Choose DeepSeek: DeepSeek V3.1 Terminus (exacto) if…
No advantage on the data we track — pick it for provider preference or output quality on your own prompts.
DeepSeek: DeepSeek V3.1 Terminus (exacto) vs OpenAI: gpt-oss-20b (batch)
OpenAI: gpt-oss-20b (batch) comes out ahead on the data we track: 1 advantage and none for DeepSeek: DeepSeek V3.1 Terminus (exacto).
Key numbers
| Spec | DeepSeek: DeepSeek V3.1 Terminus (exacto) | OpenAI: gpt-oss-20b (batch) |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Input price (per 1M tokens) | $0.21 | $0.02 |
| Output price (per 1M tokens) | $0.79 | $0.11 |
| Blended price (3:1 input/output) | $0.35 | $0.05 |
| Cheaper than … of all models we track | 61% | 87% |
| Context window | 164K tokens (~246 pages) | 131K tokens (~197 pages) |
| Larger context than … of all models | 36% | 23% |
| Max output per response | n/a | 118K tokens (~88,500 words) |
| Input types | text | text |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2025-09-22 | 2025-08-05 |
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) | DeepSeek: DeepSeek V3.1 Terminus (exacto) | OpenAI: gpt-oss-20b (batch) | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $31.55 | $4.04 | OpenAI: gpt-oss-20b (batch) saves $27.51 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $33.10 | $4.00 | OpenAI: gpt-oss-20b (batch) saves $29.10 |
| 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) | $34.68 | $4.22 | OpenAI: gpt-oss-20b (batch) saves $30.46 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $21.54 | $2.59 | OpenAI: gpt-oss-20b (batch) saves $18.95 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $11.29 | $1.31 | OpenAI: gpt-oss-20b (batch) saves $9.98 |
Capabilities side by side
| Capability | DeepSeek: DeepSeek V3.1 Terminus (exacto) | OpenAI: gpt-oss-20b (batch) | What it lets you do |
|---|---|---|---|
| Tool / function calling | ✓ Yes | ✓ Yes | call your APIs and run agent loops |
| Structured output (JSON schema) | ✓ Yes | ✓ Yes | return JSON that validates against your schema |
| Reasoning / thinking mode | ✓ Yes | ✓ Yes | 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
- DeepSeek: DeepSeek V3.1 Terminus (exacto): price unchanged since we started tracking it on 2026-03-10.
- OpenAI: gpt-oss-20b (batch): input price cut 52% ($0.05 → $0.02/1M), output price cut 44% ($0.20 → $0.11/1M) on 2026-09-23.
| Date | Model | Input / 1M | Output / 1M |
|---|---|---|---|
| 2026-09-23 | OpenAI: gpt-oss-20b (batch) | $0.02 | $0.11 |
Which should you choose?
Choose OpenAI: gpt-oss-20b (batch) if…
- cost matters at scale — it is 87% cheaper on a typical 3:1 input/output mix ($4.04 vs $31.55 a month for 50,000 support chats)
Frequently asked questions
Is DeepSeek: DeepSeek V3.1 Terminus (exacto) better than OpenAI: gpt-oss-20b (batch)?
OpenAI: gpt-oss-20b (batch) comes out ahead on the data we track: 1 advantage and none for DeepSeek: DeepSeek V3.1 Terminus (exacto).
Which is cheaper, DeepSeek: DeepSeek V3.1 Terminus (exacto) or OpenAI: gpt-oss-20b (batch)?
OpenAI: gpt-oss-20b (batch) is cheaper: $0.05 vs $0.35 per 1M tokens at a typical 3:1 input/output mix, 87% less. For 50,000 support conversations a month that is $4.04 against $31.55.
How much do DeepSeek: DeepSeek V3.1 Terminus (exacto) and OpenAI: gpt-oss-20b (batch) cost per million tokens?
DeepSeek: DeepSeek V3.1 Terminus (exacto) costs $0.21 per 1M input tokens and $0.79 per 1M output tokens; OpenAI: gpt-oss-20b (batch) costs $0.02 input and $0.11 output. Output tokens are billed separately, so long answers shift the gap.
Which has the bigger context window, DeepSeek: DeepSeek V3.1 Terminus (exacto) or OpenAI: gpt-oss-20b (batch)?
DeepSeek: DeepSeek V3.1 Terminus (exacto): 164K tokens, about 246 pages, against 131K (about 197 pages) for OpenAI: gpt-oss-20b (batch).
Do DeepSeek: DeepSeek V3.1 Terminus (exacto) and OpenAI: gpt-oss-20b (batch) support function calling and JSON output?
Tool calling — DeepSeek: DeepSeek V3.1 Terminus (exacto): yes, OpenAI: gpt-oss-20b (batch): yes. JSON-schema structured output — DeepSeek: DeepSeek V3.1 Terminus (exacto): yes, OpenAI: gpt-oss-20b (batch): yes.
Can DeepSeek: DeepSeek V3.1 Terminus (exacto) or OpenAI: gpt-oss-20b (batch) read images?
Neither accepts image input — both are text-in models.
Is DeepSeek: DeepSeek V3.1 Terminus (exacto) or OpenAI: gpt-oss-20b (batch) free to use?
No free variant is listed for either; both are pay-per-token.
When were DeepSeek: DeepSeek V3.1 Terminus (exacto) and OpenAI: gpt-oss-20b (batch) released?
DeepSeek: DeepSeek V3.1 Terminus (exacto) was listed on 2025-09-22; OpenAI: gpt-oss-20b (batch) on 2025-08-05.
Has the price of DeepSeek: DeepSeek V3.1 Terminus (exacto) or OpenAI: gpt-oss-20b (batch) changed?
DeepSeek: DeepSeek V3.1 Terminus (exacto): price unchanged since we started tracking it on 2026-03-10. OpenAI: gpt-oss-20b (batch): input price cut 52% ($0.05 → $0.02/1M), output price cut 44% ($0.20 → $0.11/1M) on 2026-09-23.
About the two models
DeepSeek: DeepSeek V3.1 Terminus (exacto)
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.
Full DeepSeek: DeepSeek V3.1 Terminus (exacto) specs →OpenAI: gpt-oss-20b (batch)
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Full OpenAI: gpt-oss-20b (batch) specs →