Choose a model to open its comparison page.
GLM-4.6 benchmark, API pricing, and provider data cover 101 API providers, with prices starting at $0.010/request. GLM-4.6 free API options are available from 2 providers. The page also shows measured API speed and first-token latency.
Zhipu AI GLM-4.6 builds on GLM-4.5 with a 200K context window, stronger real-world coding, advanced reasoning with tool use, and improved agentic performance for complex multi-step tasks.
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
Input and output token limits for this model, plus how it ranks on long-context understanding.
1 metric
2 metrics
2 metrics
1 metric · Provisional
5 metrics · Rated
4 metrics · Rated
5 metrics · Provisional
3 metrics · Provisional
0 metrics · No data
0 metrics · No data
1 metric · Provisional
Third-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
DeepInfra deepinfra/fp4 | $0.430/M | $1.74/M | 99.9% | — | — | 202.8K tokens / 131.1K tokens |
AtlasCloud atlas-cloud/fp8 | $0.600/M | $2.20/M | 99.0% | — | — | 202.8K tokens / 202.8K tokens |
Venice venice/fp4 | $0.430/M | $1.75/M | 98.7% | — | — | 198K tokens / 16.4K tokens |
Novita novita/bf16 | $0.550/M | $2.20/M | 96.7% | — | — | 204.8K tokens / 131.1K tokens |
Z.AI z-ai/fp4 | $0.600/M | $2.20/M | 86.9% | — | — | 202.8K tokens / 131.1K tokens |
Compare GLM-4.6 API pricing across 99 providers. Prices range from $0.010/request to $75.00/M. 素墨API offers the lowest rate at $0.010/request. 2 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | glm-4.6 | default | -50%$0.274/M | -50%$1.10/M | 56.0 t/s+46% | 1.36 s | — | |
L1 100% | GLM-4.6 | default | $0.040/request | - | — | — | — | |
L1 100% | glm-4.6 | sale | $1.00/M | $4.00/M | — | — | — | |
L1 99% | glm-4.6 | default | -75%$0.137/M | -75%$0.548/M | — | — | — | |
L1 100% | glm-4.6 | glm | -20%$0.438/M | -20%$1.75/M | — | — | — | |
L1 100% | glm-4.6 | default | -93%$0.041/M Cache read$0.0068/M | -93%$0.151/M | — | — | — | |
L1 100% | glm-4.6 | default | $0.010/request | - | — | — | — | |
L1 100% | glm-4.6 | default | -54%$0.255/M | -54%$1.02/M | — | — | — | |
L1 100% | glm-4.6 | other | -55%$0.250/M Cache read$0.046/M | -58%$0.917/M | — | — | — | |
L1 100% | zai-org/GLM-4.6 | 5倍倍率分组 | -38%$0.342/M Cache read$0.064/M | -41%$1.30/M | — | — | — | |
L1 100% | glm-4.6 | default | $0.822/M | $3.84/M | — | — | — | |
L1 100% | zai-org/GLM-4.6 | default | $10.50/M | $42.00/M | — | — | — | |
L1 100% | glm-4.6 | default | -80%$0.108/M Cache read$0.020/M | -84%$0.360/M | — | — | — | |
L1 100% | glm-4.6 | default | -60%$0.219/M | -60%$0.877/M | — | — | — | |
L1 100% | zai-org/GLM-4.6 | default | $1.71/M | $6.85/M | — | — | — | |
L1 100% | glm-4.6 | default | $1.96/M | $7.83/M | — | — | — | |
L1 100% | glm-4.6 | default | -75%$0.137/M | -75%$0.548/M | — | — | — | |
L1 100% | glm-4.6 | default | $0.616/M | $2.88/M | — | — | — | |
L1 100% | glm-4.6 | default | -82%$0.100/M | -82%$0.400/M | — | — | — | |
L1 99% | glm-4.6 | default | -54%$0.255/M | -54%$1.02/M | — | — | — |
