GPT-4
openai/gpt-4- OpenAI
- Family · GPT-4
- Released 14 Mar 2023
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context8K
Max output4K
Input / 1M$30.00
Output / 1M$60.002× input
Scores · standing
Intelligence6.7#364/489
Coding13.1#165/196
Usage
Tokens / day2.0M▼ 52% 7d
Usage rank#438
Requests / day1.4K
Tool calls / req0.04
Per request · 30 days
Avg input7980.1× median
Avg output1530.2× median
Cache hit26%0.4× median
Tool-call failures0.7%0.4× median
Consumption
Peak 38.2M 1 OctLow 1.1M 31 OctRank today #438
News & trends
35 mentions this week ▲ 400%this model · videos, posts, articles · 30 days
Trending · 14 days
- GPT-4は平均的な人より独創的。でも答えの70%が同じ単語 #shorts876 views
- OpenAI Switches Off GPT-4 This Friday (Check Your Code) 🔌 #ai #openai899 views
- Week of Oct 12–16, 2026: open-weight releases from Meta/Nvidia, GPT-4 API shutdown date, enterprise cost caps, and regulatory probes2 upvotes
News · latest from OpenAI
- GPT-6.1 Terra vs. Claude Opus 5.5: Cheaper and faster in three tests at maxthenewstack.io · 2 Nov
- Chinese labs now target OpenAI's GPT-6 Astra for distillationfork.zone · 1 Nov
- GPT-6.1 Terrasimonwillison.net · 31 Oct
- GPT-5.6 Sol can beat Factorio on peaceful moderyanmadden.net · 31 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across providers, latest day
Output speed#93/33393 tok/s1.4× faster than median
First token#840.61 s1.7× quicker than median
#37 cheapest of 37 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Family progress
Intelligence Index
- Family releases12.7
Technical details
- Tokenizer
- GPT
- Knowledge cutoff
- 2021-09-30
- Moderation
- none
Request parameters 13
- tools
- tool_choice
- response_format
- temperature
- top_p
- max_completion_tokens
- stop
- seed
- frequency_penalty
- logit_bias
+3 more
- logprobs
- presence_penalty
- top_logprobs
When to use
Best for
- Legacy integrations pinned to this model
- Short tool-calling prompts
- Short-form writing and rewriting
Think twice for
- Long documents because context is small
- Image input
- Cost-sensitive high-volume work
- Hard reasoning and coding tasks
Research papers
- When LLM Architectures Meet Smart Contract Vulnerability Detection: a Replication Study28 Oct
- MedJev: Evaluating Zero-Shot System-One Decision Making in Medicine26 Oct
- Beyond pass or fail: an information-processing account of the Turing Test23 Oct
- AI Representations of Mental Health Stigma: Quantifying the Gap Between AI Estimations and Human Perceptions Across Gender Groups Using GPT-Based LLMs12 Oct
- Scoring Explanations Without Reading Them: Structural Shortcuts in Automated-Interpretability Evaluation Data10 Oct
- Successive Training Stages and Large Language Model Persuasion: Effects of Misalignment, Supervised Fine-Tuning, and Preference Optimization7 Oct
- An Executable Benchmark for LLM-Based HLS Repair:Design Complexity and Repair Underconstraint2 Oct
- Autonomous OSS Threat Detection via Taxonomy-Aligned LLMs1 Oct
Same family
GPT-4- 12.7
- 9.6
Alternatives
other vendors · similar capability- 8.4
- 10.8
- 6.9
- 5.2
Want GPT-4 on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.











