GPT-3.5 Turbo
aimlapi/openai/gpt-3.5-turbo · family gpt · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.
$0.98
Blended $/1M (3:1)
$0.65
Input $/1M
$1.95
Output $/1M
$2.60
1M in + 1M out
—
Cache read $/1M
#4256 of 8,276
Cheapest rank
- Provider
- AI/ML API (
aimlapi) - Kind
- text (outputs text)
- Context
- 16,000 tokens
- Max output
- 4,096 tokens
- Capabilities
- text
Same model, other providers
“GPT-3.5 Turbo” is offered by 4 providers — cheapest-effective first. NanoGPT is the cheapest at $0.75 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $0.5 | $1.5 | $0.75 | 16k |
| Vercel AI Gateway | $0.5 | $1.5 | $0.75 | 16k |
| Merge Gateway | $0.5 | $1.5 | $0.75 | 16k |
| AI/ML API (this) | $0.65 | $1.95 | $0.98 | 16k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at AI/ML API 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):