Updated 9 Nov · updated in the last 30 hours

DeepSeek V3.1 API Pricing

DeepSeek V3.1 API pricing: $0.25 per 1M tokens for input and $0.95 per 1M tokens for output, from OpenRouter. Published Last checked · Source (data) · Methodology

OpenRouter: Amount worked out from the source page: $0.25 per 1M tokens, in USD · as shown in the United States on 9 Nov 2026 · the page does not say whether tax is included; we do not assume it is excluded · no price change seen since 16 Oct 2026.

Data as of9 Nov 2026Prices checked 9 Nov 2026 · test requests to 8 Nov 2026Data & API
Task receipt: OpenRouter: $0.043; Warm cache: $0.026 Calculated · Document analysis Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries. Warm-cache saving: $0.017 per task. Dashed outline: the no-cache bill.
Task receipt.Calculated · Document analysis Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries. Warm-cache saving: $0.017 per task. Dashed outline: the no-cache bill. Open image · Explore the chart · Measured Lab · CC BY 4.0
See cost receipt

Prices USD per 1M tokens, as listed

  • $0.25Input per 1M tokens, through OpenRouter Published
  • $0.95Output per 1M tokens, through OpenRouter Published
All prices by channel
Price per 1M tokensProvider directThrough OpenRouterPrevious prices by channel
Input—$0.25 Published—
Output—$0.95 Published—
Cached input · read—$0.13 Published—

Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026

16 Oct 2026$0.25 throughout9 Nov 2026

Context window163,840tokens Published
Max output147,456tokens Published

OpenRouter providers who serves this model through OpenRouter, at what price

OpenRouter sends a call without a pinned provider to one of these endpoints, and each endpoint has its own price. Prices are USD per 1M tokens, input / output.

Pinned min: $0.25 / $0.95 · DeepInfra (deepinfra/fp4)

Unpinned range: input $0.25–$0.65, output $0.95–$1.50 across 4 providers (listing shows $0.25 / $0.95).

Models with the widest provider price spread on OpenRouter

Request fragment that pins DeepInfra (deepinfra/fp4):

{"provider": {"order": ["deepinfra/fp4"], "allow_fallbacks": false}}

With fallbacks turned off, OpenRouter does not move the call to another provider. A full endpoint tag pins that endpoint; the provider name alone covers all of its endpoints (OpenRouter provider routing).

All endpoints (4), by input price
ProviderEndpoint tagPrecisionInputOutputContext, tokensStatus code
DeepInfradeepinfra/fp4fp4$0.25$0.95163,8400
SiliconFlowsiliconflow/fp8fp8$0.27$1.00163,8400
CoreWeavecoreweave/fp8fp8$0.50$1.50161,0000
SambaNovasambanova/fp8fp8$0.65$1.50131,072-5

Sorted by input price, then output price. Precision is the quantization field of the endpoints list. Status code is the status field of the endpoints list, as read.

How we got this number

  • What we read: the published price on openrouter.ai/api/v1/models
  • Checked: ; tracked since 16 Oct 2026
  • Shown in: the United States
  • Checks so far: 25 checks since 16 Oct 2026
  • What changed: no price change since 16 Oct 2026
  • Page updated:

Other measured facts

QuestionAnswerCheckedStatus
How much does DeepSeek V3.1 cost per 1M cache-read tokens (cache hits) on OpenRouter?$0.13 per 1M tokensPublished
How much does DeepSeek V3.1 cost per 1M output tokens on OpenRouter?$0.95 per 1M tokensPublished
What is the context window of DeepSeek V3.1 on OpenRouter, in tokens?163,840 tokensPublished
What is the maximum output length of DeepSeek V3.1 on OpenRouter, in tokens?147,456 tokensPublished

History

  1. — 32,768 tokens → 147,456 tokens (What is the maximum output length of DeepSeek V3.1 on OpenRouter, in tokens?) Confirmed by the check on 30 Oct 2026. What this means for you: The figure you would rely on has moved; check the evidence before relying on the old one.
  2. — First check: $0.25 per 1M tokens

The source record lists $0.00000025 per token ($0.25 per 1M tokens), fetched on 9 Nov 2026.

