Skip to content
Model Change Index
  • OverviewNext shutdowns and latest changes
  • ShutdownsEvery date, one row per platform
  • ChangesReleases, deprecations, redirects and prices
  • LeaderboardEvery model, its scores and price
  • Check my stackYour models on one timeline
Track my stack

GPT-3.5 Turbo

DeprecatedOpenAIopenai/gpt-3-5-turbo2 platforms

Shutting down. The gpt-3.5-turbo-0125 version of GPT-3.5 Turbo shuts down on the OpenAI API on Oct 23, 2026. OpenAI names GPT-5.6 Terra as the replacement for that version.

9 days
Next shutdown
9 daysOct 23, 2026 · OpenAI API
Arena Text
1,226#122 of 128 · Arena
GPQA Diamond
28.0%#105 of 108 · Epoch AI
List price · $ per 1M
$0.50 in $1.50 outOpenAI API
Context window
16.4KMax output 4.1K tokens

Dates on every platform

2 listings · a floor is the earliest possible date
GPT-3.5 Turbo on each platform: model ID, status, dates, replacement and source
PlatformModel ID and statusDeprecatedShuts downReplacement
OpenAI APIOpenAI: Deprecations (opens in a new tab) · checked Oct 14, 2026gpt-3.5-turbo-0125Deprecated · also gpt-3.5-turbo, gpt-3.5-turbo-completionsGPT-5.6 Terra
OpenAI APIOpenAI: Deprecations (opens in a new tab) · checked Oct 14, 2026gpt-3.5-turbo-1106Shut downGPT-5.6 Terra

Fine-tuned versions of this model follow the same shutdown date.

What breaks when you move off GPT-3.5 Turbo

  • Parameters

    Pro snapshots move to gpt-5.6-sol with reasoning.mode set to pro. There is no separate Pro model ID for GPT-5.6.

    GPT-3.5 Turbo, GPT-4, GPT-4 Turbo, GPT-4.1 nano, GPT-4o, o1, o1-pro, o3-mini, o4-mini · OpenAI API ·

  • Defaults

    GPT-5.6 models reuse reasoning across turns by default (reasoning.context all_turns); earlier models default to current_turn.

    GPT-3.5 Turbo, GPT-4, GPT-4 Turbo, GPT-4.1 nano, GPT-4o, o1, o1-pro, o3-mini, o4-mini · OpenAI API ·

  • Pricing

    GPT-5.6 bills cache writes at 1.25 times the uncached input rate. Replace prompt_cache_retention with prompt_cache_options.ttl.

    GPT-3.5 Turbo, GPT-4, GPT-4 Turbo, GPT-4.1 nano, GPT-4o, o1, o1-pro, o3-mini, o4-mini · OpenAI API ·

  • Tooling

    babbage-002 and davinci-002 used the legacy Completions endpoint. GPT-5.6 Terra does not support v1/completions.

    GPT-3.5 Turbo Instruct, babbage-002, davinci-002, GPT-3.5 Turbo to GPT-5.6 Terra · OpenAI API ·

Intelligence

Third-party results, credited below
Third-party benchmark scores for GPT-3.5 Turbo
BenchmarkPublisherScoreRankPublished
Arena TextArena1,226 ± 2#122 of 128Oct 8, 2026
GPQA DiamondEpoch AI28.0% ± 1.9%#105 of 108Jan 27, 2025
FrontierMath Tiers 1-3Epoch AI0.0% ± 0.0%#71 of 71Aug 27, 2026
OTIS Mock AIME 2024-2025Epoch AI2.2% ± 2.2%#101 of 105Aug 7, 2026

Arena (arena.ai), https://arena.ai/leaderboard

Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource].

List prices

$ per 1M tokens, with each price’s source
List prices per 1M tokens, in US dollars
PlatformInputCachedOutputIn effectSource
OpenAI APIgpt-3.5-turbo-0125$0.50–$1.50Oct 14, 2026CurrentOpenAI: Pricing (opens in a new tab)

Change history

ShutdownLegacy GPT and o-series snapshots shut down on the OpenAI APIOpenAI API3 breaks

Requests to gpt-3.5-turbo-0125, gpt-4-0613, gpt-4-turbo, gpt-4.1-nano, gpt-4o-2024-05-13, o1, o1-pro, o3-mini and o4-mini, and their aliases, fail after the shutdown date. OpenAI names GPT-5.6 Sol, Terra or Luna as the substitute for each. Fine-tuned gpt-3.5-turbo, gpt-4, gpt-4.1-nano and o4-mini models shut down the same day.

Platform
OpenAI API
Announced
  • ParametersPro snapshots move to gpt-5.6-sol with reasoning.mode set to pro. There is no separate Pro model ID for GPT-5.6.
  • DefaultsGPT-5.6 models reuse reasoning across turns by default (reasoning.context all_turns); earlier models default to current_turn.
  • PricingGPT-5.6 bills cache writes at 1.25 times the uncached input rate. Replace prompt_cache_retention with prompt_cache_options.ttl.

Source: OpenAI, Deprecations (opens in a new tab); OpenAI, Using GPT-5.6 (opens in a new tab)

ShutdownGPT-3.5 Turbo Instruct, babbage-002, davinci-002 and gpt-3.5-turbo-1106 shut downOpenAI API1 break

OpenAI removed gpt-3.5-turbo-instruct, babbage-002, davinci-002 and the gpt-3.5-turbo-1106 snapshot. It recommends GPT-5.6 Terra.

Platform
OpenAI API
Replacement
GPT-5.6 Terra
Announced
  • Toolingbabbage-002 and davinci-002 used the legacy Completions endpoint. GPT-5.6 Terra does not support v1/completions.

Source: OpenAI, Deprecations (opens in a new tab); OpenAI, GPT-5.6 Terra model page (opens in a new tab)

Built by TeqEngine. Forward-deployed AI engineering, no model to sell. Moving an agent to a new model? Ask for a Next-Model Check.