aiticker

OpenAI · Released Sep 28, 2023

GPT-3.5 Turbo Instruct

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

Compare in showdown → OpenRouter ↗ All OpenAI models
Released
Sep 28 2023
Context window
4K 4K out
Input / 1M tokens
$1.50
Output / 1M tokens
$2.00

Where to run it

Providers

Only OpenAI serves GPT-3.5 Turbo Instruct on OpenRouter right now.

ProviderInputOutputContextMax outputUptimevs. best
OpenAIno tool calling $1.50 $2.00 4K4K0%24h Cheapest

Value

Price vs. performance

6 models score higher for the same price or lesson METR time horizon, e.g. GPT-5.1-Codex-Max.
1 min4 h8 h12 h $0.10$1.00$10.00$100.00 Gemini 3.1 Pro Preview (Google) — 6.4 h · $2.00/1M in Claude Opus 4.6 (Anthropic) — 12 h · $5.00/1M in Claude Opus 4.5 (Anthropic) — 4.9 h · $5.00/1M in Kimi K2 Thinking (Moonshot AI) — 54 min · $0.60/1M in Claude Sonnet 4.5 (Anthropic) — 2 h · $3.00/1M in Claude Opus 4.1 (Anthropic) — 1.9 h · $15.00/1M in R1 0528 (DeepSeek) — 31 min · $0.50/1M in GPT-5.4 (OpenAI) — 5.7 h · $2.50/1M in GPT-5.3-Codex (OpenAI) — 5.8 h · $1.75/1M in GPT-5.2 (OpenAI) — 5.9 h · $1.75/1M in GPT-5.1-Codex-Max (OpenAI) — 3.7 h · $1.25/1M in GPT-5 (OpenAI) — 3.4 h · $1.25/1M in gpt-oss-120b (OpenAI) — 42 min · $0.15/1M in o3 (OpenAI) — 2 h · $2.00/1M in o4 Mini (OpenAI) — 1.3 h · $1.10/1M in o1 (OpenAI) — 39 min · $15.00/1M in GPT-4o (2024-11-20) (OpenAI) — 9 min · $2.50/1M in GPT-4o (2024-08-06) (OpenAI) — 9 min · $2.50/1M in GPT-4o (OpenAI) — 9 min · $2.50/1M in GPT-4o (2024-05-13) (OpenAI) — 9 min · $5.00/1M in GPT-4 Turbo (OpenAI) — 7 min · $10.00/1M in GPT-4 (OpenAI) — 5 min · $30.00/1M in GPT-3.5 Turbo Instruct (OpenAI) — 1 min · $1.50/1M in GPT-3.5 Turbo Instruct

GPT-3.5 Turbo Instruct Other OpenAI Other labs Value frontier · METR time horizon vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.

Benchmarks

1 benchmark score

BenchmarkScoreRankLeader
METR time horizonSoftware engineering · Length of software task solved more often than not 1 min #23of 23 Claude Opus 4.612 h

Specs

Details

Model ID
openai/gpt-3.5-turbo-instruct
Developer
OpenAI
Release date
Sep 28, 2023 ·
Context window
4,095 tokens
Max output
3,685 tokens
API price
$1.50 / $2.00 per 1M input / output tokens
Providers
1
Input types
text
Reasoning
No
Tool calling
No
Open weights
No
Free tier
No

Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.