GPT-4o (08-06)
GPT-4o (08-06) 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
- 2024-08-06
- Context
- 128k
- Parameters
- 1.76T (8x222B MoE)*
- Architecture
- Mixture of Experts
- Knowledge cutoff
- 2023-10
- Specialization
- general
- License
- Proprietary
- Training
- finetuned
Cheapest of 3 routes · OpenAI API · cache read $1.25
This model is deprecated. OpenAI recommends switching to GPT-4o.
About
GPT-4o (08-06) is OpenAI's GPT-4o model with multimodal text and image input. It is deprecated (originally released 2024-08-06); use it only for reproducing earlier results or evaluating drift over time.
GPT-4o (08-06) is a proprietary model in the GPT-4o family. The structured metadata tracks a 128k-token context window, multimodal input, structured outputs, and code execution. This page tracks provider routes through OpenAI API, Salesforce Einstein Generative AI, and OpenRouter, with the cheapest tracked route listed at $2.5 input and $10 output per 1M tokens. Headline tracked benchmarks include Aider Polyglot 23.1 and MMLU PRO 74.7.
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 3Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Batch in / out | Cache | Route |
|---|---|---|---|---|---|
| OpenAI API | $2.50 | $10.00 | $1.25 / $5.00 | read $1.25 | Serverless |
| OpenRouter | $2.50 | $10.00 | - | - | Serverless |
| Salesforce Einstein Generative AI | - | - | - | - | ServerlessPartial |
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(2)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Aider Polyglot | 23.1 | 2026-04 | https://aider.chat/docs/leaderboards |
| MMLU PRO | 74.7 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
Migration checks
No linked migration route is available for this model yet.
API versions
gpt-4o-2024-08-06gpt-4o