jishie

GPT-5-Codex

impossibl/openai/gpt-5-codex · family gpt-codex · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

$3.44Blended $/1M (3:1)
$1.25Input $/1M
$10Output $/1M
$11.251M in + 1M out
$0.125 −90%Cache read $/1M
#4427 of 5,000Cheapest rank
Provider
Impossibl (impossibl)
Context
400,000 tokens
Max output
128,000 tokens
Capabilities
toolsreasoningtextimage

Same model, other providers

“GPT-5-Codex” is offered by 8 providers — cheapest-effective first. Poe is the cheapest at $3.08 blended.

ProviderInputOutputBlendedContext
Poe$1.1$9$3.08400k
Jiekou.AI$1.125$9$3.09400k
Impossibl (this)$1.25$10$3.44400k
Abacus$1.25$10$3.44400k
Azure Cognitive Services$1.25$10$3.44400k
Azure$1.25$10$3.44400k
OrcaRouter$1.25$10$3.44400k
Vercel AI Gateway$1.25$10$3.44400k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Impossibl 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-5-codex","messages":[{"role":"user","content":"hello"}]}'

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