Verdict
computed from the published numbersGLM 5.1 wins on price. GLM 5.2 wins on coding, on intelligence and on context window.
Price
GLM 5.1
Coding
GLM 5.2
Intelligence
GLM 5.2
Context window
GLM 5.2
Key takeaways
who wins on what, from the published numbersGLM 5.1 wins
- Cheaper input ($1.05 vs $1.40 /1M)
- Cheaper output ($3.50 vs $4.40 /1M)
- More serving providers (2 vs 1)
- Supports prompt caching
GLM 5.2 wins
- Larger context window (203K vs 262K)
- Higher max output (128K vs 262K)
Cheaper overall
GLM 5.1
$1.05 + $3.50 /1M
Larger context
GLM 5.2
262K
More providers
GLM 5.1
2 providers
Pricing & specs
cheapest serving route · per 1M tokens| GLM 5.1 | GLM 5.2 | |
|---|---|---|
| Input $/1M | $1.05 best | $1.40 |
| Output $/1M | $3.50 best | $4.40 |
| Context window | 203K | 262K best |
| Max output | 128K | 262K best |
| Serving providers | 2 best | 1 |
| Released | 2026-04-07 | 2026-06-13 |
Benchmarks
Artificial Analysis indices, side by side| GLM 5.1 | GLM 5.2 | |
|---|---|---|
| Intelligence | 40.2 | 51.1 best |
| Coding | 55.8 | 68.8 best |
| GPQA Diamond | 87% | 89% best |
| Output speed | 91 t/s | 200 t/s best |
| Latency (TTFT) | 10.49s | 6.32s best |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
GLM 5.1
via OpenRouter
$8.75
GLM 5.2
via Cloudflare
$11
Capabilities
feature support, side by side| Feature | GLM 5.1 | GLM 5.2 |
|---|---|---|
| Vision | — | — |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | — |
| Structured output | — | — |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, GLM 5.1 or GLM 5.2?
GLM 5.1 is cheaper for input ($1.05 vs $1.40 per 1M tokens). GLM 5.1 is cheaper for output ($3.50 vs $4.40 per 1M tokens).
What is the context window difference between GLM 5.1 and GLM 5.2?
GLM 5.1 has a 203K-token context window and GLM 5.2 has 262K tokens, so GLM 5.2 can take a larger prompt.
How do GLM 5.1 and GLM 5.2 compare on benchmarks?
On the tracked Artificial Analysis indices, GLM 5.2 leads on coding, and GLM 5.2 leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI