GLM-5
zai-org/glm-5
multi-mode thinking & long-range planning.
cmd --model zai-org/glm-5
Intelligence index
39.5
Output speed
not yet scored
Input
$1 /M
Output
$3.20 /M
Cache read
$0.20 /M
Agent-loop cost
$0.44 /M in
Context window
200K tokens
Released
February 11, 2026
Modalities
→
vs. the lineup
GLM-5 beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.
pin a rival:
| Model | Intelligence | Coding | Speed | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|---|
| GPT-5.6 Luna | 51.2◆ | 71.4◆ | 169.1◆ | $0.10◆ | $0.60◆ | $0.23◆ | 1.05M◆ |
| GLM-5.2 | 51.1◆ | 68.8◆ | 124◆ | $1.40◆ | $4.40◆ | $2.15◆ | 1M◆ |
| GLM-5.1 | 40.2◆ | 55.8◆ | —◆ | $1.40◆ | $4.40◆ | $2.15◆ | 200K◆ |
| GLM-5 ◆ | 39.5◆ | —◆ | —◆ | $1◆ | $3.20◆ | $1.55◆ | 200K◆ |
| Step 3.7 Flash | 30.3◆ | 39.6◆ | 407.1◆ | $0.20◆ | $1.15◆ | $0.44◆ | 256K◆ |
| GLM-5.2 Fast | —◆ | —◆ | —◆ | $3◆ | $10.25◆ | $4.81◆ | 1M◆ |
| DeepSeek V4 Propinned | 44.3◆ | 59.4◆ | 59.3◆ | $0.43◆ | $0.87◆ | $0.54◆ | 1M◆ |
| DeepSeek V4 Flashpinned | 49.9◆ | 69.1◆ | —◆ | $0.14◆ | $0.28◆ | $0.18◆ | 1M◆ |
coding performance
The Intelligence Index and its sub-scores, ranked against every scored model in the catalog. A metric that has not been measured for GLM-5 has been left empty.
IFBench
72.3
instruction following
Intelligence Index
39.5
#33 of 44 scored
Long-context reasoning
63.3
reasoning across a long context
SciCode
46.2
scientific coding
GPQA Diamond
82
graduate-level QA
usage calculator
How far a month of credits goes on GLM-5.
Input tokensfresh prompt
800Output tokensmodel reply
180Cache read tokensre-read context
50Kcost / request $0.011 · in $1 · out $3.20 · cache $0.20 per M
fresh input 7%output 5%cache reads 88%
Requests / 30 days
879
$10 credits ÷ $0.011 per request
~176 quick fixes~35 bug fixes~6 feature PRs
what real work costs
Real coding tasks priced end to end on GLM-5, from a quick lookup to a full-repo agent run.
One agent task
$0.11
180K in at 75% cache hit, 12K out
What you pay
$0.57 /M
all-in across every token that task touched
Sticker input
$1 /M
cache reads bill at $0.20 /M instead
| Task | Tokens in · out | GLM-5 | GPT-5.6 Luna | Claude Haiku 4.5 |
|---|---|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0054 | $0.0008 | $0.0065 |
| Review a 500-line PR | 60K · 4K | $0.04 | $0.0046 | $0.04 |
| Fix a bug (agent loop) | 180K · 12K | $0.11 | $0.01 | $0.12 |
| Refactor a module | 320K · 20K | $0.20 | $0.02 | $0.21 |
| Full-repo agent run | 900K · 45K | $0.48 | $0.05 | $0.49 |
frequently asked
What is GLM-5 best for?+
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.
How much does GLM-5 cost?+
$1/M input and $3.20/M output, cache reads $0.20/M. In an agent loop most input is cache-read, so the effective input rate is about $0.44/M.Which plan do I need?+
Available on Go and above.
How do I switch to it?+
Run
cmd --model zai-org/glm-5, or type /model in a session and pick it. You can switch mid-session without losing context.Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.
commandcode.ai/models/glm-5
