LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-3.5 Turbo Instruct

openai·openai/gpt-3.5-turbo-instruct·Deprecated·Closed·gpt series
Compact GPT model for low-latency assistance and high-volume workloads

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·PoeGateway
$1.40 / $1.80
Blended $1.50 · 1.1× spread
Context
4,096
Output limit
4,096
Knowledge cutoff
2021-08
Released / updated
2023-09-21 / 2023-09-21
Capabilities
ReasoningTool use? Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage

GPT-3.5 Turbo Instruct by openai is offered by 3 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Poe at $1.40 / $1.80 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

The context window is 4,096 tokens at the reference host, but hosts report different limits, from 3,500 to 4,096, so the usable window depends on the provider you pick. Accepted input modalities are Text and Image. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2021-08.

Available at 3 providers3 with public prices

  • ProviderInput / Output
  • PoeGateway
    $1.40 / $1.80
    Context 3,500 ⚠Output limit 1,024deprecated
  • Azure Cognitive ServicesCloud
    $1.50 / $2.00
    Context 4,096Output limit 4,096deprecated
  • AzureCloud
    $1.50 / $2.00
    Context 4,096Output limit 4,096deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
PoeGateway$1.40$1.80——3,500 ⚠1,024deprecated
Azure Cognitive ServicesCloud$1.50$2.00——4,0964,096deprecated
AzureCloud$1.50$2.00——4,0964,096deprecated

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1Poe$370.00
2Azure Cognitive Services$400.00
3Azure$400.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $1.50

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-05). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

GPT-6.2 Astra Prosame series—GPT-6.2 Sol Prosame series—GPT 6.1 Terra Prosame series—GPT-3.5-turbosame lab$0.50 / $1.50GPT-4same lab$30.00 / $60.00
Data partly from models.dev (MIT)