How much does GLM 4.6 cost?

GLM 4.6 costs $0.43/M input tokens and $1.75/M output tokens, with separate rates for Cache Read at $0.08/M tokens.

What is the context length of GLM 4.6?

GLM 4.6 has a 204,800 token context window. It supports up to 16,384 completion tokens.

Does GLM 4.6 support tool calling and structured outputs?

Yes. GLM 4.6 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Which providers serve GLM 4.6?

GLM 4.6 is served by 4 providers on OpenRouter: DeepInfra, Venice, NovitaAI, and Z.ai. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was GLM 4.6 released?

GLM 4.6 was released on September 30, 2025. Its knowledge cutoff is March 31, 2025.

Z.ai: GLM 4.6

z-ai/glm-4.6

Model weights

Compare

Compared with GLM-4.5, this generation brings several key improvements:

Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks. Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages. Advanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability. More capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks. Refined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.

Modalities

In / out price

$0.43 / $1.75per 1M

Context

205K

Released

Sep 30, 2025

Knowledge cutoff

Mar 2025

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$0.43	$1.75	$0.08	0.90s	32 tok/s	99.92%
	$0.50	$2.00	$0.10	0.83s	32 tok/s	99.96%
	$0.60	$2.20	$0.11	3.96s	29 tok/s	99.87%
	$0.55	$2.20	$0.11	4.52s	27 tok/s	100.00%
Not used in Standard routing:Why these endpoints are not used
Flex	$0.40	$1.60	$0.08	0.81s	27 tok/s	100.00%

Input $0.43Output $1.75
32 tok/s99.92% uptime
Input $0.50Output $2.00
32 tok/s99.96% uptime
Input $0.60Output $2.20
29 tok/s99.87% uptime
Input $0.55Output $2.20
27 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.40Output $1.60
Flex
27 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.273/M tokens

Output

$2.006/M tokens

GLM 4.6 — Price history

Price history

No effective price data for this selection

		$0.238	$2.20	71.0%	16.4%
		$0.258	$2.20	69.9%	22.0%
		$0.260	$1.75	48.7%	21.8%
		$0.304	$2.00	49.1%	39.8%
Not used in Standard routing:Why these endpoints are not used
	Flex	$0.400	$1.60	0.0%	0.0%

Effective in $0.238Effective out $2.20
Token share
16.4%
Effective in $0.258Effective out $2.20
Token share
22.0%
Effective in $0.260Effective out $1.75
Token share
21.8%
Effective in $0.304Effective out $2.00
Token share
39.8%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.400Effective out $1.60
FlexToken share
0.0%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

32tok/s

P50, best across providers

Latency

0.81s

P50, best provider

Latency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchNovitaAI84.8%72.8%Z.ai85.5%71.5%auto-routing80.0%72.2%DeepInfra78.3%69.1%Venice73.6%69.0%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.25%

Availability over the last 3 days

Last 72 hours

Availability 99.25%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

98.88%

Without Routing

97.71%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Z.ai: GLM 4.6 (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	GLM-4.6 (Reasoning) Coding Index	45.8
Artificial Analysis	GLM-4.6 (Reasoning) GPQA Diamond	78.0%
Artificial Analysis	GLM-4.6 (Reasoning) HLE	14.5%
Artificial Analysis	GLM-4.6 (Reasoning) IFBench	43.4%
Artificial Analysis	GLM-4.6 (Reasoning) τ²-Bench Telecom	70.5%
Artificial Analysis	GLM-4.6 (Reasoning) AA-LCR	54.0%
Artificial Analysis	GLM-4.6 (Reasoning) τ-Bench Banking	13.4%
Artificial Analysis	GLM-4.6 (Reasoning) GDPval-AA	13.2%
Artificial Analysis	GLM-4.6 (Reasoning) CritPt	1.1%
Artificial Analysis	GLM-4.6 (Reasoning) LiveCodeBench	69.5%
Artificial Analysis	GLM-4.6 (Reasoning) Terminal-Bench Hard	25.0%
Artificial Analysis	GLM-4.6 (Reasoning) Terminal-Bench 2.1	49.4%
Artificial Analysis	GLM-4.6 (Reasoning) MMLU-Pro	82.9%
Artificial Analysis	GLM-4.6 (Reasoning) AIME 2025	86.0%
Artificial Analysis	GLM-4.6 (Non-reasoning) GPQA Diamond	63.2%
Artificial Analysis	GLM-4.6 (Non-reasoning) HLE	5.5%
Artificial Analysis	GLM-4.6 (Non-reasoning) IFBench	36.7%
Artificial Analysis	GLM-4.6 (Non-reasoning) τ²-Bench Telecom	76.9%
Artificial Analysis	GLM-4.6 (Non-reasoning) AA-LCR	26.3%
Artificial Analysis	GLM-4.6 (Non-reasoning) CritPt	0.0%
Artificial Analysis	GLM-4.6 (Non-reasoning) LiveCodeBench	56.1%
Artificial Analysis	GLM-4.6 (Non-reasoning) Terminal-Bench Hard	28.8%
Artificial Analysis	GLM-4.6 (Non-reasoning) MMLU-Pro	78.4%
Artificial Analysis	GLM-4.6 (Non-reasoning) AIME 2025	44.3%
Design Arena	GLM 4.6 Agents Arena Androidnative Elo	1072
Design Arena	GLM 4.6 Agents Arena Full Stack Elo	1003
Design Arena	GLM 4.6 Agents Arena Godotgamedev Elo	1180
Design Arena	GLM 4.6 Agents Arena Mobile Apps Elo	1088
Design Arena	GLM 4.6 Models Arena 3D Elo	1108
Design Arena	GLM 4.6 Models Arena Code Categories Elo	1155
Design Arena	GLM 4.6 Models Arena Data Visualization Elo	1158
Design Arena	GLM 4.6 Models Arena Game Development Elo	1140
Design Arena	GLM 4.6 Models Arena SVG Elo	1098
Design Arena	GLM 4.6 Models Arena UI Component Elo	1138
Design Arena	GLM 4.6 Models Arena Website Elo	1166
Vals AI	GLM 4.6 AIME	92.7%
Vals AI	GLM 4.6 CorpFin v2	56.8%
Vals AI	GLM 4.6 Finance Agent v1.1	36.5%
Vals AI	GLM 4.6 GPQA Diamond	74.5%
Vals AI	GLM 4.6 IOI v1	4.3%
Vals AI	GLM 4.6 LiveCodeBench	81.0%
Vals AI	GLM 4.6 LegalBench	79.6%
Vals AI	GLM 4.6 MedQA	92.2%
Vals AI	GLM 4.6 MGSM	89.7%
Vals AI	GLM 4.6 MMLU Pro	82.2%
Vals AI	GLM 4.6 TaxEval v2	66.2%
Vals AI	GLM 4.6 Terminal-Bench 2.0	28.1%
Vals AI	GLM 4.6 Vibe Code Bench v1.1	3.1%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Janitor AI

