Glm 4.5v

Provider: novita · novita/zai-org/glm-4.5v

Pricing per million tokens

Component USD per 1M tokens
Input $0.60
Output $1.80
Cached input (read) $0.11

💡 With prompt caching, you save up to 82% on cached input tokens — massive for repeated context like system prompts, RAG retrieval, or long conversations.

Monthly cost estimates

Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.

Small
1M in / 200k out
$0.81
per month
Saves $0.15 via caching
Medium
10M in / 2000k out
$8.13
per month
Saves $1.47 via caching
Large
100M in / 20000k out
$81.30
per month
Saves $14.70 via caching

Context

Input window
65,536 tokens
Max output
16,384 tokens

Capabilities

  • ✅ Vision (image input)
  • ✅ Function / tool calling
  • ⬜ Prompt caching
  • ⬜ Web search
  • ✅ JSON / response schema

Compare Glm 4.5v with similar models

Qwen3 Vl 235b A22b Thinking
novita
$0.98 in / $3.95 out
Glm 4.6v
novita
$0.30 in / $0.90 out
Qwen3 Vl 235b A22b Instruct
novita
$0.30 in / $1.50 out
Kimi K2 Instruct
novita
$0.57 in / $2.30 out
Glm 4.5
novita
$0.60 in / $2.20 out
Qwen3 235b A22b Thinking 2507
novita
$0.30 in / $3.00 out

Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.