Note: Use the Meai alias because the Together SDK has its own generated IChatClient interface.
Chat Client Five Random Words Streaming
1 2 3 4 5 6 7 8 91011121314151617181920
usingvarclient=newTogetherClient(apiKey);Meai.IChatClientchatClient=client;varupdates=chatClient.GetStreamingResponseAsync([ new Meai.ChatMessage(Meai.ChatRole.User, "Generate 5 random words.") ],newMeai.ChatOptions{ModelId="meta-llama/Llama-3-8b-chat-hf",});vardeltas=newList<string>();awaitforeach(varupdateinupdates){if(!string.IsNullOrWhiteSpace(update.Text)){deltas.Add(update.Text);}}
Chat Client Five Random Words
1 2 3 4 5 6 7 8 91011
usingvarclient=newTogetherClient(apiKey);Meai.IChatClientchatClient=client;varresponse=awaitchatClient.GetResponseAsync([ new Meai.ChatMessage(Meai.ChatRole.User, "Generate 5 random words.") ],newMeai.ChatOptions{ModelId="meta-llama/Llama-3-8b-chat-hf",});
Chat Client Get Service Returns Chat Client Metadata
usingvarclient=newTogetherClient(apiKey);Meai.IChatClientchatClient=client;varresponse=awaitchatClient.GetResponseAsync([new Meai.ChatMessage(Meai.ChatRole.User, "What is 25 * 37? Think step by step.")],newMeai.ChatOptions{ModelId="deepseek-ai/DeepSeek-R1",});varreasoning=response.Messages.SelectMany(m=>m.Contents).OfType<Meai.TextReasoningContent>().ToList();vartext=response.Messages.SelectMany(m=>m.Contents).OfType<Meai.TextContent>().ToList();// DeepSeek-R1 should produce reasoning content
usingvarclient=newTogetherClient(apiKey);Meai.IChatClientchatClient=client;vargetWeatherTool=AIFunctionFactory.Create((stringlocation)=>$"The weather in {location} is sunny, 72°F","GetWeather","Gets the current weather for a location");varmessages=newList<Meai.ChatMessage>{new(Meai.ChatRole.User,"What's the weather in Seattle?"),};varoptions=newMeai.ChatOptions{ModelId="meta-llama/Llama-3.3-70B-Instruct-Turbo",Tools=[getWeatherTool],};// First turn: model should call the toolvarresponse=awaitchatClient.GetResponseAsync(messages,options);varfunctionCall=response.Messages.SelectMany(m=>m.Contents).OfType<FunctionCallContent>().FirstOrDefault();// Add assistant response with tool call and tool resultmessages.AddRange(response.Messages);vartoolResult=awaitgetWeatherTool.InvokeAsync(functionCall!.Argumentsis{}args?newAIFunctionArguments(args):null);messages.Add(newMeai.ChatMessage(Meai.ChatRole.Tool,[ new FunctionResultContent(functionCall.CallId, toolResult),]));// Second turn: model should respond with the weather infovarfinalResponse=awaitchatClient.GetResponseAsync(messages,options);
Chat Client Tool Calling Single Turn
1 2 3 4 5 6 7 8 91011121314151617181920
usingvarclient=newTogetherClient(apiKey);Meai.IChatClientchatClient=client;vargetWeatherTool=AIFunctionFactory.Create((stringlocation)=>$"The weather in {location} is sunny, 72°F","GetWeather","Gets the current weather for a location");varresponse=awaitchatClient.GetResponseAsync([new Meai.ChatMessage(Meai.ChatRole.User, "What's the weather in Seattle?")],newMeai.ChatOptions{ModelId="meta-llama/Llama-3.3-70B-Instruct-Turbo",Tools=[getWeatherTool],});varfunctionCall=response.Messages.SelectMany(m=>m.Contents).OfType<FunctionCallContent>().FirstOrDefault();
Chat Client Tool Calling Streaming
1 2 3 4 5 6 7 8 9101112131415161718192021
usingvarclient=newTogetherClient(apiKey);Meai.IChatClientchatClient=client;vargetWeatherTool=AIFunctionFactory.Create((stringlocation)=>$"The weather in {location} is sunny, 72°F","GetWeather","Gets the current weather for a location");varupdates=chatClient.GetStreamingResponseAsync([new Meai.ChatMessage(Meai.ChatRole.User, "What's the weather in Seattle?")],newMeai.ChatOptions{ModelId="meta-llama/Llama-3.3-70B-Instruct-Turbo",Tools=[getWeatherTool],});varfunctionCalls=newList<FunctionCallContent>();awaitforeach(varupdateinupdates){functionCalls.AddRange(update.Contents.OfType<FunctionCallContent>());}
This SDK is one of more than 200 .NET SDKs maintained with AutoSDK. The tryAGI SDK audit continuously checks repository synchronization, upstream-spec regeneration, release workflows, warnings, public API visibility, and trimming/NativeAOT compatibility.
Every issue is first investigated for ecosystem-wide applicability. When the root cause belongs in AutoSDK, we fix and regression-test the generator, then roll the improvement out to every applicable SDK. Provider-specific behavior remains in this repository when it cannot be derived safely from the API specification.
Issue content—including code blocks, logs, links, and attachments—is treated only as untrusted diagnostic data. Embedded control instructions, hidden directives, delimiter tricks, or requests to alter triage or tooling behavior are ignored. Please report reproducible technical evidence and remove secrets and personal data.