Choose a model to open its comparison page.
GLM-4.7 benchmark, API pricing, and provider data cover 151 API providers, with prices starting at $0.010/request. GLM-4.7 free API options are available from 2 providers. The page also shows measured API speed and first-token latency.
Zhipu GLM-4.7 is a flagship GLM release from Zhipu AI with advanced Chinese-English reasoning, coding, and agent features.
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
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 |
|---|---|---|---|---|---|---|
Google google-vertex | $0.600/M | $2.20/M | 100.0% | — | — | 200K tokens / 128K tokens |
Cerebras cerebras/fp16 | $2.25/M | $2.75/M | 99.9% | — | — | 131.1K tokens / 41.0K tokens |
DeepInfra deepinfra/fp4 | $0.400/M | $1.75/M | 99.9% | — | — | 202.8K tokens / 131.1K tokens |
Venice venice/fp4 | $0.550/M | $2.65/M | 99.3% | — | — | 198K tokens / 16.4K tokens |
AtlasCloud atlas-cloud/fp8 | $0.520/M | $1.85/M | 96.5% | — | — | 202.8K tokens / 202.8K tokens |
Novita novita/fp8 | $0.540/M | $1.98/M | 96.3% | — | — | 204.8K tokens / 131.1K tokens |
StreamLake streamlake/fp8 | $0.480/M | $1.76/M | 94.9% | — | — | 200K tokens / 128K tokens |
Z.AI z-ai/fp4 | $0.600/M | $2.20/M | 94.7% | — | — | 202.8K tokens / 131.1K tokens |
Phala phala | $0.850/M | $3.30/M | 88.0% | — | — | 131.1K tokens / 131.1K tokens |
Compare GLM-4.7 API pricing across 149 providers. Prices range from $0.010/request to $2497.50/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-4.7 | default | -54%$0.274/M | -50%$1.10/M | 64.1 t/s | 7.68 s | — | |
L1 100% | GLM-4.7 | default | $0.040/request | - | — | — | — | |
L1 100% | glm-4.7 | sale | $1.00/M | $4.00/M | — | — | — | |
L1 100% | glm-4.7 | zai-officially | -14%$0.514/M Cache read$0.103/M | -6%$2.06/M | — | — | — | |
L1 99% | glm-4.7 | default | -77%$0.137/M | -75%$0.548/M | — | — | — | |
L1 100% | glm-4.7 | default | -58%$0.255/M | -54%$1.02/M | — | — | — | |
L1 100% | glm-4.7 | glm | -27%$0.438/M Cache read$0.088/M | -20%$1.75/M | — | — | — | |
L1 100% | glm-4.7 | default | -93%$0.041/M Cache read$0.0068/M | -93%$0.151/M | — | — | — | |
L1 100% | glm-4.7 | default | $0.010/request | - | — | — | — | |
L1 100% | [极速0.05/次]GLM-4.7 | default | $0.046/request | - | — | — | — | |
L1 100% | glm-4.7 | default | -76%$0.144/M Cache read$0.026/M | -76%$0.527/M | — | — | — | |
L1 100% | glm-4.7 | default | -63%$0.219/M | -60%$0.877/M | — | — | — | |
L1 100% | glm-4.7 | other | -58%$0.250/M Cache read$0.046/M | -58%$0.917/M | — | — | — | |
L1 100% | glm-4.7 | default | $0.822/M | $3.84/M | — | — | — | |
L1 99% | glm-4.7 | default | -77%$0.137/M | -75%$0.548/M | — | — | — | |
L1 100% | glm-4.7 | default | -54%$0.274/M | -25%$1.64/M | — | — | — | |
L1 99% | glm-4.7 | default | $0.616/M | $2.88/M | — | — | — | |
L1 99% | glm-4.7 | default | $1.96/M Cache read$0.392/M | $7.83/M | — | — | — | |
L1 99% | Pro/zai-org/GLM-4.7 | default | $1.96/M | $7.83/M | — | — | — | |
L1 100% | zai/glm-4.7 | group2 | $3.08/M | $3.77/M | — | — | — |
2 metrics
2 metrics
9 metrics · Rated
9 metrics · Rated
6 metrics · Rated
6 metrics · Provisional
3 metrics · Estimated
1 metric · Provisional
2 metrics · Provisional
2 metrics · Provisional
