DeepSeek Reasoner
deepseek/reasoner出品方： DeepSeek · 系列: deepseek-thinking · 發布 2025-12-01 · 知識截止: 2025-09
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
能力清單
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding3
- Tool calling0/40
- Structured output0/20
- Reasoning0/10
- Context window (100K → 1M)0/20
- Provider availability3/10
Agents18
- Tool calling0/35
- Structured output0/25
- Reasoning0/15
- Output token limit15/15
- Provider availability3/10
JSON / structured output29
- Structured output / JSON mode0/50
- Tool calling0/20
- Temperature control10/10
- Price-friendly for high-volume19/20
Cost efficiency76
- Headline price (log-scaled)71/95
- Has prompt-cache pricing5/5
Long context0
- Context ≥ 100K0/100
Production-readiness71
- Number of independent providers15/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $0.88 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $1.77 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $0.44 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $1.47 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $1.94 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
定價詳情
推薦定價來自 orcarouter · deepseek/deepseek-reasoner
於 3 家供應商可用
| 服務商 | 服務商模型 ID | 輸入 / 1M | 輸出 / 1M | 上下文 | 發布日期 |
|---|---|---|---|---|---|
| NanoGPT nano-gpt | deepseek-reasoner | $0.400 | $1.70 | 64K | 2025-12-01 |
| OrcaRouter orcarouter | deepseek/deepseek-reasoner | $0.147 | $0.295 | 1M | 2025-12-01 |
| Helicone helicone | deepseek-reasoner | $0.560 | $1.68 | 128K | 2025-01-20 |
各渠道資料存在不一致
- context_window varies: 1000000, 128000, 64000
- release_date varies (span 315d): 2025-01-20, 2025-12-01
各服務商對此模型的回報值不一致。上方「核心數據」採用代表性服務商的值；逐項請以下表為準。
Frequently asked questions
How much does DeepSeek Reasoner cost?
DeepSeek Reasoner costs $0.147 per 1M input tokens and $0.295 per 1M output tokens, sourced from orcarouter. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of DeepSeek Reasoner?
DeepSeek Reasoner has a context window of 64K tokens, with a max output of 66K tokens per reply. This is the total combined size of prompt + completion.
Does DeepSeek Reasoner support tool calling?
No. DeepSeek Reasoner does not support tool calling (function calling). If your workflow requires it, look at the /capabilities/tool-calling list for alternatives.
Does DeepSeek Reasoner support structured output / JSON mode?
No. DeepSeek Reasoner does not support structured output / JSON-schema-constrained decoding. If your workflow requires it, look at the /capabilities/structured-output list for alternatives.
Can DeepSeek Reasoner accept image input?
No. DeepSeek Reasoner only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is DeepSeek Reasoner open-weight?
Yes. DeepSeek Reasoner's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to DeepSeek Reasoner?
If DeepSeek Reasoner doesn't fit, consider DeepSeek V4 Pro, DeepSeek V4 Flash, DeepSeek V4.1 Flash. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More DeepSeek models
- DeepSeek V4 Pro$0.43 in / $0.87 out
- DeepSeek V4 Flash$0.15 in / $0.60 out
- DeepSeek V4.1 Flash$0.14 in / $0.28 out
- DeepSeek V4 Flash 0731$0.04 in / $0.07 out
- DeepSeek V4 Pro 0813$0.35 in / $0.80 out
Capability lists this model is in
最近更新：
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.