jishie

GPT-5.3 Codex

llmgateway/gpt-5.3-codex · family gpt-codex · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.

$4.81
Blended $/1M (3:1)
$1.75
Input $/1M
$14
Output $/1M
$15.75
1M in + 1M out
$0.175 −90%
Cache read $/1M
#7282 of 8,573
Cheapest rank
Provider
DevPass (LLM Gateway) (llmgateway)
Kind
text (outputs text)
Context
400,000 tokens
Max output
128,000 tokens
Capabilities
tools reasoning text image pdf

Same model, other providers

“GPT-5.3 Codex” is offered by 24 providers — cheapest-effective first. CommandCode is the cheapest at $3.50 blended.

ProviderInputOutputBlendedContext
CommandCode$2$8$3.50400k
DevPass (LLM Gateway) (this)$1.75$14$4.81400k
Requesty$1.75$14$4.81400k
Neon$1.75$14$4.81400k
FastRouter$1.75$14$4.81400k
OpenRouter$1.75$14$4.81400k
FrogBot$1.75$14$4.81400k
Kilo Gateway$1.75$14$4.81400k
Abacus$1.75$14$4.81400k
OpenCode$1.75$14$4.81400k
FreeModel$1.75$14$4.81400k
ZenMux$1.75$14$4.81400k
OrcaRouter$1.75$14$4.81400k

Call it

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

Most providers are OpenAI-compatible — point base_url at DevPass (LLM Gateway) and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.3-codex","messages":[{"role":"user","content":"hello"}]}'

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

← all DevPass (LLM Gateway) models · model index · JSON