Documentation
¶
Overview ¶
Package together wraps Together AI's OpenAI-compatible API. Together hosts hundreds of open-weight models (Llama, DeepSeek, Qwen, Mistral, etc.) with serverless and dedicated endpoints.
Together-specific knobs reachable through the namespaced OpenAI request extension:
- "echo" / "min_p" / "repetition_penalty" / "top_k" are accepted on top of the standard openai surface.
- The "safety_model" field enables Llama Guard prefilter / postfilter by naming a guard model.
See https://docs.together.ai/ for the full reference.
Index ¶
Constants ¶
View Source
const ( OpenAIRequestExtensionKey = "together/openai_request" OpenAIResponseExtensionKey = "together/openai_response" OpenAIStreamChunkExtensionKey = "together/openai_stream_chunk" )
View Source
const ( Provider = "Together" BaseURL = "https://api.together.xyz/v1" )
View Source
const ( ModelMiniMaxM27 = "MiniMaxAI/MiniMax-M2.7" ModelQwen37Max = "Qwen/Qwen3.7-Max" ModelQwen36Plus = "Qwen/Qwen3.6-Plus" ModelKimiK26 = "moonshotai/Kimi-K2.6" ModelGLM51 = "zai-org/GLM-5.1" ModelGPTOSS120B = "openai/gpt-oss-120b" ModelGPTOSS20B = "openai/gpt-oss-20b" ModelDeepSeekV4Pro = "deepseek-ai/DeepSeek-V4-Pro" ModelRnj1Instruct = "essentialai/rnj-1-instruct" ModelLlama33Instruct = "meta-llama/Llama-3.3-70B-Instruct-Turbo" ModelQwen3Instruct2507 = "Qwen/Qwen3-235B-A22B-Instruct-2507-tput" ModelQwen35_397BA17B = "Qwen/Qwen3.5-397B-A17B" )
A representative slice of Together's current serverless catalog. See https://docs.together.ai/docs/serverless-models for the full list.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Chat ¶ added in v0.13.0
type Chat = openai.ChatCompletions
Chat implements Together's chat endpoint.
func NewChat ¶ added in v0.13.0
func NewChat(config ChatConfig) (*Chat, error)
Click to show internal directories.
Click to hide internal directories.