Ornith 1.5 9B

ornith-ai/ornith-1.5-9b

Currently unavailable for maintenance.

A dense 9B model with a 262,144-token context, the lightweight member of the Ornith 1.5 family. Built for coding and agentic work at a size that runs on a single GPU.

Get an API key

Endpoints

Launch offer· ends 30 September 2026

Each row is one provider serving these weights at one precision. Prices are per million tokens.

Quantisation	Context	Max out	Input	Output	Cached in
BF16	256K	128K	~~$0.06~~$0.03	~~$0.24~~$0.12	~~$0.015~~$0.0075

Agent config

Paste this into your coding agent and it can configure itself. The timeout is derived from this variant's measured throughput, not a guess — a long generation that outlives a client's default ceiling is the most common way a working request looks broken.

# Infersia — ornith-ai/ornith-1.5-9b
# Paste this to your agent. Values are measured, not aspirational.

provider:
  type: openai-compatible
  base_url: https://api.infersia.com/v1
  api_key: ${INFERSIA_API_KEY}   # from https://infersia.com/dashboard/keys
  model: ornith-ai/ornith-1.5-9b

limits:
  max_input_tokens: 262144      # hard limit — over this returns HTTP 413
  max_output_tokens: 131072
  timeout_seconds: 600                  # no throughput measured yet; 600 is a safe default

features:
  streaming: true
  tools: false
  vision: false
  reasoning: false
  prompt_caching: false

pricing_usd_per_million_tokens:
  input: 0.03
  output: 0.12
  cached_input: 0.0075

What BF16 means

Full bfloat16 precision — no quantisation loss.

Call it

curlbash

curl https://api.infersia.com/v1/chat/completions \
  -H "Authorization: Bearer $INFERSIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ornith-ai/ornith-1.5-9b",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

Pin a provider with ornith-ai/ornith-1.5-9b@infersia, or take the cheapest with the bare id. Add :free for the rate-limited free tier where one exists.