jishie

GPT-4.1 nano

cloudflare-ai-gateway/openai/gpt-4.1-nano · family gpt-nano · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: toolstextimage.

$0.18Blended $/1M (3:1)
$0.1Input $/1M
$0.4Output $/1M
$0.501M in + 1M out
$0.025 −75%Cache read $/1M
#1195 of 5,863Cheapest rank
Provider
Cloudflare AI Gateway (cloudflare-ai-gateway)
Kind
text (outputs text)
Context
1,047,576 tokens
Max output
32,768 tokens
Capabilities
toolstextimage

Same model, other providers

“GPT-4.1 nano” is offered by 15 providers — cheapest-effective first. This one (Cloudflare AI Gateway) is the cheapest.

ProviderInputOutputBlendedContext
Cloudflare AI Gateway (this)$0.1$0.4$0.181M
OrcaRouter$0.1$0.4$0.181M
Impossibl$0.1$0.4$0.181M
OpenRouter$0.1$0.4$0.181M
OpenAI$0.1$0.4$0.181M
NEAR AI Cloud$0.1$0.4$0.181M
Azure Cognitive Services$0.1$0.4$0.181M
Azure$0.1$0.4$0.181M
Vercel AI Gateway$0.1$0.4$0.181M
LLM Gateway$0.1$0.4$0.181M
Kilo Gateway$0.1$0.4$0.181M
Pioneer$0.1$0.4$0.181M
Abacus$0.1$0.4$0.181M

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Cloudflare AI Gateway and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-4.1-nano","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):