Gpt 5 Nano

Provider: openrouter · openrouter/openai/gpt-5-nano

Pricing per million tokens

Component USD per 1M tokens
Input $0.05
Output $0.40
Cached input (read) $0.0050

💡 With prompt caching, you save up to 90% 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
$0.12
per month
Saves $0.01 via caching
Medium
10M in / 2000k out
$1.16
per month
Saves $0.14 via caching
Large
100M in / 20000k out
$11.65
per month
Saves $1.35 via caching

Context

Input window
272,000 tokens
Max output
128,000 tokens

Capabilities

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

Compare Gpt 5 Nano with similar models

Qwen3 235b A22b 2507
openrouter
$0.07 in / $0.10 out
Mimo V2 Flash
openrouter
$0.09 in / $0.29 out
Glm 4.7 Flash
openrouter
$0.07 in / $0.40 out
Ui Tars 1.5 7b
openrouter
$0.10 in / $0.20 out
Deepseek Chat V3.1
openrouter
$0.20 in / $0.80 out
Deepseek V3.2 Exp
openrouter
$0.20 in / $0.40 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.