together-chat-completions

name

together-chat-completions

description

Real-time and streaming text generation via Together AI's OpenAI-compatible chat/completions API, including multi-turn conversations, tool and function calling, structured JSON outputs, and reasoning models. Reach for it whenever the user wants to build or debug text generation on Together AI, unless they specifically need batch jobs, embeddings, fine-tuning, dedicated endpoints, dedicated containers, or GPU clusters.

Together Chat Completions

Overview

Use Together AI's serverless chat/completions API for interactive inference workloads:

• basic text generation
• streaming responses
• multi-turn chat state
• tool and function calling
• structured outputs
• reasoning-capable models

Treat this skill as the default entry point for Together AI text generation unless the task is clearly offline batch processing, vector retrieval, model training, or infrastructure management.

When This Skill Wins

• Build a chatbot, assistant, or text-generation endpoint on Together AI
• Add streaming output to a real-time user experience
• Implement tool calling or function-calling loops
• Constrain model output to JSON or a regex-defined shape
• Choose between standard chat models and reasoning models
• Debug request parameters, model behavior, or response shapes

Hand Off To Another Skill

• Use together-batch-inference for large offline runs, backfills, or lower-cost asynchronous jobs
• Use together-embeddings for vector search, semantic retrieval, or reranking
• Use together-fine-tuning when the user wants to train or adapt a model
• Use together-dedicated-model-inference when the user needs always-on single-tenant hosting
• Use together-dedicated-containers or together-gpu-clusters for custom infrastructure
• For production stock-model workloads that need a defined SLA (committed throughput and reliability) without managing hardware, point users to Together's provisioned throughput tier (reserved PTU capacity, one-month minimum term, contact sales; uses the same chat/completions API surface)

Quick Routing

• Basic chat, streaming, or multi-turn state
  • Start with references/api-parameters.md
  • Use scripts/chat_basic.py or scripts/chat_basic.ts
• OpenAI SDK migration, rate limits, or debug headers
  • Read references/api-parameters.md
  • Use scripts/debug_headers.py or scripts/debug_headers.ts
• Parallel async requests
  • Use scripts/async_parallel.py
• Tool calling or function calling
  • Read references/function-calling-patterns.md
  • Start from scripts/tool_call_loop.py or scripts/tool_call_loop.ts
• Designing tools, schemas, or tool_choice for reliability
  • Read the "Best Practices" section in references/function-calling-patterns.md
• Structured outputs
  • Read references/structured-outputs.md
  • Start from scripts/structured_outputs.py or scripts/structured_outputs.ts
• Reasoning models or thinking-mode toggles
  • Read references/reasoning-models.md
  • Start from scripts/reasoning_models.py or scripts/reasoning_models.ts
• Combining tools + structured output, or tools + streaming
  • Read the "Combining Tool Calls with Structured Output" section in references/function-calling-patterns.md
  • Read the "Streaming Structured Output" section in references/structured-outputs.md
• Model selection, context length, or pricing-aware choices
  • Read references/models.md

Workflow

1. Confirm that the workload is interactive serverless inference rather than batch, retrieval, or training.
2. Pick the smallest model that satisfies latency, quality, and context requirements.
3. Decide whether the job needs plain text, tools, structured output, or reasoning.
4. Start from the matching script instead of re-deriving request shapes from scratch.
5. Pull deeper details from the relevant reference file only when needed.

High-Signal Rules

• Python scripts require the Together v2 SDK (together>=2.0.0). If the user is on an older version, they must upgrade first: uv pip install --upgrade "together>=2.0.0".
• Use client.chat.completions.create() for Python and client.chat.completions.create() for TypeScript.
• Preserve full messages history for multi-turn conversations; do not rebuild context from final text only.
• For tools, implement the full loop: model tool call -> execute tool -> append tool result -> second model call.
• For tool definitions, prefer enum over free-form strings, set "additionalProperties": false, and add "strict": true on the function definition when you need argument generation to conform to the schema.
• Tool names must not contain spaces, periods, or dashes. Branch on finish_reason ("tool_calls" vs "stop") instead of assuming a tool was called, and parse function.arguments as JSON inside a try/except.
• Prefer json_schema over looser JSON modes when the user needs stable machine-readable output.
• Use reasoning models only when the task benefits from deeper deliberation; otherwise prefer cheaper standard models.
• Preserved thinking uses the reasoning key on both output and input (the field is symmetric). When you pass a prior assistant turn back to the API, include "reasoning": ... on the assistant message; reasoning_content is still accepted on input for backward compatibility but prefer reasoning in new code.
• Reasoning models nest extra token counts OpenAI-style (usage.completion_tokens_details.reasoning_tokens, usage.prompt_tokens_details.cached_tokens), but some non-reasoning models return cached_tokens flat at the top of usage. Read both locations defensively — clients that only check one shape will silently return 0. See references/reasoning-models.md for the defensive-read pattern.
• To combine tool calling with structured output, use a two-phase approach: Phase 1 sends tools (no response_format), Phase 2 sends response_format (no tools) after tool results are appended.
• Streaming works with ; accumulate chunks and parse the final concatenated string as JSON.

Resource Map

• Parameters and response fields: references/api-parameters.md
• OpenAI compatibility, rate-limit headers, and debug headers: references/api-parameters.md
• Function-calling patterns: references/function-calling-patterns.md
• Structured outputs: references/structured-outputs.md
• Reasoning models: references/reasoning-models.md
• Model catalog: references/models.md

Scripts

• scripts/chat_basic.py and scripts/chat_basic.ts: basic chat, streaming, and multi-turn state
• scripts/debug_headers.py and scripts/debug_headers.ts: raw-response inspection for routing, latency, and rate-limit headers
• scripts/async_parallel.py: async Python fan-out for independent requests
• scripts/tool_call_loop.py and scripts/tool_call_loop.ts: full tool-call loop
• scripts/structured_outputs.py and scripts/structured_outputs.ts: schema-guided and regex outputs
• scripts/reasoning_models.py and scripts/reasoning_models.ts: reasoning fields, effort, and hybrid toggles

Official Docs

• Chat Overview
• Inference Parameters
• Serverless Models
• Function Calling
• JSON Mode
• Reasoning Overview
• Chat Completions API