OpenAI: GPT-4

openai/gpt-4

GPT-4 is OpenAI's budget option at $30/$60 per million input/output tokens, with a 8K-token context. It sits toward the back of the board on capability, at #203 of 260 on the TryAii Score — its best showing is #1 on GSM8K. It's reasonably quick at roughly 60-84 tokens/sec.

Prompt $/1M

$30.000

Completion $/1M

$60.000

Context

8,191 tok

Best provider

95 tok/s · Azure

Specs

Model id: openai/gpt-4
Display name: OpenAI: GPT-4
Modality: text->text
Tokenizer: GPT
Instruct type: —
Context length: 8,191
Max completion: 4,096
Prompt $/1M: $30.000
Completion $/1M: $60.000
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionyes
Moderatedno

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	TTFT	Total latency
Azurefastest	95	870 ms	954 ms
OpenAI	49	951 ms	1,015 ms