together-sandboxes
Together Sandboxes
Overview
Use Together Sandboxes when the user wants to execute Python remotely in a managed sandbox.
Typical fits:
- stateful Python sessions
- data analysis and chart generation
- agent-generated code execution
- file uploads into a remote runtime
When This Skill Wins
- The user wants remote execution rather than local shell execution
- Session state needs to persist across multiple calls
- The result may include display outputs such as charts
- A lightweight managed runtime is enough; no custom infra is required
Hand Off To Another Skill
- Use
together-gpu-clustersfor full infrastructure control or larger distributed jobs - Use
together-dedicated-containersfor custom containerized runtime logic - Use
together-chat-completionsif the user only wants generated code, not executed code
Quick Routing
- Remote execution with session reuse
- Response schema and session listing
- MCP-style access for agent workflows
Workflow
- Decide whether the task needs code execution or only code generation.
- Start a session with
client.code_interpreter.execute(). - Reuse
session_idwhen the workflow depends on prior state. - Inspect
stdout,stderr, structured outputs, and display outputs separately. - List sessions only when the user needs operational visibility or cleanup.
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". - Treat
session_idas part of the workflow state. - Inspect
response.errorsbefore assuming a run succeeded. plt.show()with the Agg backend does not reliably producedisplay_dataoutputs. To retrieve charts, save the figure to aBytesIObuffer withfig.savefig(), base64-encode it, and print the encoded string to stdout. Parse it from thestdoutoutput on the client side. See the chart example in scripts/execute_with_session.py.- Use this skill when the user benefits from remote stateful execution, not just because Python is involved.
- If the task outgrows the sandbox model, hand off to GPU clusters or dedicated containers.
Resource Map
- API reference: references/api-reference.md
- Alternative access patterns: references/api-reference.md
- Python workflow: scripts/execute_with_session.py
- TypeScript workflow: scripts/execute_with_session.ts
Official Docs
More from togethercomputer/skills
together-chat-completions
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.
40together-batch-inference
High-volume, asynchronous offline inference at up to 50% lower cost via Together AI's Batch API. Prepare JSONL inputs, upload files, create jobs, poll status, and download outputs. Reach for it whenever the user needs non-interactive bulk inference rather than real-time chat or evaluation jobs.
39together-images
Text-to-image generation and image editing via Together AI, including FLUX and Kontext models, LoRA-based styling, reference-image guidance, and local image downloads. Reach for it whenever the user wants to generate or edit images on Together AI rather than create videos or build text-only chat applications.
33together-fine-tuning
LoRA, full fine-tuning, DPO preference tuning, VLM training, function-calling tuning, reasoning tuning, and BYOM uploads on Together AI. Reach for it whenever the user wants to adapt a model on custom data rather than only run inference, evaluate outputs, or host an existing model.
32together-embeddings
Dense vector embeddings, semantic search, RAG pipelines, and reranking via Together AI. Generate embeddings with open-source models and rerank results behind dedicated endpoints. Reach for it whenever the user needs vector representations or retrieval quality improvements rather than direct text generation.
31together-evaluations
LLM-as-a-judge evaluation framework on Together AI. Classify, score, and compare model outputs, select judge models, use external-provider judges or targets, poll results and download reports. Reach for it whenever the user wants to benchmark outputs, grade responses, compare A/B variants, or operationalize automated evaluations.
31