jishie

GPT-5.5 Pro

neon/gpt-5-5-pro · family gpt-pro · in: text, image, pdf → out: text, image · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.

$67.50
Blended $/1M (3:1)
$30
Input $/1M
$180
Output $/1M
$210.00
1M in + 1M out
—
Cache read $/1M
#7690 of 7,708
Cheapest rank
Provider
Neon (neon)
Kind
text (outputs text, image)
Context
1,050,000 tokens
Max output
128,000 tokens
Capabilities
tools reasoning text image pdf

Same model, other providers

“GPT-5.5 Pro” is offered by 16 providers — cheapest-effective first. This one (Neon) is the cheapest.

ProviderInputOutputBlendedContext
Neon (this)$30$180$67.501.1M
Kilo Gateway$30$180$67.501.1M
OpenRouter$30$180$67.501.1M
ZenMux$30$180$67.501.1M
Impossibl$30$180$67.501.1M
Cloudflare AI Gateway$30$180$67.501M
FastRouter$30$180$67.501.1M
OrcaRouter$30$180$67.501.1M
Opper$30$180$67.501.1M
Eden AI$30$180$67.501.1M
OpenCode Zen$30$180$67.501.1M
Requesty$30$180$67.501.1M
DevPass (LLM Gateway)$30$180$67.501.1M

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gpt-5-5-pro","messages":[{"role":"user","content":"hello"}]}'

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

← all Neon models · model index · JSON