Skip to main content

Mistral 7B Instruct

Balanced, general-purpose LLM with an excellent quality-to-size ratio.

Overview​

  • model_name: mistral-7b-instruct (curated base)
  • Source: mistralai/Mistral-7B-Instruct-v0.3
  • Scale: ~7B parameters
  • Served on: GPU via vLLM (transformers fallback)
  • Public endpoint: mistral-7b-instruct-public (task type chat, billed per request in USD)

When to use​

✅ General-purpose chat, customer-support agents, summarization, Q&A, content generation — a solid default for most production text workloads.

❌ For code, prefer Qwen 2.5 Coder; for heavier multilingual work, Qwen 2.5 7B; for higher quality, step up to gpt-oss-20b or mistral-small-24b (see All LLMs).

Live specs​

Context window, VRAM footprint, price, and readiness come from the live catalog — this page does not hardcode them:

curl "https://api.colabhive.com/api/builder/v1/endpoints?visibility=public&search=mistral-7b"

Quick start​

from colabhive import ColabHive

client = ColabHive(api_key="hive_...", account_id="YOUR_ACCOUNT_ID")

result = client.endpoints.infer(
    endpoint_id="mistral-7b-instruct-public",   # SDK resolves the name to a UUID
    input_data={"messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "How can I integrate your API?"},
    ]},
    max_tokens=500,
    temperature=0.7,
)

# Sync by default; a "queued" status means poll GET /tasks/{task_id}
print(result["result"] if result.get("status") != "queued"
      else client.endpoints.get_task(result["task_id"]))

The same model is also reachable through the OpenAI-compatible /v1/chat/completions surface, addressed by model name or endpoint UUID.

Tips​

  • Define role and tone in a clear system prompt.
  • Temperature around 0.7 balances consistency and variety; drop to 0.3–0.5 for factual answers.
  • OpenAI-compatible streaming is incremental on current node runtimes and falls back to one complete SSE chunk on older nodes — see All LLMs.

Next steps​

Authors: José Luis Minich, Maximiliano Lucius.