Inkling 2 Small
by Ollama Cloud · family ling · listed Nov 2026RTVW
Multimodal MoE reasoning model (594B total, 17B active) for agentic coding, vision, and knowledge work
Current rates USD per 1M tokens
Input$0.30
Output$1.00
Cache read$0.03
Cache write—
Against the market
On the record
- Model id
inkling-2-small- Context window
- 1.0M tokens
- Max output
- 131K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-11-05
- Last updated
- 2026-11-12
- Provider docs
- docs.ollama.com/cloud
Back of the envelope
≈
Also listed at
- Kilo Gateway$0.15 in · $0.50 out
- Prime Inference$0.15 in · $0.50 out
- Tinfoil$0.30 in · $1.00 out
- Vercel AI Gateway$0.30 in · $1.00 out
- Eden AI$0.30 in · $1.00 out
- OpenRouter$0.30 in · $1.00 out
- Nebius Token Factory$0.30 in · $1.00 out
- Hugging Face$0.30 in · $1.00 out
- Deep Infra$0.30 in · $1.00 out
- NanoGPT$0.30 in · $1.00 out
- Cloudflare Workers AI$0.30 in · $1.00 out
- Cortecs$0.306 in · $1.02 out