Back to Models
GPT-4
OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning capabilities. Training data: up to Sep 2021.
5/28/2023
8,191 tokens
#132 Text (spanish)
Specifications
Modalities
Input
text
Output
text
Supported Parameters
frequency_penalty
logit_bias
logprobs
max_tokens
presence_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_logprobs
top_p
Max Output Tokens
4,096Data policy
- Prompt retention
- Unknown — we could not confirm
- Training
- Unknown — not declared
"Unknown" does not mean "safe". It means we could not confirm it.
Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.
Frequently asked questions
- Is GPT-4 available on FastMetal?
- Not at the moment. GPT-6.1 Sol, from the same lab, is available on the FastMetal API today.
- What is the context window of GPT-4?
- 8,191 tokens, shared between the prompt and the response.
- How does GPT-4 rank?
- #233 on the public arena's Japanese board (ELO 1,202). Ranks move as the leaderboard is updated.
Leaderboard
Text
spanishELO: 1,411
#132russianELO: 1,258
#306CodingELO: 1,314
#299MathELO: 1,273
#281Creative WritingELO: 1,255
#294Instruction FollowingELO: 1,277
#293Hard PromptsELO: 1,290
#298Multi-TurnELO: 1,262
#306OverallELO: 1,276
#309JapaneseELO: 1,202
#233ChineseELO: 1,260
#316KoreanELO: 1,176
#257EnglishELO: 1,293
#305frenchELO: 1,271
#258germanELO: 1,252
#255Vision
OverallELO: 1,089
#139Rankings: LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, snapshot 2026-10-22; category names mapped and ratings rounded by FastMetal.