Benchmarks

OpenAI: GPT-3.5 Turbo 16k

openai/gpt-3.5-turbo-16k

GPT-3.5 Turbo 16k is OpenAI's budget option at $3/$4 per million input/output tokens, with a 16K-token context. It sits toward the back of the board on capability, at #207 of 235 on the TryAii Score. It's on the slow side at roughly 8-16 tokens/sec.

Prompt $/1M
$3.000
Completion $/1M
$4.000
Context
16,385 tok
Best provider
19 tok/s · OpenAI

Specs

Model id
openai/gpt-3.5-turbo-16k
Display name
OpenAI: GPT-3.5 Turbo 16k
Modality
text->text
Tokenizer
GPT
Instruct type
Context length
16,385
Max completion
4,096
Prompt $/1M
$3.000
Completion $/1M
$4.000
Free tier
no

Capabilities

  • Function callingno
  • JSON modeno
  • System promptno
  • Visionno
  • 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

Providertok/s
OpenAIfastest19
Azure5
openaifastest