GLM-5
zai/glm-5Por Z.AI / Zhipu · família: glm · lançado 2026-02-11 · data de conhecimento: 2025-04
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capacidades
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding66
- Tool calling40/40
- Structured output0/20
- Reasoning10/10
- Context window (100K → 1M)6/20
- Provider availability10/10
Agents75
- Tool calling35/35
- Structured output0/25
- Reasoning15/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output42
- Structured output / JSON mode0/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume12/20
Cost efficiency52
- Headline price (log-scaled)47/95
- Has prompt-cache pricing5/5
Long context56
- Context window (100K → 2M)46/90
- Has published price for full window10/10
Production-readiness96
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $6.60 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $13.20 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $3.60 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $11.20 $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $13.92 $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Detalhes de preço
Preço recomendado de zai · glm-5
Provedor mais barato: alibaba-coding-plan · Unknown entrada + Unknown saída
Disponível em 38 provedores
| Provedor | ID do modelo do provedor | Entrada / 1M | Saída / 1M | Contexto | Lançado |
|---|---|---|---|---|---|
| Z.AI zai | glm-5 | $1.00 | $3.20 | 205K | 2026-02-11 |
| Zhipu AI zhipuai | glm-5 | $1.00 | $3.20 | 205K | 2026-02-11 |
| Amazon Bedrock amazon-bedrock | zai.glm-5 | $1.00 | $3.20 | 203K | 2026-03-18 |
| OpenRouter openrouter | z-ai/glm-5 | $1.00 | $3.20 | 203K | 2026-02-12 |
| Vercel AI Gateway vercel | zai/glm-5 | $1.00 | $3.20 | 203K | 2026-02-12 |
| Fireworks AI fireworks-ai | accounts/fireworks/models/glm-5 | $1.00 | $3.20 | 203K | 2026-02-11 |
| Deep Infra deepinfra | zai-org/GLM-5 | $0.800 | $2.56 | 203K | 2026-02-12 |
| Hugging Face huggingface | zai-org/GLM-5 | $1.00 | $3.20 | 203K | 2026-02-11 |
| 302.AI 302ai | glm-5 | $0.600 | $2.60 | 205K | 2026-02-12 |
| NanoGPT nano-gpt | TEE/glm-5 | $1.20 | $3.50 | 203K | 2026-02-11 |
| NanoGPT nano-gpt | zai-org/glm-5 | $0.300 | $2.55 | 200K | 2026-02-11 |
| Abacus abacus | zai-org/glm-5 | $1.00 | $3.20 | 205K | 2026-02-11 |
| SiliconFlow (China) siliconflow-cn | Pro/zai-org/GLM-5 | $1.00 | $3.20 | 205K | 2026-02-12 |
| OpenCode Go opencode-go | glm-5 | $1.00 | $3.20 | 203K | 2026-02-11 |
| Alibaba (China) alibaba-cn | glm-5 | $0.860 | $3.15 | 203K | 2026-02-11 |
| ZenMux zenmux | z-ai/glm-5 | $0.580 | $2.60 | 200K | 2026-02-12 |
| NovitaAI novita-ai | zai-org/glm-5 | $1.00 | $3.20 | 203K | 2026-02-11 |
| Weights & Biases wandb | zai-org/GLM-5-FP8 | $1.00 | $3.20 | 200K | 2026-02-11 |
| DInference dinference | glm-5 | $0.750 | $2.40 | 200K | 2026-02-11 |
| Qiniu qiniu-ai | z-ai/glm-5 | Unknown | Unknown | 200K | 2026-02-12 |
| Kilo Gateway kilo | z-ai/glm-5 | $0.720 | $2.30 | 203K | 2026-02-12 |
| OpenCode Zen opencode | glm-5 | $1.00 | $3.20 | 205K | 2026-02-11 |
| Nebius Token Factory nebius | zai-org/GLM-5 | $1.00 | $3.20 | 200K | 2026-03-01 |
| Ollama Cloud ollama-cloud | glm-5 | Unknown | Unknown | 203K | 2026-02-11 |
| Baseten baseten | zai-org/GLM-5 | $0.950 | $3.15 | 203K | 2026-02-12 |
| Alibaba Coding Plan alibaba-coding-plan | glm-5 | Unknown | Unknown | 203K | 2026-02-11 |
| Venice AI venice | zai-org-glm-5 | $1.00 | $3.20 | 198K | 2026-02-11 |
| Meganova meganova | zai-org/GLM-5 | $0.800 | $2.56 | 203K | 2026-02-11 |
| Synthetic synthetic | hf:zai-org/GLM-5 | $1.00 | $3.00 | 197K | 2026-02-12 |
| DigitalOcean digitalocean | glm-5 | $1.00 | $3.20 | 203K | 2026-02-11 |
| Vultr vultr | GLM-5-FP8 | $0.850 | $3.10 | 200K | 2026-02-11 |
| Alibaba Coding Plan (China) alibaba-coding-plan-cn | glm-5 | Unknown | Unknown | 203K | 2026-02-11 |
| Friendli friendli | zai-org/GLM-5 | $1.00 | $3.20 | 203K | 2026-02-12 |
| Cortecs cortecs | glm-5 | $1.08 | $3.44 | 203K | 2026-02-11 |
| SiliconFlow siliconflow | zai-org/GLM-5 | $1.00 | $3.20 | 205K | 2026-02-12 |
| LLM Gateway llmgateway | glm-5 | $1.00 | $3.20 | 205K | 2026-02-11 |
| FastRouter fastrouter | z-ai/glm-5 | $0.950 | $3.15 | 205K | 2026-02-11 |
| Tencent Coding Plan (China) tencent-coding-plan | glm-5 | Unknown | Unknown | 203K | 2026-02-11 |
Inconsistências de dados entre provedores
- context_window varies: 196608, 198000, 200000, 202752, 202800, 203000, 204800, 205000
- release_date varies (span 35d): 2026-02-11, 2026-02-12, 2026-03-01, 2026-03-18
Os provedores reportam valores diferentes para este modelo. Os dados rápidos acima usam um provedor representativo; consulte a tabela para detalhes por provedor.
Frequently asked questions
How much does GLM-5 cost?
GLM-5 costs $1.00 per 1M input tokens and $3.20 per 1M output tokens, sourced from zai. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of GLM-5?
GLM-5 has a context window of 205K tokens, with a max output of 131K tokens per reply. This is the total combined size of prompt + completion.
Does GLM-5 support tool calling?
Yes. GLM-5 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does GLM-5 support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for GLM-5 in our data source. Verify with Z.AI / Zhipu's official documentation before relying on it in production.
Can GLM-5 accept image input?
No. GLM-5 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is GLM-5 open-weight?
Yes. GLM-5's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to GLM-5?
If GLM-5 doesn't fit, consider GLM-4.7, GLM-5.1, GLM-4.6. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More Z.AI / Zhipu models
- GLM-4.7$0.60 in / $2.20 out
- GLM-5.1$1.40 in / $4.40 out
- GLM-4.6$0.60 in / $2.20 out
- GLM-4.7-Flash$0.06 in / $0.40 out
- GLM-4.5$0.60 in / $2.20 out
Capability lists this model is in
Última atualização:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.