Verdict
computed from the published numbersGLM 5.1 wins on coding, on intelligence and on context window. Mercury 2 wins on price.
Price
Mercury 2
Coding
GLM 5.1
Intelligence
GLM 5.1
Context window
GLM 5.1
Key takeaways
who wins on what, from the published numbersGLM 5.1 wins
- Larger context window (205K vs 128K)
- Higher max output (131K vs 50K)
- More serving providers (5 vs 2)
- Has reasoning mode
Mercury 2 wins
- Cheaper input ($1.05 vs $0.25 /1M)
- Cheaper output ($3.50 vs $0.75 /1M)
Cheaper overall
Mercury 2
$0.25 + $0.75 /1M
Larger context
GLM 5.1
205K
More providers
GLM 5.1
5 providers
Pricing & specs
cheapest serving route · per 1M tokens| GLM 5.1 | Mercury 2 | |
|---|---|---|
| Input $/1M | $1.05 | $0.25 best |
| Output $/1M | $3.50 | $0.75 best |
| Context window | 205K best | 128K |
| Max output | 131K best | 50K |
| Serving providers | 5 best | 2 |
| Released | 2026-04-07 | 2026-02-24 |
Benchmarks
Artificial Analysis indices, side by side| GLM 5.1 | Mercury 2 | |
|---|---|---|
| Intelligence | 41.0 best | 21.9 |
| Coding | 55.8 best | 31.1 |
| GPQA Diamond | 87% best | 77% |
| Output speed | 56 t/s | 939 t/s best |
| Latency (TTFT) | 1.71s best | 3.44s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
GLM 5.1
via DeepInfra
$8.75
Mercury 2
via Inception
$2.00
Capabilities
feature support, side by side| Feature | GLM 5.1 | Mercury 2 |
|---|---|---|
| Vision | — | — |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | — |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, GLM 5.1 or Mercury 2?
Mercury 2 is cheaper for input ($1.05 vs $0.25 per 1M tokens). Mercury 2 is cheaper for output ($3.50 vs $0.75 per 1M tokens).
What is the context window difference between GLM 5.1 and Mercury 2?
GLM 5.1 has a 205K-token context window and Mercury 2 has 128K tokens, so GLM 5.1 can take a larger prompt.
How do GLM 5.1 and Mercury 2 compare on benchmarks?
On the tracked Artificial Analysis indices, GLM 5.1 leads on coding, and GLM 5.1 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