GPT-3.5-Turbo
poe/openai/gpt-3.5-turbo · family gpt · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$0.69
Blended $/1M (3:1)
$0.45
Input $/1M
$1.4
Output $/1M
$1.85
1M in + 1M out
—
Cache read $/1M
#3380 of 7,708
Cheapest rank
- Provider
- Poe (
poe) - Kind
- text (outputs text)
- Context
- 16,384 tokens
- Max output
- 2,048 tokens
- Capabilities
- tools text image
Same model, other providers
“GPT-3.5-Turbo” is offered by 8 providers — cheapest-effective first. This one (Poe) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Poe (this) | $0.45 | $1.4 | $0.69 | 16k |
| Kilo Gateway | $0.5 | $1.5 | $0.75 | 16k |
| OpenRouter | $0.5 | $1.5 | $0.75 | 16k |
| Impossibl | $0.5 | $1.5 | $0.75 | 16k |
| OrcaRouter | $0.5 | $1.5 | $0.75 | 16k |
| Eden AI | $0.5 | $1.5 | $0.75 | 16k |
| DevPass (LLM Gateway) | $0.5 | $1.5 | $0.75 | 16k |
| OpenAI | $0.5 | $1.5 | $0.75 | 16k |
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-3.5-turbo","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):