OpenAI: GPT-4o
openai/gpt-4o
GPT-4o is OpenAI's budget option at $2.5/$10 per million input/output tokens, with a 128K-token context. It sits toward the back of the board on capability, at #184 of 260 on the TryAii Score — it holds up best on reasoning (#7 on LiveBench). It's reasonably quick at roughly 61-70 tokens/sec.
Prompt $/1M
$2.500
Completion $/1M
$10.000
Context
128,000 tok
Best provider
75 tok/s · OpenAI
Specs
- Model id
- openai/gpt-4o
- Display name
- OpenAI: GPT-4o
- Modality
- text+image+file->text
- Tokenizer
- GPT
- Instruct type
- —
- Context length
- 128,000
- Max completion
- 16,384
- Prompt $/1M
- $2.500
- Completion $/1M
- $10.000
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionno
- Moderatedyes
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| OpenAIfastest | 75 |
| Azure | 56 |
Prompt caching by provider
| Provider | Min tokens to cache |
|---|---|
| OpenAI | 1,024 tokens |