The source record, as published
"prompt":"0.00000025"
What the source says · openrouter.ai

Latest briefings each price change recalculated as a task cost

  1. DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)
  2. DeepSeek V4.1 Flash 1017: price cut input $0.300 → $0.0060 per 1M tokens (-98 %), output $1.20 → $0.500 per 1M tokens (-58 %)
  3. MoonshotAI Kimi K2.5: price rise input $0.500 → $0.532 per 1M tokens (+6 %), output $2.50 → $3.33 per 1M tokens (+33 %)

All briefings

Record history — 113 records for 5 questions
Last record
Shown in
the United States
How much does DeepSeek V3.1 cost per 1M input tokens on OpenRouter?
TimeValueStatus
9 Nov 2026$0.25 per 1M tokensPublished
8 Nov 2026$0.25 per 1M tokensPublished
7 Nov 2026$0.25 per 1M tokensPublished
6 Nov 2026$0.25 per 1M tokensPublished
5 Nov 2026$0.25 per 1M tokensPublished
4 Nov 2026$0.25 per 1M tokensPublished
3 Nov 2026$0.25 per 1M tokensPublished
2 Nov 2026$0.25 per 1M tokensPublished
1 Nov 2026$0.25 per 1M tokensPublished
31 Oct 2026$0.25 per 1M tokensPublished
30 Oct 2026$0.25 per 1M tokensPublished
29 Oct 2026$0.25 per 1M tokensPublished
How much does DeepSeek V3.1 cost per 1M cache-read tokens (cache hits) on OpenRouter?
TimeValueStatus
9 Nov 2026$0.13 per 1M tokensPublished
8 Nov 2026$0.13 per 1M tokensPublished
7 Nov 2026$0.13 per 1M tokensPublished
6 Nov 2026$0.13 per 1M tokensPublished
5 Nov 2026$0.13 per 1M tokensPublished
4 Nov 2026$0.13 per 1M tokensPublished
3 Nov 2026$0.13 per 1M tokensPublished
2 Nov 2026$0.13 per 1M tokensPublished
1 Nov 2026$0.13 per 1M tokensPublished
31 Oct 2026$0.13 per 1M tokensPublished
30 Oct 2026$0.13 per 1M tokensPublished
29 Oct 2026$0.13 per 1M tokensPublished
How much does DeepSeek V3.1 cost per 1M output tokens on OpenRouter?
TimeValueStatus
9 Nov 2026$0.95 per 1M tokensPublished
8 Nov 2026$0.95 per 1M tokensPublished
7 Nov 2026$0.95 per 1M tokensPublished
6 Nov 2026$0.95 per 1M tokensPublished
5 Nov 2026$0.95 per 1M tokensPublished
4 Nov 2026$0.95 per 1M tokensPublished
3 Nov 2026$0.95 per 1M tokensPublished
2 Nov 2026$0.95 per 1M tokensPublished
1 Nov 2026$0.95 per 1M tokensPublished
31 Oct 2026$0.95 per 1M tokensPublished
30 Oct 2026$0.95 per 1M tokensPublished
29 Oct 2026$0.95 per 1M tokensPublished
What is the context window of DeepSeek V3.1 on OpenRouter, in tokens?
TimeValueStatus
9 Nov 2026163,840 tokensPublished
8 Nov 2026163,840 tokensPublished
7 Nov 2026163,840 tokensPublished
6 Nov 2026163,840 tokensPublished
5 Nov 2026163,840 tokensPublished
4 Nov 2026163,840 tokensPublished
3 Nov 2026163,840 tokensPublished
2 Nov 2026163,840 tokensPublished
1 Nov 2026163,840 tokensPublished
31 Oct 2026163,840 tokensPublished
30 Oct 2026163,840 tokensPublished
29 Oct 2026163,840 tokensPublished
What is the maximum output length of DeepSeek V3.1 on OpenRouter, in tokens?
TimeValueStatus
9 Nov 2026147,456 tokensPublished
8 Nov 2026147,456 tokensPublished
7 Nov 2026147,456 tokensPublished
6 Nov 2026147,456 tokensPublished
5 Nov 2026147,456 tokensPublished
4 Nov 2026147,456 tokensPublished
3 Nov 2026147,456 tokensPublished
2 Nov 2026147,456 tokensPublished
1 Nov 2026147,456 tokensPublished
31 Oct 2026147,456 tokensPublished
30 Oct 2026147,456 tokensPublished
29 Oct 2026147,456 tokensPublished

Showing the latest 60 of 113 records; the full history is in data.json and data.csv.

Download JSON Download CSV

Explore the numbers

DeepSeek V3.1

OpenRouter$0.043Warm cache$0.026$0.00$0.02$0.04$0.06OpenRouter$0.043Warm cache$0.026$0.00$0.02$0.04$0.06
OpenRouter$621.96Warm cache$374.27$0$200$400$600$800OpenRouter$621.96Warm cache$374.27$0$200$400$600$800

Calculated · Document analysis

Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries.

Warm-cache saving: $0.017 per task. Dashed outline: the no-cache bill.

Assumption: first-step cache fraction 75%; earlier context is read again and new context is written. All calls stay within the cache lifetime.

Formula: sum of input, output, cache reads and cache writes × their published rates / 1M. Each step uses its own context tier. Missing cache or batch prices are Unknown.

Fresh input · Visible output · Cache read · Cache write

Sources: this page; published model prices (data (JSON)); task assumptions (data (JSON)). Published prices · Observed responses · Calculated scenarios · Assumptions stated with each chart.