Deprecated on Jan 20, 2026. 9 providers still list it at the prices below.
Context
205K
Max output
203K
Serving providers
9
Cheapest input
$0.50 /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
34 t/s
tokens / second
Time to first token
4.45s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CritPt | 1% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 631.4 | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 933.9 | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 78% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 14% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 43% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| LiveCodeBench | 70% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Long-Context Reasoning | 54% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 83% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience | -31.7 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Accuracy | 0.3 | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Non Hallucination | 0.3 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 38% | — | — | |||||||||||||||||
| ||||||||||||||||||||
| SWE-bench Pro | 10% | default | — | |||||||||||||||||
| TerminalBench Hard | 29% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 49% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 13% | reasoning: true | — | |||||||||||||||||
| τ²-bench | 77% | 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 $0.50 to $2.25 per 1M tokens across 9 providers, so the dearest route costs 350% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $0.50 | $2.00 | 1 | ||||||||||||||||
Standarddeepinfra/zai-org/GLM-4.6
| |||||||||||||||||||
| OpenRouter | $0.50 | $2.00 | 1 | ||||||||||||||||
Standardz-ai/glm-4.6
| |||||||||||||||||||
| Fireworks AI | $0.55 | $2.19 | 1 | ||||||||||||||||
Standardfireworks_ai/accounts/fireworks/models/glm-4p6
| |||||||||||||||||||
| Novita | $0.55 | $2.20 | 1 | ||||||||||||||||
Standardnovita/zai-org/glm-4.6
| |||||||||||||||||||
| Baseten | $0.60 | $2.20 | 1 | ||||||||||||||||
Standardbaseten/zai-org/GLM-4.6
| |||||||||||||||||||
| Together AI | $0.60 | $2.20 | 1 | ||||||||||||||||
Standardtogether_ai/zai-org/GLM-4.6
| |||||||||||||||||||
| VercelVercel reseller quote | $0.60 | $2.20 | 1 | ||||||||||||||||
Standardzai/glm-4.6
| |||||||||||||||||||
| Zai | $0.60 | $2.20 | 1 | ||||||||||||||||
Standardzai/glm-4.6
| |||||||||||||||||||
| Cerebras is dearest at $2.25 / $2.75 | |||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 25% since first tracked
Cost calculator
estimate your monthly spend on this model$260
estimated / month
Model IDs
copy the exact identifier for your platformz-ai/glm-4.6deepinfra/zai-org/GLM-4.6fireworks_ai/accounts/fireworks/models/glm-4p6novita/zai-org/glm-4.6baseten/zai-org/GLM-4.6together_ai/zai-org/GLM-4.6zai/glm-4.6zai/glm-4.6cerebras/zai-glm-4.6
Frequently asked questions
GLM 4.6 pricing, context and availabilityIs GLM 4.6 still available?
GLM 4.6 was deprecated on 2026-01-20, but 9 serving providers still list it.
How much does GLM 4.6 cost?
GLM 4.6 costs $0.50 per 1M input tokens from DeepInfra, and $2.00 per 1M output tokens from DeepInfra. Across 9 serving providers, input prices range from $0.50 to $2.25 per 1M tokens.
What is the context window of GLM 4.6?
GLM 4.6 accepts up to 205K tokens of context and can return up to 203K output tokens.
Which providers serve GLM 4.6?
GLM 4.6 is available from 9 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.
What can GLM 4.6 do?
GLM 4.6 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