Appndo
All models

GLM 4.6

Z.ai205K contextReasoningTool calling

LMArena score 1440 · #76 overall · #103 in coding (2026-10-13)

Official price from Z.ai

Pricing page

Per million tokens

Input
$0.60
Output
$2.20
Cached input
$0.11
Batch input / output
—
  • Writing to the prompt cache costs $0 per million tokens.
  • Up to 128K output tokens per request.

Estimate your monthly cost

Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.

From Z.ai: $10.40 a month. Vercel AI Gateway is the cheapest seller at $8.10, $2.30 less.

Where to buy it (6)

Sorted by your monthly estimate. Prices per million tokens.

  • Vercel AI GatewayCheapest

    Input / output
    $0.45 / $1.80
    Context
    200K
    Per month
    $8.10

    vercel_ai_gateway/zai/glm-4.6

  • DeepInfra

    Input / output
    $0.50 / $2.00
    Context
    203K
    Per month
    $9.00

    deepinfra/zai-org/GLM-4.6

  • Novita AI

    Input / output
    $0.55 / $2.20
    Context
    205K
    Per month
    $9.90

    novita/zai-org/glm-4.6

  • Baseten

    Input / output
    $0.60 / $2.20
    Context
    —
    Per month
    $10.40

    baseten/zai-org/GLM-4.6

  • Together AI

    Input / output
    $0.60 / $2.20
    Context
    203K
    Per month
    $10.40

    together_ai/zai-org/GLM-4.6

  • Z.aiOfficial

    Input / output
    $0.60 / $2.20
    Context
    200K
    Per month
    $10.40

    zai/glm-4.6

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Reasoning, Tool calling.

Similar models