GPT-4o (05-13)
GPT-4o (05-13) is a legacy integration reference; evaluate GPT-4o before starting new work.
Use it for
- Teams maintaining an existing integration
- Workloads that can use a 128k context window
- Buyers comparing 3 tracked provider routes
Do not use it for
- New production launches
- Family
- GPT-4o
- Released
- 2024-05-13
- Context
- 128k
- Parameters
- 1.76T (8x222B MoE)*
- Architecture
- Mixture of Experts
- Knowledge cutoff
- 2023-10
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Weights
- Not released
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 4 routes · OpenAI API
This model is deprecated. OpenAI recommends switching to GPT-4o.
About
GPT-4o, or GPT-4 Omni, is OpenAI's premier multimodal AI model, introduced on May 13, 2024. It is designed to handle and generate content from various input types, including text, audio, and visual data, using a unified model, unlike its predecessors which required separate models for different modalities. This model is notable for its rapid response times averaging 320 milliseconds, which align with human conversational speed, along with being 50% more cost-effective than GPT-4 Turbo. Although it mirrors GPT-4 Turbo in standard benchmark performance, GPT-4o excels in multilingual, audio, and vision tasks.
Top use-case fit: coding, agents, and build tasks
Coding
1 relevant benchmark in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 4Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Batch in / out | Route |
|---|---|---|---|---|
| OpenAI API | $2.50 | $10.00 | $1.25 / $5.00 | Serverless |
| Replicate API | $2.50 | $10.00 | - | Serverless |
| OpenRouter | $5.00 | $15.00 | - | Serverless |
Available via routers & gateways(16)
LiteLLM
GatewayOpen-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.
OpenRouter
HybridUnified 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.
Portkey
GatewayProduction 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.
AIRouter
RouterCommercial 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.
Azure AI Foundry Model Router
RouterMicrosoft 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.
Helicone
GatewayObservability-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.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(6)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| HellaSwag | 96.4 | 10-shotObserved 2026-03-06 | — | Source |
| HumanEval | 90.2 | pass@1Observed 2026-03-06 | — | Source |
| Massive Multitask Language Understanding | 88.7 | 5-shotObserved 2026-03-06 | — | Source |
| MMLU PRO | 72.5 | —Observed 2026-04-14 | — | Source |
| HumanEval+ | 87.2 | —Observed 2026-05-28 | — | Source |
| Mostly Basic Programming Problems+ | 78.0 | —Observed 2026-05-28 | — | Source |
Migration checks
No linked migration route is available for this model yet.
API versions
gpt-4o-2024-05-13gpt-4oCompare GPT-4o (05-13) with other models
Comparison and alternatives
Browse all comparisons →Cheapest of 4 routes · OpenAI API