Z.ai · Model
GLM 4.6V pricing, context window and specs
GLM 4.6V costs $0.30 per million input tokens and $0.90 per million output tokens, and reads up to 131,072 tokens per request. By blended price it is number 2 of Z.ai’s 7 current models here, counting from the cheapest.
- Input / 1M
- $0.30
- Output / 1M
- $0.90
- Cached / 1M
- $0.055
- Context
- 131,072
- Max output
- 32,768
- Released
- 2025-12-08
Estimate your cost with GLM 4.6VCompare all Z.ai modelsCount tokens for GLM 4.6V
Pricing
GLM 4.6V API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.30 | $0.90 |
| Cached input (read) | $0.055 | – |
Output costs 3.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 18% of the normal input price.
Examples
What GLM 4.6V costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.000626 | $19.05 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.00196 | $29.75 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.00596 | $36.26 |
| Document summariser | 8,000 / 600 | 300 | $0.00294 | $26.83 |
Change any number in the cost calculator.
Context
Context window
GLM 4.6V accepts up to 131,072 tokens per request, roughly 98,304 English words or 197 pages. That budget is shared between your prompt and the reply, and a single reply is capped at 32,768 tokens.
Filling the whole window with one prompt costs about $0.0393 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
Capabilities
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- Yes
- Accepts
- image, text, video
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
GLM 4.6V model ID
- OpenRouter
z-ai/glm-4.6v- Open weights
- zai-org/GLM-4.6V
Use the OpenRouter ID when calling it through OpenRouter; Z.ai’s own API may name it differently. See the model ID reference for the providers we document.
Z.ai
Where GLM 4.6V sits in Z.ai’s line-up
Ranked by blended price (three parts input to one part output, $0.45 per 1M for GLM 4.6V), it is number 2 of Z.ai’s 7 current models here, counting from the cheapest. One step down, GLM 5.3 Flash costs $0.2375 blended (47% less). Unlike GLM 4.6V, it reads up to 1,048,575 tokens (131,072 here). One step up, GLM 5.3 FlashX costs $0.59 (1.3× as much). Unlike GLM 4.6V, it reads up to 1,048,576 tokens (131,072 here), caps a reply at 131,072 tokens (32,768 here) and is API-only. See every Z.ai model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| GLM 5.3 Flash | $0.15 | $0.50 | 1,048,575 | 2026-08-26 |
| GLM 4.6V (this page) | $0.30 | $0.90 | 131,072 | 2025-12-08 |
| GLM 5.3 FlashX | $0.37 | $1.25 | 1,048,576 | 2026-09-18 |
| GLM 5 Turbo | $1.20 | $4 | 202,752 | 2026-03-15 |
| GLM 5V Turbo | $1.20 | $4 | 202,752 | 2026-04-01 |
| GLM 5.3 | $1.40 | $4.40 | 1,048,576 | 2026-08-18 |
| GLM 5.3 Prime | $2.80 | $8.80 | 1,000,000 | 2026-09-23 |
Z.ai’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
History
Earlier versions of GLM 4.6V
The previous model in this line is GLM 4.5V, first listed on 2025-08-11. Compared with it, GLM 4.6V’s input price is 50% lower and its output price is 50% lower, and the context window went from 65,536 to 131,072 tokens.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| GLM 4.5V | $0.60 | $1.80 | 65,536 | 2025-08-11 |
Earlier releases with the same name and size in our data, newest first. Dates are when our source first listed each model.
Save
Cheaper alternatives
- Qwen3.5-9BQwen75% cheaper
- Seed 1.6 FlashByteDance Seed71% cheaper
- GPT-6 LunaOpenAI56% cheaper
- Claude Haiku 5.5Anthropic56% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- DeepSeek V3.2DeepSeek$0.259 / $0.80
- Muse Glimmer 30BMeta$0.30 / $1.20
- MiniMax M3MiniMax$0.30 / $1.20
- Qwen3 VL 8B InstructQwen$0.25 / $0.75
- Command A+Cohere$0.30 / $1.50
Current models from other major providers, closest blended price.
FAQ
GLM 4.6V questions
How much does GLM 4.6V cost?
GLM 4.6V costs $0.30 per million input tokens and $0.90 per million output tokens, with cached input at $0.055. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00081. Use the LLM cost calculator for your own workload.
What is GLM 4.6V’s context window?
131,072 tokens, about 98,304 English words or 197 printed pages, shared between your prompt and the reply. A single reply can be up to 32,768 tokens.
Does GLM 4.6V support prompt caching and batch requests?
Yes, cached input is billed at $0.055 per million tokens (18% of the normal input price). No batch price is published for it.
What are cheaper alternatives to GLM 4.6V?
With the same essentials (image input and tool calling), the cheapest options are Qwen3.5-9B (75% cheaper), Seed 1.6 Flash (71% cheaper), GPT-6 Luna (56% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for GLM 4.6V?
On OpenRouter it is z-ai/glm-4.6v. Z.ai’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.
What did GLM 4.6V replace?
The previous Z.ai model in the same line is GLM 4.5V, first listed on 2025-08-11. Compared with it, GLM 4.6V’s input price is 50% lower and its output price is 50% lower. Prices are only part of the picture, so test the newer model on your own prompts before switching.
Is GLM 4.6V open source?
Yes, GLM 4.6V has open weights, so you can run it yourself or choose between several hosting providers. The prices here are a typical hosted price.