CaIon c833e07ee3 feat: add support for gpt-5 models and adjust temperature settings ...

- Updated the model list to include various gpt-5 variants.
- Enhanced the ConvertOpenAIRequest function to handle gpt-5 model temperature settings based on specific model prefixes.
- Adjusted default cache and model ratios for new gpt-5 models.

2025-08-08 10:43:07 +08:00

..

ai360

fix: 360智能接口地址更新

2024-12-02 15:59:08 +00:00

ali

feat: support qwen claude format

2025-08-07 18:32:31 +08:00

aws

Merge pull request #1508 from wzxjohn/feature/aws_new_apikey_support

2025-08-06 12:04:28 +08:00

baidu

feat: update MaxTokens handling

2025-08-07 16:15:59 +08:00

baidu_v2

feat: enhance Adaptor to support multiple relay modes in request handling

2025-08-07 19:30:42 +08:00

claude

feat: support qwen claude format

2025-08-07 18:32:31 +08:00

cloudflare

feat: update MaxTokens handling

2025-08-07 16:15:59 +08:00

cohere

feat: update MaxTokens handling

2025-08-07 16:15:59 +08:00

coze

feat: convert gemini format to openai chat completions

2025-08-01 22:23:35 +08:00

deepseek

feat: support deepseek claude format (convert)

2025-08-07 19:01:49 +08:00

dify

feat: convert gemini format to openai chat completions

2025-08-01 22:23:35 +08:00

gemini

Merge pull request #1518 from RedwindA/fix/disable-gemini-sse

2025-08-07 20:44:24 +08:00

jimeng

feat: convert gemini format to openai chat completions

2025-08-01 22:23:35 +08:00

jina

feat: convert gemini format to openai chat completions

2025-08-01 22:23:35 +08:00

lingyiwanwu

Update Perplexity and 01 models

2024-05-17 19:37:18 +08:00

minimax

feat: support minimax

2024-05-16 19:03:42 +08:00

mistral

feat: update MaxTokens handling

2025-08-07 16:15:59 +08:00

mokaai

feat: convert gemini format to openai chat completions

2025-08-01 22:23:35 +08:00

moonshot

feat: support minimax

2024-05-16 19:03:42 +08:00

ollama

feat: update MaxTokens handling

2025-08-07 16:15:59 +08:00

openai

feat: add support for gpt-5 models and adjust temperature settings

2025-08-08 10:43:07 +08:00

openrouter

feat: support claude cache and thinking for upstream [OpenRouter] (#983)

2025-06-05 17:35:48 +08:00

palm

feat: update MaxTokens handling

2025-08-07 16:15:59 +08:00

perplexity

feat: update MaxTokens handling

2025-08-07 16:15:59 +08:00

siliconflow

feat: convert gemini format to openai chat completions

2025-08-01 22:23:35 +08:00

task

feat: add vidu video channel

2025-07-24 10:14:25 +08:00

tencent

feat: convert gemini format to openai chat completions

2025-08-01 22:23:35 +08:00

vertex

feat: support qwen claude format

2025-08-07 18:32:31 +08:00

volcengine

feat: enhance Adaptor to support multiple relay modes in request handling

2025-08-07 19:30:42 +08:00

xai

feat: convert gemini format to openai chat completions

2025-08-01 22:23:35 +08:00

xinference

🔧 fix(xinference): update Document type to 'any' for flexibility

2025-06-25 18:04:34 +08:00

xunfei

feat: update MaxTokens handling

2025-08-07 16:15:59 +08:00

zhipu

feat: convert gemini format to openai chat completions

2025-08-01 22:23:35 +08:00

zhipu_4v

feat: update MaxTokens handling

2025-08-07 16:15:59 +08:00

adapter.go

feat: convert gemini format to openai chat completions

2025-08-01 22:23:35 +08:00

api_request.go

增加 DisablePing 字段以控制是否发送自定义 Ping

2025-07-18 23:38:35 +08:00