Janitor AI is a chatbot platform where users create and chat with custom AI characters for interactive roleplay, storytelling, and immersive fiction.

11.5Btokens

Sophia's LoreBary

Organize and enhance your roleplay creations.

3.98Btokens

SillyTavern

SillyTavern is the LLM frontend for power users, a chat interface that connects to any model and gives deep control through character creation, roleplay, and prompt customization.

2.04Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

1.68Btokens

Chub AI

GenAI for everyone

1.25Btokens

Rest of OpenRouter

305M

Top 5 Apps

183M

Not currently available through EU in-region routing. In-region routing docs

More models from Z.ai

GLM 5.3 FlashX Legal

GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement learning in task environments modeled on real legal workflows, targeting document understanding, legal reasoning, and multi-step task execution such as legal research, contract review, cross-document consistency checks, and drafting or revising legal documents.

It keeps the GLM-5.3-FlashX 1M-token context window, mandatory thinking mode, function calling, structured output, and streaming, and is designed to run in agent setups connected to legal data and document-editing tools (MCP services).

Text1.0M context$0.37 / $1.25

GLM 5.3 Prime

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token context window and up to 128K output tokens, and targets coding and agentic workloads, including long-horizon multi-turn agent orchestration, real-time conversation, and streaming code generation.

Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.

Text1M context$2.80 / $8.80

GLM 5.3 FlashX

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture (320B total parameters, 18B active), it is suited for efficient coding, visual understanding, and long-horizon agent tasks with a 1M-token context window.

Text1.0M context$0.37 / $1.25

GLM Flash Latest

This model always redirects to the latest model in the GLM Flash family.

Text1.0M context

GLM 5.3 Flash

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.

Text1.0M context$0.0399 / $0.0784

GLM 5.3 Flash (batch)

Text1.0M context$0.05 / $0.18

GLM Latest

This model always redirects to the latest GLM model from Z.ai.

Text1.0M context

GLM 5.3

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.

Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.

Text1.0M context$0.0699 / $1.40

GLM 5.3 (batch)

Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.

Text1.0M context$0.45 / $2

GLM 5.2

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.

Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.

Text1.0M context$0.0066 / $7.983

GLM 5.2 (batch)

Text1.0M context$0.298 / $0.916

GLM 5.1

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.

Text205K context$0.8988 / $2.825

GLM 5V Turbo

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.

Text203K context$1.20 / $4

GLM 5 Turbo

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.

Text203K context$1.20 / $4

GLM 5

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.

Text205K context$0.60 / $1.92

GLM 4.7 Flash

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.

Text200K context$0.0605 / $0.40

GLM 4.7

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.

Text205K context$0.40 / $1.75

GLM 4.6V

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts and charts directly as visual inputs, and integrates native multimodal function calling to connect perception with downstream tool execution. The model also enables interleaved image-text generation and UI reconstruction workflows, including screenshot-to-HTML synthesis and iterative visual editing.

Text131K context$0.30 / $0.90

GLM 4.5V

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a "thinking mode" for deep reasoning and a "non-thinking mode" for fast responses. Reasoning behavior can be toggled via the reasoning enabled boolean. Learn more in our docs

Text66K context$0.60 / $1.80

GLM 4.5

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a "thinking mode" designed for complex reasoning and tool use, and a "non-thinking mode" optimized for instant responses. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs

Text131K context$0.60 / $2.20

Z.ai: GLM 4.6

Providers