Scheduled for retirement on Mar 30, 2027. Still available at the prices below until then.
Context
205K
Max output
203K
Serving providers
10
Cheapest input
$0.40 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
42 t/s
tokens / second
Time to first token
2.31s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CritPt | 2% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 1324.5 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 1169.1 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 86% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 27% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 68% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| LiveCodeBench | 89% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Long-Context Reasoning | 71% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 86% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience | -36.4 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Accuracy | 0.3 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Non Hallucination | 0.1 | reasoning: false | — | |||||||||||||||||
| ||||||||||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 45% | — | — | |||||||||||||||||
| ||||||||||||||||||||
| SWE-bench Verified | 74% | default | — | |||||||||||||||||
| TerminalBench Hard | 32% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 45% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 12% | default | — | |||||||||||||||||
| τ²-bench | 96% | default | — | |||||||||||||||||
| ||||||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.40 to $2.25 per 1M tokens across 10 providers, so the dearest route costs 463% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $0.40 | $1.75 | 1 | |||||||||||||
Standarddeepinfra/zai-org/GLM-4.7
| ||||||||||||||||
| Together AI | $0.45 | $2.00 | 1 | |||||||||||||
Standardtogether_ai/zai-org/GLM-4.7
| ||||||||||||||||
| Baseten | $0.60 | $2.20 | 1 | |||||||||||||
Standardbaseten/zai-org/GLM-4.7
| ||||||||||||||||
| Amazon Bedrock | $0.60 | $2.20 | 1 | |||||||||||||
Standardzai.glm-4.7
| ||||||||||||||||
| Fireworks AI | $0.60 | $2.20 | 1 | |||||||||||||
Standardfireworks_ai/accounts/fireworks/models/glm-4p7
| ||||||||||||||||
| Novita | $0.60 | $2.20 | 1 | |||||||||||||
Standardnovita/zai-org/glm-4.7
| ||||||||||||||||
| OpenRouter | $0.60 | $2.20 | 1 | |||||||||||||
Standardz-ai/glm-4.7
| ||||||||||||||||
| VercelVercel reseller quote | $0.60 | $2.20 | 1 | |||||||||||||
Standardzai/glm-4.7
| ||||||||||||||||
| Cerebras is dearest at $2.25 / $2.75 | ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 33% since first tracked
Cost calculator
estimate your monthly spend on this model$220
estimated / month
Model IDs
copy the exact identifier for your platformdeepinfra/zai-org/GLM-4.7together_ai/zai-org/GLM-4.7fireworks_ai/accounts/fireworks/models/glm-4p7zai/glm-4.7zai.glm-4.7novita/zai-org/glm-4.7z-ai/glm-4.7zai/glm-4.7baseten/zai-org/GLM-4.7cerebras/zai-glm-4.7
Frequently asked questions
GLM 4.7 pricing, context and availabilityIs GLM 4.7 still available?
Yes. GLM 4.7 is scheduled for retirement on 2027-03-30.
How much does GLM 4.7 cost?
GLM 4.7 costs $0.40 per 1M input tokens from DeepInfra, and $1.75 per 1M output tokens from DeepInfra. Across 10 serving providers, input prices range from $0.40 to $2.25 per 1M tokens.
What is the context window of GLM 4.7?
GLM 4.7 accepts up to 205K tokens of context and can return up to 203K output tokens.
Which providers serve GLM 4.7?
GLM 4.7 is available from 10 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.
What can GLM 4.7 do?
GLM 4.7 supports tool use, reasoning, prompt caching and structured output.
Other Zhipu models
compare pricing across the Zhipu lineup Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI