Skip to content
Sovyron

GLM-4.6

glm205k context131k max outputreleased Sep 30, 2025Open weightsReasoningTool calling

As of Nov 22, 2026, the cheapest GLM-4.6 API price is $0.274 per 1M input tokens (AIHubMix) and $1.0959 per 1M output tokens (AIHubMix). GLM-4.6 is offered by 26 providers in the glm family, open weights, reasoning enabled. Z.AI's own rate is $2.2 per 1M output tokens. One provider lists it as a free-tier offer.

Cheapest input
$0.274
Cheapest output
$1.0959
Official (Z.AI)
$2.2
output per 1M tokens
Providers
26
offering this model
Spread
2.0×
max / min output
Free offers
1
free-tier offer

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.

GLM-4.6 API prices by provider in USD per 1M tokens, updated Nov 22, 2026
AIHubMixopenglm-4.6Cheapest$0.274Cheapest$1.0959$0.0548—200k—
302.AIopenglm-4.6†$0.286$1.142——205k—
ZenMuxopenz-ai/glm-4.6$0.2911$1.1645$0.0582—200k63d ago
Heliconeopenglm-4.6$0.45$1.5——205k31d ago
Venice AIopenzai-org-glm-4.6$0.43$1.75$0.08—198k—
Meganovaopenzai-org/GLM-4.6$0.45$1.9——203k—
Deep Infraopenzai-org/GLM-4.6$0.5$2$0.1—203k—
Kilo Gatewayopenz-ai/glm-4.6$0.5$2$0.1—203k24d agoout −9.1%
OpenRouteropenz-ai/glm-4.6$0.5$2$0.1—205k24d agoout −9.1%
IO.NETopenzai-org/GLM-4.6$0.52$2.0375$0.26—200k31d ago
Abacusopenzai-org/GLM-4.6$0.55$2.2——203k31d ago
Hugging Faceopenzai-org/GLM-4.6$0.55$2.2——205k—
DevPass (LLM Gateway)openglm-4.6$0.55$2.2$0.11free205k—
LLM Gatewayopennovita/glm-4.6$0.55$2.2$0.11—205k—
NanoGPTopenz-ai/glm-4.6$0.55$2.2$0.11—200k11d agoout +10%
Novita AIopenzai-org/glm-4.6$0.55$2.2$0.11—205k—
Eden AIopenzai/glm-4.6$0.6$2.2$0.11—203k—
Impossiblopenzai/glm-4.6$0.6$2.2$0.11—205k—
LLM Gatewayopenzai/glm-4.6$0.6$2.2$0.11—200k—
Merge Gatewayopenzai/glm-4.6$0.6$2.2$0.11free200k—
Ofoxopenz-ai/glm-4.6$0.6$2.2$0.11—205k71d ago
OrcaRouteropenz-ai/glm-4.6$0.6$2.2$0.11free205k—
Vercel AI Gatewayopenzai/glm-4.6$0.6$2.2$0.11—200k—
Z.AIopenglm-4.6$0.6$2.2$0.11free205k—
Zhipu AIopenglm-4.6$0.6$2.2$0.11free205k—
Poeopennovita/glm-4.6$0.6061$2.2222$0.1111———
ModelScopefreeZhipuAI/GLM-4.6freefree——203k—

GLM-4.6 price history

Output price per 1M tokens since tracking began on Sep 10, 2026, for the 6 cheapest of 8 providers whose rate moved. Each step is a recorded change. All recent price changes.

GLM-4.6 output price per 1M tokens by provider, Sep 10, 2026 to Nov 22, 2026$0$0.625$1.25$1.875$2.5Sep 10, 2026Oct 17, 2026Nov 22, 2026
ZenMux$1.1645Helicone$1.5Kilo Gateway$2OpenRouter$2IO.NET$2.0375Abacus$2.2
GLM-4.6 price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
NanoGPT$0.5 → $0.55$2 → $2.2+10%
Kilo Gateway$0.55 → $0.5$2.2 → $2−9.1%
OpenRouter$0.55 → $0.5$2.2 → $2−9.1%
IO.NET$0.4 → $0.52$1.75 → $2.0375+16.4%
Abacus$0.6 → $0.55$2.2−8.3%
Helicone$0.45 → $0.45$1.5+0%
Kilo Gateway$0.5 → $0.55$2 → $2.2+10%
OpenRouter$0.5 → $0.55$2 → $2.2+10%
NanoGPT$0.35 → $0.5$1.4 → $2+42.9%
Kilo Gateway$0.43 → $0.5$1.75 → $2+14.3%
OpenRouter$0.43 → $0.5$1.75 → $2+14.3%
ZenMux$0.35 → $0.2911$1.54 → $1.1645−24.4%
Ofox$0.4 → $0.6$1.9 → $2.2+15.8%

GLM-4.6 pricing FAQ

What is the cheapest GLM-4.6 API?

As of Nov 22, 2026, AIHubMix has the lowest GLM-4.6 output price at $1.0959 per 1M tokens, and AIHubMix has the lowest input price at $0.274 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How much does GLM-4.6 cost on Z.AI?

Z.AI charges $0.6 per 1M input tokens and $2.2 per 1M output tokens for GLM-4.6.

How many providers offer GLM-4.6?

26 providers list GLM-4.6 on Sovyron; 26 of them sell it at a metered per-token price.

Is GLM-4.6 free?

One provider lists a free-tier offer: ModelScope. Free tiers usually have rate limits.

What is the context window of GLM-4.6?

GLM-4.6 supports a 205k-token context window and up to 131k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—