Model card

Niah 1

niah-1

Best frontier / cost mix — default balanced SKU.

OpenAI Chat Completions Full tools max_turns 40

API

model
niah-1
endpoint
POST https://api.niah.si/v1/chat/completions
curl -s https://api.niah.si/v1/chat/completions \
-H "Authorization: Bearer $NIAH_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"niah-1","messages":[{"role":"user","content":"Hello"}]}'

Developer portal

Intended use

Default everyday intelligence — strong reasoning and tools at the best frontier / cost balance.

How it works

Niah's best frontier / cost mix: full tools and a balanced turn budget. We route across frontier and open-weight providers to maximize quality per dollar; exact backends change over time.

Positioning: Best frontier / cost mix

Capabilities

  • Streaming
  • OpenAI-compatible
  • Tools
  • Web search
  • Image generation
  • Multi-turn agents

Evaluations

Scores appear here when published. Until then, status stays planned.

  • Agentic / coding (SWE-bench style) planned

    Best fits full-tool SKUs with orchestration.

  • LMArena (Chatbot Arena) planned

    Submit niah-1 as a public API black box when the SKU is frozen for eval.

  • Artificial Analysis / academic suite planned

    Run the shipped SKU as a product black box (prompts + tools + orchestration) vs naked frontier models — we rank the product, not stripped base weights.

Pricing

Billed as Niah API / plan AI usage (not a separate provider invoice). See niah.si/pricing for plans and prepaid credits.

View pricing

Limits & safety

Not a base LLM. Responses inherit provider safety systems for the active frontier plus Niah org policy, rate limits, and usage controls. Do not treat as a downloadable weight release.

Trust Center · Security

Changelog

  • — Public SKU cards published (tier positioning; underlying frontiers may rotate).

Other SKUs