Z.ai · in Borg
Z.aiGLM-5.1
GLM-5.1 extends the GLM-5 foundation with a specific emphasis on sustained autonomous work.
Reasoning200K tokens (vendor-stated)text
Included in Borg
Download Borg Borg for BusinessAt a glance
| Specification | Value |
|---|---|
| Provider | Z.ai |
| Family | GLM |
| Release date | 2026-04-07 Vendor source |
| Context window | 200K tokens (vendor-stated) Vendor source |
| Input modalities | text |
| Output modalities | text |
| Reasoning | Yes |
| Open weights | Yes |
| Borg lane ids | glm-5.1, z-ai/glm-5.1 |
| Versions in Borg | GLM-4.5 · GLM-4.6 · GLM-4.7 · GLM-5 · GLM-5.1 · GLM-5.2 · GLM-5.3 |
Not published by the vendor: thinking modes, knowledge cutoff, fusion roles.
What GLM-5.1 is good for
GLM-5.1 extends the GLM-5 foundation with a specific emphasis on sustained autonomous work. Z.ai positions it for long-horizon coding agents that plan, execute, inspect their progress and revise an approach across multiple stages, rather than stopping after a single answer. Its context remains in the same class as GLM-5, whereas the later GLM-5.2 expands to a project-scale window; this makes GLM-5.1 a distinct choice when persistent execution matters more than loading a huge repository in one request. Beyond coding, the vendor highlights complex conversations, creative writing and front-end artifacts. Use it for iterative debugging, multi-file implementation or tool-using agents with dependent subtasks. Borg includes GLM-5.1 in the subscription, with optional Fusion routing or direct selection of its lane.
- long-running autonomous coding
- iterative engineering optimization
- multi-stage debugging
- front-end artifact generation
How Borg uses it
GLM-5.1 is available as a subscription catalog lane in Borg. The catalog does not publish which Fusion profiles route to this model, so no routing role is claimed here. You can pick it directly by setting the OpenAI-compatible gateway model field to a listed lane id. Check the current catalog for availability before building a workflow around a lane.
OpenAImodel: "glm-5.1"Measured on Borg
Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 24 requests. Minimum 100 samples per published request metric.
Completion speed covers the whole turn including queueing and reasoning time; it is not a streaming tokens-per-second figure.
Borg served 24 requests for this model in the last 30 days; not enough timed samples to publish a speed figure yet.
Benchmarks
| Benchmark | Vendor-reported score | Source |
|---|---|---|
| SWE-Bench Pro | 58.4 | Vendor source |
| Terminal-Bench 2.0 (Terminus-2) | 63.5 | Vendor source |
| BrowseComp | 68 | Vendor source |
| GPQA-Diamond | 86.2 | Vendor source |
Pricing
Included in Borg subscription. Vendor API list price: $1.4 input / $4.4 output per 1M tokens. Vendor price source.
Compare subscription and API pricing · Cost Savings Calculator
FAQ
What is GLM-5.1?
GLM-5.1 is listed in Borg's subscription catalog as glm-5.1. GLM-5.1 extends the GLM-5 foundation with a specific emphasis on sustained autonomous work.
Is GLM-5.1 in Borg?
Yes. GLM-5.1 is listed in Borg's subscription catalog under the lane glm-5.1. You can choose the lane directly, or explore the available Fusion profiles. Availability and model details can change; check the current catalog before deployment.
What context window does GLM-5.1 have?
The published context window is 200K tokens (vendor-stated). Consult the cited sources for details and current limits. Vendor source
Is GLM-5.1 good for coding?
Vendor-published evaluations appear in the benchmarks section; their settings may differ from your tasks. Its listed uses include long-running autonomous coding, iterative engineering optimization, multi-stage debugging, front-end artifact generation. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.
How fast is GLM-5.1 on Borg?
Borg served 24 requests for this model in the last 30 days; not enough timed samples to publish a speed figure yet.
How much does GLM-5.1 cost on Borg vs the API?
This model is included in the Borg subscription. The vendor API list prices appear below with a source link. See the pricing explainer and cost savings calculator to compare billing approaches.
Sources
Related
Other versions of GLM: GLM-4.5 · GLM-4.6 · GLM-4.7 · GLM-5 · GLM-5.2 · GLM-5.3
Other Z.ai models: GLM-4.5 · GLM-4.5-Air · GLM-4.6 · GLM-4.7 · GLM-5 · GLM-5-Turbo · GLM-5.2 · GLM-5.3
Models sharing a Fusion role: Not published