Appndo
All models

GLM 5

Z.ai203K contextReasoningTool calling

LMArena score 1446 · #60 overall · #82 in coding (2026-10-13)

Official price from Z.ai

Pricing page

Per million tokens

Input
$1.00
Output
$3.20
Cached input
$0.20
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: $16.40 a month. DeepInfra is the cheapest seller at $10.16, $6.24 less.

Where to buy it (5)

Sorted by your monthly estimate. Prices per million tokens.

  • DeepInfraCheapest

    Input / output
    $0.60 / $2.08
    Context
    203K
    Per month
    $10.16

    deepinfra/zai-org/GLM-5

  • Baseten

    Input / output
    $0.95 / $3.15
    Context
    —
    Per month
    $15.80

    baseten/zai-org/GLM-5

  • Novita AI

    Input / output
    $1.00 / $3.20
    Context
    203K
    Per month
    $16.40

    novita/zai-org/glm-5

  • Google Vertex AI

    Input / output
    $1.00 / $3.20
    Context
    200K
    Per month
    $16.40

    vertex_ai/zai-org/glm-5-maas

  • Z.aiOfficial

    Input / output
    $1.00 / $3.20
    Context
    200K
    Per month
    $16.40

    zai/glm-5

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

Similar models