Nemotron 3.5 Super VL vs GLM 5.2
Practical read: Nemotron 3.5 Super VL costs about a quarter as much. GLM 5.2 starts answering sooner. One API key runs both.
No card required. Start with 1 million free tokens.
Side by side:
| Attribute | Nemotron 3.5 Super VL | GLM 5.2 |
|---|---|---|
| Price, 1M in + out | $0.53 Crusoe, cheapest route | $2.30 Engy, cheapest route |
| Best for | Low cost | Speed |
| Input / output, 1M | $0.11 / $0.42 | $0.72 / $1.58 |
| Cached input | $0.0211/1M to $0.089675/1M | $0.131875/1M to $0.80391/1M |
| Context window | 1.05M 1,048,576 tokens | 1.05M 1,048,576 tokens |
| First token, p50 | 0.93 s via Crusoe | 0.83 s via FriendliAI |
| Throughput | Measuring | 197 tok/s via Databricks |
| AI IQ | IQ 105 #100 on AI IQ | IQ 118 #53 on AI IQ |
| Provider routes | 4 with failover | 32 with failover |
| Privacy | Zero retention route | Confidential E2EE and zero retention route |
| Recent route uptime range | 100.00% | 50.00% to 100.00% |
| Publisher | NVIDIA | Z.AI |
| Modes | chat | chat |
| More detail |
Price adds one million input and one million output tokens on the cheapest route. Prices and speed change: see the monthly reports and run a small eval before you choose a default.
Test both with your agent
Paste this into Claude Code, Cursor or any coding agent.
Compare Nemotron 3.5 Super VL and GLM 5.2 in this project through TrustedRouter.
1. Read https://trustedrouter.com/docs/llms.txt
2. Point the OpenAI-compatible client at
https://api.trustedrouter.com/v1 and read the key from
TRUSTEDROUTER_API_KEY.
3. Run our eval prompts on nvidia/nemotron-3.5-super-vl, then on z-ai/glm-5.2.
4. Show me cost, latency and quality side by side before changing the default.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.trustedrouter.com/v1",
api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
for model in ("nvidia/nemotron-3.5-super-vl", "z-ai/glm-5.2"):
response = client.chat.completions.create(
model=model,
messages=[{"role": "user", "content": "What is the capital of France?"}],
)
print(model, response.choices[0].message.content)
for model in nvidia/nemotron-3.5-super-vl z-ai/glm-5.2; do
curl https://api.trustedrouter.com/v1/chat/completions \
-H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d "{\"model\": \"$model\", \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}]}"
done
Questions
Which should I use, NVIDIA: Nemotron 3.5 Super VL or Z.ai: GLM 5.2?
NVIDIA: Nemotron 3.5 Super VL has the lower published input-plus-output rate. Z.ai: GLM 5.2 has more Credits provider routes and the lower measured p50 time to first token. Their context windows are the same size.
Is NVIDIA: Nemotron 3.5 Super VL or Z.ai: GLM 5.2 cheaper?
The current cheapest TrustedRouter route is $0.5275/1M for NVIDIA: Nemotron 3.5 Super VL and $2.2999/1M for Z.ai: GLM 5.2. The comparison uses current catalog prices and updates as provider pricing changes.
Is NVIDIA: Nemotron 3.5 Super VL or Z.ai: GLM 5.2 faster?
Current measured p50 time to first token is 931 ms for NVIDIA: Nemotron 3.5 Super VL and 832 ms for Z.ai: GLM 5.2. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.
Can I test NVIDIA: Nemotron 3.5 Super VL and Z.ai: GLM 5.2 with the same API?
Yes. Use the same OpenAI-compatible TrustedRouter base URL and API key, then change only the model id between nvidia/nemotron-3.5-super-vl and z-ai/glm-5.2. This makes side-by-side evals possible without maintaining two provider integrations.
More comparisons
All comparisonsTry Nemotron 3.5 Super VL and GLM 5.2 with one key.
TrustedRouter is useful when you know the model you want, but still need provider rollover, budget limits, usage records, and a prompt path you can verify.
No card required. Start with 1 million free tokens.