Amazon lists 5 models and Inference.net 2. Inference.net is cheaper on a typical model ($0.08 per 1M tokens median). Below: line-up, price tiers, the cheapest model for each capability, and what each costs for five real workloads.
| Amazon | Inference.net | |
|---|---|---|
| Models listed | 5 | 2 |
| Models with published pricing | 5 | 2 |
| Typical price (median, 3:1 blend per 1M) | $0.85 | $0.08 |
| Cheapest paid model | Amazon: Nova Micro 1.0 ($0.06) | Inference.net: Schematron V2 Turbo ($0.06) |
| Longest context | Amazon: Nova 2 Lite (1M) | Inference.net: Schematron V2 Small (128K) |
| Free models | 0 | 0 |
| Newest model | Amazon: Nova 2 Lite (2025-12-02) | Inference.net: Schematron V2 Small (2026-09-12) |
| Price changes in the last 90 days | 0 | 0 |
For each workload: the cheapest model from each provider that can actually do it (fits the context window; tool calling required for the agent), and its monthly cost at list price.
| Workload (per month) | Amazon | Inference.net |
|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation | $5.43 with Amazon: Nova Micro 1.0 | $5.25 with Inference.net: Schematron V2 Turbo |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages | $5.60 with Amazon: Nova Micro 1.0 | $5.10 with Inference.net: Schematron V2 Turbo |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context | $5.88 with Amazon: Nova Micro 1.0 | no suitable model |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page | $3.64 with Amazon: Nova Micro 1.0 | $3.30 with Inference.net: Schematron V2 Turbo |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass | $1.89 with Amazon: Nova Micro 1.0 | $1.65 with Inference.net: Schematron V2 Turbo |
| You need | Amazon | Inference.net |
|---|---|---|
| Any model | Amazon: Nova Micro 1.0 ($0.06) | Inference.net: Schematron V2 Turbo ($0.06) |
| With tool calling | Amazon: Nova Micro 1.0 ($0.06) | none listed |
| With image input | Amazon: Nova Lite 1.0 ($0.10) | none listed |
| With reasoning mode | Amazon: Nova 2 Lite ($0.85) | none listed |
| 128K+ context | Amazon: Nova Micro 1.0 ($0.06) | Inference.net: Schematron V2 Turbo ($0.06) |
| 1M+ context | Amazon: Nova 2 Lite ($0.85) | none listed |
| Model type | Amazon | Inference.net |
|---|---|---|
| text+image+file+video->text | 1 | 0 |
| text+image->text | 3 | 0 |
| text->text | 1 | 2 |
| Price per 1M (3:1 blend) | Amazon | Inference.net |
|---|---|---|
| Free | 0 | 0 |
| Under $0.50 | 2 | 2 |
| $0.50 – $3 | 2 | 0 |
| $3 – $10 | 1 | 0 |
| $10 and up | 0 | 0 |
Inference.net is cheaper on a typical model: a median of $0.08 per 1M tokens (3:1 input/output) against $0.85 for Amazon. The cheapest paid models are Amazon: Nova Micro 1.0 at $0.06 and Inference.net: Schematron V2 Turbo at $0.06.
It depends on the job: Amazon offers the broader line-up (5 models vs 2), Inference.net the lower typical price, Amazon the longest context (1M tokens). The workload table above shows which wins for chat, RAG, agents, batch jobs and long documents.
Amazon: Amazon lists 5 models and Inference.net lists 2.
Amazon: Amazon's longest is Amazon: Nova 2 Lite at 1M tokens; Inference.net's is Inference.net: Schematron V2 Small at 128K.
Neither lists a free model; both are pay-per-token.
Amazon: 4 of 5 models accept images. Inference.net: 0 of 2.