Choose Cohere: Command R (08-2024) if…
- you need tool / function calling — to call your APIs and run agent loops; Inference.net: Schematron V2 Turbo does not advertise it
Cohere: Command R (08-2024) vs Inference.net: Schematron V2 Turbo
Neither wins outright: Cohere: Command R (08-2024) is the pick when you need tool / function calling, Inference.net: Schematron V2 Turbo when cost matters at scale.
Key numbers
| Spec | Cohere: Command R (08-2024) | Inference.net: Schematron V2 Turbo |
|---|---|---|
| Provider | Cohere | Inference.net |
| Input price (per 1M tokens) | $0.15 | $0.03 |
| Output price (per 1M tokens) | $0.60 | $0.15 |
| Blended price (3:1 input/output) | $0.26 | $0.06 |
| Cheaper than … of all models we track | 65% | 86% |
| Context window | 128K tokens (~192 pages) | 128K tokens (~192 pages) |
| Larger context than … of all models | 14% | 14% |
| Max output per response | 4K tokens (~3,000 words) | 8K tokens (~6,100 words) |
| Input types | text | text |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2024-08-30 | 2026-09-12 |
Advertisement
What it costs for real workloads
Monthly cost at list price for five common workloads. Token counts per unit are stated so you can scale them to your own traffic. A workload that does not fit a model's context window is marked rather than priced.
| Workload (per month) | Cohere: Command R (08-2024) | Inference.net: Schematron V2 Turbo | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $23.25 | $5.25 | Inference.net: Schematron V2 Turbo saves $18.00 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $24.00 | $5.10 | Inference.net: Schematron V2 Turbo saves $18.90 |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context (60,000 in / 6,000 out tokens) | $25.20 | $5.40 | Inference.net: Schematron V2 Turbo saves $19.80 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $15.60 | $3.30 | Inference.net: Schematron V2 Turbo saves $12.30 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $8.10 | $1.65 | Inference.net: Schematron V2 Turbo saves $6.45 |
Capabilities side by side
| Capability | Cohere: Command R (08-2024) | Inference.net: Schematron V2 Turbo | What it lets you do |
|---|---|---|---|
| Tool / function calling | ✓ Yes | — | call your APIs and run agent loops |
| Structured output (JSON schema) | ✓ Yes | ✓ Yes | return JSON that validates against your schema |
| Reasoning / thinking mode | — | — | spend extra tokens thinking before answering hard problems |
| Image input | — | — | read screenshots, charts and scanned pages |
| Audio input | — | — | take speech or audio directly |
| File / PDF input | — | — | accept documents without your own parsing step |
| Image output | — | — | generate images, not just text |
| Built-in web search | — | — | answer from live web results |
| Seed (reproducible sampling) | ✓ Yes | ✓ Yes | repeat a generation for tests and evals |
| Log-probabilities | — | — | read token confidence for classification and scoring |
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
Price history
- Cohere: Command R (08-2024): price unchanged since we started tracking it on 2026-03-10.
- Inference.net: Schematron V2 Turbo: price unchanged since we started tracking it on 2026-09-12.
Which should you choose?
Choose Inference.net: Schematron V2 Turbo if…
- cost matters at scale — it is 77% cheaper on a typical 3:1 input/output mix ($5.25 vs $23.25 a month for 50,000 support chats)
- you generate long outputs in one go — up to 8K tokens (about 6,100 words) per response
- you want the newer model — released 2026-09-12, 25 months after the other
Frequently asked questions
Is Cohere: Command R (08-2024) better than Inference.net: Schematron V2 Turbo?
Neither wins outright: Cohere: Command R (08-2024) is the pick when you need tool / function calling, Inference.net: Schematron V2 Turbo when cost matters at scale. In short: Cohere: Command R (08-2024) when you need tool / function calling; Inference.net: Schematron V2 Turbo when cost matters at scale, you generate long outputs in one go, you want the newer model.
Which is cheaper, Cohere: Command R (08-2024) or Inference.net: Schematron V2 Turbo?
Inference.net: Schematron V2 Turbo is cheaper: $0.06 vs $0.26 per 1M tokens at a typical 3:1 input/output mix, 77% less. For 50,000 support conversations a month that is $5.25 against $23.25.
How much do Cohere: Command R (08-2024) and Inference.net: Schematron V2 Turbo cost per million tokens?
Cohere: Command R (08-2024) costs $0.15 per 1M input tokens and $0.60 per 1M output tokens; Inference.net: Schematron V2 Turbo costs $0.03 input and $0.15 output. Output tokens are billed separately, so long answers shift the gap.
Which has the bigger context window, Cohere: Command R (08-2024) or Inference.net: Schematron V2 Turbo?
Both take 128K tokens per request — roughly 192 pages of text.
Do Cohere: Command R (08-2024) and Inference.net: Schematron V2 Turbo support function calling and JSON output?
Tool calling — Cohere: Command R (08-2024): yes, Inference.net: Schematron V2 Turbo: not advertised. JSON-schema structured output — Cohere: Command R (08-2024): yes, Inference.net: Schematron V2 Turbo: yes.
Can Cohere: Command R (08-2024) or Inference.net: Schematron V2 Turbo read images?
Neither accepts image input — both are text-in models.
Is Cohere: Command R (08-2024) or Inference.net: Schematron V2 Turbo free to use?
No free variant is listed for either; both are pay-per-token.
What is the maximum output length of Cohere: Command R (08-2024) and Inference.net: Schematron V2 Turbo?
Cohere: Command R (08-2024) can write up to 4K tokens (about 3,000 words) per response; Inference.net: Schematron V2 Turbo up to 8K (about 6,100 words).
When were Cohere: Command R (08-2024) and Inference.net: Schematron V2 Turbo released?
Cohere: Command R (08-2024) was listed on 2024-08-30; Inference.net: Schematron V2 Turbo on 2026-09-12.
About the two models
Cohere: Command R (08-2024)
command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...
Full Cohere: Command R (08-2024) specs →Inference.net: Schematron V2 Turbo
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...
Full Inference.net: Schematron V2 Turbo specs →