模型詳情
gpt-4-0613
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.
模型規格
- 上下文長度
- 8.192K
- 最大輸出
- 8.192K
- 輸入/輸出模態
- 文字
- 發布日期
- 2023-05
02
API 端點
單一 MixRoute 閘道，OpenAI 相容
-
OpenAI-compatible
/v1/chat/completionsPOST
03
價格
固定費率，單位：/1M Tokens
輸入
$30.0000 /1M Tokens
補全
$60.0000 /1M Tokens
05
選型摘要
快速判斷是否適合你的工作負載
What is this model good for?
Snapshot of GPT-4 for stable deployments
Use gpt-4-0613 as a pinned snapshot of GPT-4 for applications requiring a stable, unchanging model version. It is a large-scale multimodal model capable of solving difficult problems.
What should you check before using it?
Consider newer GPT-4 snapshots or models
This is a June 2023 snapshot. Newer models offer improved performance. Verify this version provides the stability you need.
Why use it through MixRoute?
Use the OpenAI-compatible endpoint with stable model ID
Use the confirmed compatible endpoint with model ID gpt-4-0613 through MixRoute.
08
Token 成本估算
基於本頁價格的即時估算，非實際帳單
此模型沒有快取讀取價格，不計算快取費用
單一端點，可驗證的決策
使用相同的請求格式測試此模型與替代路由
從真實工作負載開始，再由品質、總成本與故障條件決定是否導入正式環境流量。