12, 2026, featuring multiple thinking modes, enhanced long-range planning and memory, and improved handling of complex multi-step agent tasks. - supports https://vercel.com/ai-gateway/models/glm-5/about > GLM 5 is Z.ai's GLM-5 generation model released February 12, 2026, featuring multiple thinking modes, enhanced long-range planning and memory, and improved handling of complex multi-step agent tasks. It supports agentic coding and structured data extraction workflows. ... GLM 5 was released February 12, 2026 as Z.ai's GLM-5 generation model, introducing multiple thinking modes and enhanced long-range planning. It builds on the GLM-4.x family, with added focus on agentic coding, autonomous tool use, and complex multi-step workflows. ... . Z.ai highlights structured extraction from documents like contracts and financial reports, and agentic coding workflows where the model autonomously plans, writes, tests, and iterates on code. Through AI Gateway, GLM 5 is available with unified API access, - (single_source) Claude Opus 4.1 became available on AI Gateway on August 5, 2025, the same day Anthropic released the model. - supports https://vercel.com/ai-gateway/models/claude-opus-4.1 > :** 200,000 - **Maximum output tokens:** 32,000 - **Pricing:** $15.0/1M input ... Claude Opus 4.1 became available on AI Gateway on August 5, 2025, the same day Anthropic released the model. Access it via the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python, with the model string `anthropic/claude-opus-4.1`. Through AI Gateway, you get a unified API, usage and cost tracking, and provider routing across Anthropic, Bedrock, Google Vertex AI, a single integration point without separate credentials for each provider. ... AI Gateway routes Claude Opus 4.1 across Anthropic, Bedrock, Google Vertex AI. Provider availability changes over time, so check the providers panel on this page when planning failover for critical production pipelines. - (single_source) Claude Opus 4.1 can be accessed via the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python, with the model string anthropic/claude-opus-4.1. - supports https://vercel.com/ai-gateway/models/claude-opus-4.1 > :** 200,000 - **Maximum output tokens:** 32,000 - **Pricing:** $15.0/1M input ... Claude Opus 4.1 became available on AI Gateway on August 5, 2025, the same day Anthropic released the model. Access it via the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python, with the model string `anthropic/claude-opus-4.1`. Through AI Gateway, you get a unified API, usage and cost tracking, and provider routing across Anthropic, Bedrock, Google Vertex AI, a single integration point without separate credentials for each provider. ... AI Gateway routes Claude Opus 4.1 across Anthropic, Bedrock, Google Vertex AI. Provider availability changes over time, so check the providers panel on this page when planning failover for critical production pipelines. - (single_source) Z.ai highlights structured extraction from documents like contracts and financial reports, and agentic coding workflows where GLM 5 autonomously plans, writes, tests, and iterates on code. - supports https://vercel.com/ai-gateway/models/glm-5/about > GLM 5 is Z.ai's GLM-5 generation model released February 12, 2026, featuring multiple thinking modes, enhanced long-range planning and memory, and improved handling of complex multi-step agent tasks. It supports agentic coding and structured data extraction workflows. ... GLM 5 was released February 12, 2026 as Z.ai's GLM-5 generation model, introducing multiple thinking modes and enhanced long-range planning. It builds on the GLM-4.x family, with added focus on agentic coding, autonomous tool use, and complex multi-step workflows. ... . Z.ai highlights structured extraction from documents like contracts and financial reports, and agentic coding workflows where the model autonomously plans, writes, tests, and iterates on code. Through AI Gateway, GLM 5 is available with unified API access, - (single_source) Drilling into any Agent Run allows inspecting every turn, model call, and tool call in the conversation, and runtime errors correlate to the failing step. - supports https://vercel.com/changelog/eve-agent-observability > You can now view [Agent Runs](https://vercel.com/docs/eve/observability) in your Vercel dashboard for [eve](https://eve.dev/), the open-source agent framework. ... The Agent Runs tab appears automatically for every eve project, surfacing trigger, duration, and token usage for each session at a glance. Drill into any run to inspect every turn, model call, and tool call in the conversation. Runtime errors that previously vanished into function logs now correlate to the failing step. ... Open [Agent Runs](https://vercel.com/d?to=%2F%5Bteam%5D%2F%5Bproject%5D%2Fobservability%2Fagent-runs) in your project and read the [documentation](https://vercel.com/docs/eve/observability) to get ... Pick a template, deploy in minutes, and debug every agent session in the Vercel dashboard from the first run. - (single_source) The similar model anthropic/claude-fable-5 has 1M context, 2.9s latency, 96tps throughput, $10/M input pricing, $50/M output pricing, and a release date of 07/01/2026. - supports https://vercel.com/ai-gateway/models/claude-opus-4.8/similar > | anthropic/claude-opus-5 | 1M | 2.9s | 94tps | $5/MFast $10/M | $25/MFast $50/M | Read:$0.5/M Write: $6.25/M+1 more | $10/K + input costs | +3 | +1 | 07/24/2026 | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | ... | anthropic/claude-fable-5 | 1M | 2.9s | 96tps | $10/M | $50/M | Read:$1/M Write: $12.5/M+1 more | $10/K + input costs | +2 | | 07/01/2026 | ... | anthropic/claude-sonnet-5 | 1M | 1.1s | 112tps | $3/M$2/M | $15/M$10/M | Read:$0.3/M$0.2/M Write: $3.75/M$2.5/M+1 more | $10/K + input costs | +3 | +1 | 06/29/2026 | ... /claude-sonnet-4.6 | 1M | 1.0s | 55tps | $3/M | $15/M | Read:$0.3/M Write: $3.75/M+1 more | $10/K ... | anthropic/claude-opus-4.6 | 1M | 1.6s | 55tps | $5/MFast $30/M | $25/MFast $150/M | Read:$0.5/M Write: $6.25/M+1 more | $10/K + input costs | + - (single_source) GLM 5 builds on the GLM-4.x family, with added focus on agentic coding, autonomous tool use, and complex multi-step workflows. - supports https://vercel.com/ai-gateway/models/glm-5/about > GLM 5 is Z.ai's GLM-5 generation model released February 12, 2026, featuring multiple thinking modes, enhanced long-range planning and memory, and improved handling of complex multi-step agent tasks. It supports agentic coding and structured data extraction workflows. ... GLM 5 was released February 12, 2026 as Z.ai's GLM-5 generation model, introducing multiple thinking modes and enhanced long-range planning. It builds on the GLM-4.x family, with added focus on agentic coding, autonomous tool use, and complex multi-step workflows. ... . Z.ai highlights structured extraction from documents like contracts and financial reports, and agentic coding workflows where the model autonomously plans, writes, tests, and iterates on code. Through AI Gateway, GLM 5 is available with unified API access, ## Timeline - 2026-08-28T16:45:32.000Z: GLM 5 released February 12, 2026 by Z.ai with multiple thinking modes, enhanced long-range planning and memory, and improved multi-step agent task handling GLM 5 builds on GLM-4.x family with focus on agentic coding, autonomous tool use, and complex multi-step workflows Z.ai highlights structured document extraction and agentic coding workflows where GLM 5 autonomously plans, writes, tests, and iterates on code GLM 5 available through AI Gateway with unified API access Use of GLM 5 is subject to Z.AI's Terms and Privacy Policies