Neither wins outright: DeepSeek Chat (legacy id) is the pick when you need tool / function calling, Inference.net: Schematron V2 Turbo when cost matters at scale.
| Spec | DeepSeek Chat (legacy id) | Inference.net: Schematron V2 Turbo |
|---|---|---|
| Provider | DeepSeek | Inference.net |
| Input price (per 1M tokens) | $0.26 | $0.03 |
| Output price (per 1M tokens) | $1.03 | $0.15 |
| Blended price (3:1 input/output) | $0.45 | $0.06 |
| Cheaper than … of all models we track | 55% | 86% |
| Context window | 164K tokens (~246 pages) | 128K tokens (~192 pages) |
| Larger context than … of all models | 35% | 14% |
| Max output per response | 16K tokens (~12,000 words) | 8K tokens (~6,100 words) |
| Input types | text | text |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2024-12-26 | 2026-09-12 |
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) | DeepSeek Chat (legacy id) | Inference.net: Schematron V2 Turbo | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $39.88 | $5.25 | Inference.net: Schematron V2 Turbo saves $34.63 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $41.17 | $5.10 | Inference.net: Schematron V2 Turbo saves $36.07 |
| 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) | $43.23 | $5.40 | Inference.net: Schematron V2 Turbo saves $37.83 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $26.76 | $3.30 | Inference.net: Schematron V2 Turbo saves $23.46 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $13.90 | $1.65 | Inference.net: Schematron V2 Turbo saves $12.25 |
| Capability | DeepSeek Chat (legacy id) | 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.
| Date | Model | Input / 1M | Output / 1M |
|---|---|---|---|
| 2026-10-20 | DeepSeek Chat (legacy id) | $0.26 | $1.03 |
| 2026-10-17 | DeepSeek Chat (legacy id) | $0.32 | $0.89 |
| 2026-10-16 | DeepSeek Chat (legacy id) | $0.26 | $1.03 |
| 2026-10-10 | DeepSeek Chat (legacy id) | $0.32 | $0.89 |
| 2026-09-28 | DeepSeek Chat (legacy id) | $0.26 | $1.03 |
| 2026-09-18 | DeepSeek Chat (legacy id) | $0.32 | $0.89 |
| 2026-09-10 | DeepSeek Chat (legacy id) | $0.26 | $1.03 |
| 2026-09-04 | DeepSeek Chat (legacy id) | $0.32 | $0.89 |
Neither wins outright: DeepSeek Chat (legacy id) is the pick when you need tool / function calling, Inference.net: Schematron V2 Turbo when cost matters at scale. In short: DeepSeek Chat (legacy id) when you need tool / function calling, you generate long outputs in one go; Inference.net: Schematron V2 Turbo when cost matters at scale, you want the newer model.
Inference.net: Schematron V2 Turbo is cheaper: $0.06 vs $0.45 per 1M tokens at a typical 3:1 input/output mix, 87% less. For 50,000 support conversations a month that is $5.25 against $39.88.
DeepSeek Chat (legacy id) costs $0.26 per 1M input tokens and $1.03 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.
DeepSeek Chat (legacy id): 164K tokens, about 246 pages, against 128K (about 192 pages) for Inference.net: Schematron V2 Turbo.
Tool calling — DeepSeek Chat (legacy id): yes, Inference.net: Schematron V2 Turbo: not advertised. JSON-schema structured output — DeepSeek Chat (legacy id): yes, Inference.net: Schematron V2 Turbo: yes.
Neither accepts image input — both are text-in models.
No free variant is listed for either; both are pay-per-token.
DeepSeek Chat (legacy id) can write up to 16K tokens (about 12,000 words) per response; Inference.net: Schematron V2 Turbo up to 8K (about 6,100 words).
DeepSeek Chat (legacy id) was listed on 2024-12-26; Inference.net: Schematron V2 Turbo on 2026-09-12.
DeepSeek Chat (legacy id): input price cut 20% ($0.32 → $0.26/1M), output price raised 13% ($0.89 → $1.03/1M) on 2026-10-20 (9 price changes since 2026-03-10). Inference.net: Schematron V2 Turbo: price unchanged since we started tracking it on 2026-09-12.
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
Full DeepSeek Chat (legacy id) specs →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 →