Inference.net: Schematron V2 Small API Pricing
Inference.net: Schematron V2 Small costs $0.050 per 1M input tokens and $0.230 per 1M output tokens (cache reads: $0.050). Context window: 128K. Prices verified 2026-10-21 · source
Alternatives to consider
Cheapest inference-net model — 37% less per month
Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.
From our own daily snapshot archive — independent of provider announcements.
Token economics
| Token type | Price | vs base input |
|---|---|---|
| Standard input | $0.050 | — |
| Cache read | $0.050 | −0% |
| Output | $0.230 | — |
Prompt caching stores repeated context server-side: reads cost far less, but writes carry a one-time premium.
What would Inference.net: Schematron V2 Small cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $1.32 |
| Coding agent | 5,000 | 8,000 / 2,000 | $4.30 |
| RAG pipeline | 30,000 | 4,000 / 500 | $9.45 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $2.46 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About Inference.net: Schematron V2 Small
Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...
Compare Inference.net: Schematron V2 Small with
- V2 Small vs OpenAI: GPT-5.6 Terra Pro
- V2 Small vs Anthropic: Claude Fable 5
- V2 Small vs Anthropic: Claude Opus 5
- V2 Small vs OpenAI: GPT-5.6 Sol
Popular head-to-heads — see all on the comparisons index.
Frequently asked questions
How much does Inference.net: Schematron V2 Small cost?
Inference.net: Schematron V2 Small costs $0.050 per 1M input tokens and $0.230 per 1M output tokens; cached input tokens cost $0.050 per 1M. Verified 2026-10-21 — provider source.
What is the context window?
128K tokens, with up to 4K output tokens per response. That's roughly 160 pages of text in a single request.
Does it support prompt caching?
Yes — cached input is $0.050/1M, about 0% cheaper than standard input. Agents and RAG workloads with repeated context benefit most.
What's a cheaper alternative?
Mistral: Mistral Nemo saves about 71% on a typical workload with comparable quality.
Official resources
- Inference.net: Schematron V2 Small on OpenRouter — live endpoint, pricing source of record.
- Artificial Analysis leaderboard → — independent intelligence and performance rankings.
- Shred your current bill — paste a CSV and see if switching saves money.