The board shows this model's cheapest measured offer ($0.750/1M); the smaller figure under it is the mean of the 6 offers listed below ($0.896/1M). Add those up and divide — it matches.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| azure | Pricebook (LiteLLM) | $0.500 | $1.50 | — | — | — | Official list |
| openai | Pricebook (LiteLLM) | $0.500 | $1.50 | — | — | — | Official list |
| vercel_ai_gateway | Pricebook (LiteLLM) | $0.500 | $1.50 | — | — | — | Official list |
| openrouter-best | OpenRouter | $0.500 | $1.50 | — | — | — | API-measured |
| burncloud | burncloud | $0.500 | $1.50 | — | — | — | API-measured |
| openrouter | Pricebook (LiteLLM) | $1.50 | $2.00 | — | — | — | Official list |
Price trend
Cheapest blended price, last 31 days (USD/1M): $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.375 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75 → $0.75
Data & method
Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/gpt-3.5-turbo.json. Free reuse requires attribution to tkx.org.
FAQ
How much does gpt-3.5-turbo cost?
Cheapest measured offer right now: $0.5/1M input, $1.5/1M output via azure — across 6 tracked providers, refreshed hourly.
Who serves gpt-3.5-turbo?
6 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
Is the price of gpt-3.5-turbo going up or down?
The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.