jishie

GPT-4o

poe/openai/gpt-4o · family gpt · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.

This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See Poe’s docs for per-unit rates.

Provider
Poe (poe)
Kind
text (outputs text)
Context
128,000 tokens
Max output
8,192 tokens
Capabilities
tools text image

Same model, other providers

“GPT-4o” is offered by 21 providers — cheapest-effective first. Cloudflare AI Gateway is the cheapest at $2.19 blended.

ProviderInputOutputBlendedContext
Cloudflare AI Gateway$1.25$5$2.19128k
Ofox$2$8$3.50128k
302.AI$2.5$10$4.38128k
NanoGPT$2.5$10$4.38128k
Kilo Gateway$2.5$10$4.38128k
Abacus$2.5$10$4.38128k
OpenRouter$2.5$10$4.38128k
Azure$2.5$10$4.38128k
Azure Cognitive Services$2.5$10$4.38128k
Impossibl$2.5$10$4.38128k
FrogBot$2.5$10$4.38128k
Vercel AI Gateway$2.5$10$4.38128k
Poe (this)———128k

Call it

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

Most providers are OpenAI-compatible — point base_url at Poe 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-4o","messages":[{"role":"user","content":"hello"}]}'

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

← all Poe models · model index · JSON