GPT-4.5

Released
2025-02-27
Last refreshed
2026-05-20
Status
Researched 133d ago
DeprecatedProprietaryCommercial use: conditionalMultimodalCodingAgentsVisionClassificationJSON / Tool use

GPT-4.5 is a legacy integration reference; evaluate GPT-4.1 before starting new work.

OpenAI releases · 51 in the last 12 monthsChangelog →
Specifications
Family
GPT-4.5
Released
2025-02-27
Context
8k
Knowledge cutoff
2025-04
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Created by
OpenAI

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website
Pricing
Output / 1M
-
Input / 1M
-

Cheapest of 2 routes · Azure OpenAI

Providers(2)
OpenAI APIAzure OpenAI
View 2 provider routes

This model is deprecated. OpenAI recommends switching to GPT-4.1.

About

Improved GPT-4 variant released March 2026. Enhanced performance over GPT-4o with better reasoning and code generation.

Provider price ladder

Compare all 2

Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Azure OpenAI--
ServerlessPartial
OpenAI API--
ServerlessPartial

Available via routers & gateways(16)

LiteLLM

Gateway

Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.

Free OSSOpenAI APIAzure OpenAI

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughOpenAI API

Portkey

Gateway

Production AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.

SubscriptionOpenAI APIAzure OpenAI

AIRouter

Router

Commercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.

Passthrough + feeOpenAI API

Azure AI Foundry Model Router

Router

Microsoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.

PassthroughAzure OpenAI

Helicone

Gateway

Observability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.

SubscriptionOpenAI APIAzure OpenAI

Capabilities

VisionMultimodalJSON / Tool useStructured OutputsCode ExecutionFine-tuning

Benchmark peer barsfor Classification

MMLU PRORank 25 of 105
Gemini 3 Pro
91.8
Gemini 3.1 Pro Preview
91.0
Qwen3.7-Max
89.6
Claude Opus 4.6
89.1
GPT-4.5current
86.1

Benchmark scores(2)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
MMLU PRO86.1—Observed 2026-04-14—Source
Google-Proof Q&A71.4—Observed 2025-02-27—Source

Migration checks

No linked migration route is available for this model yet.