Z.ai · Open weights
GLM 5V Turbo Thinking
Thinking-enabled GLM 5V Turbo for image, video, and text inputs. Uses the same multimodal foundation model with more deliberate vision-grounded analysis, planning, and tool use.
- Reasoning
- Tools
- Vision
- Structured output
- Video input
- Input
- Text, Images, Video
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $1.20
- Output
- $4.00
- Cache read
- $0.24
Reference prices as published by the model provider. API example
Specifications
- Context window
- 202.8K
- Max output
- 131.1K
- Average output (7 days)
- 942 tokens
- Longer than 69% of 468 models
Side by side
GLM 5V Turbo Thinking compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| GLM 5V Turbo ThinkingZ.aiThis model | Kimi K2.5MoonshotRemove | |
|---|---|---|
| Provider | Z.ai | Moonshot |
| Discovery tier | Open weights | Open weights |
| Added | Apr 2, 2026 | Jan 26, 2026 |
| Limits | ||
| Context window | 202.8K | 262.14KBest |
| Max output | 131.07KBest | 65.54K |
| Average output | 942 tokens | 437 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $1.20 | $0.38Best |
| Output | $4.00 | $2.00Best |
| Cache read | $0.24 | $0.07Best |
| Performance | ||
| Throughput | 41.0 tok/s | 98.6 tok/sBest |
| Time to first token | 6.5 s | 2.0 sBest |
| Request success (24h) | 97.6% | 99.8%Best |
| Benchmark indexes | ||
| Intelligence Index | 23.5 | 23.5 |
| Coding Index | — | 46.8 |
| Capabilities | ||
| Reasoning | Yes | No |
| Tools | Yes | Yes |
| Vision | Yes | Yes |
| Structured output | Yes | No |
| Video input | Yes | No |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- GLM 5V Turbo Thinking
- Kimi K2.5
Intelligence Index
- GLM 5V Turbo Thinking23.5
- Kimi K2.523.5
GLM 5V Turbo Thinking: Better than 57% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- GLM 5V Turbo Thinking: —
- Kimi K2.5: 46.8
Agentic work
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- GLM 5V Turbo Thinking: —
- Kimi K2.5: 839 Elo
Document reasoning
AA-LCRv1.1
Reasoning across long documents
- GLM 5V Turbo Thinking: 70.3%
- Kimi K2.5: 78.0%Top
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- GLM 5V Turbo Thinking: 17.1%
- Kimi K2.5: 30.7%Top
GPQA Diamond
Graduate-level science questions
- GLM 5V Turbo Thinking: 80.9%
- Kimi K2.5: 87.9%Top
IFBench
Following precise output instructions
- GLM 5V Turbo Thinking: 61.1%
- Kimi K2.5: 70.2%Top
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- GLM 5V Turbo Thinking: 32.6%
- Kimi K2.5: 34.8%Top
τ²-Bench Telecom
Tool use in a customer-support simulation
- GLM 5V Turbo Thinking: 98.5%Top
- Kimi K2.5: 95.9%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- GLM 5V Turbo Thinking: 70.3%
- Kimi K2.5: 78.0%Top
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
- GLM 5V Turbo Thinking
- Kimi K2.5
| Leaderboard | GLM 5V Turbo Thinking | Kimi K2.5 |
|---|---|---|
| SWE-bench Verified | Not in top 20 | #10 · 73.8% |
Ranks among Noumen catalog models on Epoch AI leaderboards. Only top-20 placements are listed.Epoch AI
- GLM 5V Turbo Thinking
- Kimi K2.5
| Leaderboard | GLM 5V Turbo Thinking | Kimi K2.5 |
|---|---|---|
| EQ-Bench 3 | Not in top 20 | #15 · 1530 |
Ranks among Noumen catalog models on EQ-Bench leaderboards. Only top-20 placements are listed.EQ-Bench
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Throughput
- 41.0 tok/s
- Faster than 30% of 254 models
- Time to first token
- 6.5 s
- Quicker than 26% of 254 models
- Prompt cache hits
- 60.3%
- About $0.62 per 1M input tokens with caching
- Request success (24h)
- 97.6%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-5v-turbo:thinking",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="z-ai/glm-5v-turbo:thinking",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Z.ai
Related models
Other Z.ai models, starting with the same family.