Skip to content
OSMEXO

GPT-4 Turbo

openai/gpt-4-turbo
  • OpenAI
  • Family · GPT-4 Turbo
  • Released 6 Nov 2023
  • Text · Image → Text
  • Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context125K
Max output4K
Input / 1M$10.00
Output / 1M$30.003× input
Scores · standing
Intelligence7.0#354/490
Coding21.5#137/196
Usage
Requests / day2.4K
Tool calls / req0.01
Per request · 30 days
Avg input1.0K0.1× median
Avg output460.1× median
Tool-call failures1.6%0.9× median

Consumption

13.3M26.7M40.0M26 Sep9 Oct23 Oct
Peak 30.0M 14 OctLow 1.7M 27 Sep

News & trends

News · latest from OpenAI

Benchmarks

bar = share of the top score · Benchmark data: Artificial Analysis
MMLU-Pro#169 of 273
69.4%
MATH-500#103 of 167
73.7%
LiveCodeBench#170 of 269
29.1%
Coding index#137 of 196
21.5
AIME#87 of 160
15.0%
Intelligence index#354 of 490
7.0
Humanity's Last Exam#452 of 465
3.1%

#38 cheapest of 39 with a similar score

Value
Intelligence Index
66.577.58$10$20GPT-4 Turbo
Blended price per 1M tokens (log)

Technical details

Tokenizer
GPT
Knowledge cutoff
2023-12-31
Moderation
moderated
Request parameters 14
  • tools
  • tool_choice
  • response_format
  • structured_outputs
  • temperature
  • top_p
  • max_tokens
  • stop
  • seed
  • frequency_penalty
+4 more
  • logit_bias
  • logprobs
  • presence_penalty
  • top_logprobs

When to use

Best for

  • Legacy apps already tuned to this model
  • Image understanding in chat
  • Tool-calling assistants with moderate context
  • Structured JSON extraction

Think twice for

  • Long outputs because the cap is small
  • Hard reasoning and coding tasks
  • High-volume cheap chat
  • New projects when newer models exist

Research papers

Same family

GPT-4 Turbo

Alternatives

other vendors · similar capability

Want GPT-4 Turbo on OSMEXO?

Sign in to request it. Requests are reviewed; a request does not guarantee availability.