DeepSeek V4.1 Flash API pricing
DeepSeek · Budget · Apache 2.0 · released 2026-09. Prices in USD per 1 million tokens. Data snapshot: 2026-10-14.
The price we quote for DeepSeek V4.1 Flash has changed 17 times since 2026-09-11, most recently on 2026-10-12 when the quoted host changed (-50.0%); it is now the 74th cheapest of 144 Budget models. Buying from Decart rather than at the price we quote lowers the token price by about 67%, for a quantized fp4 build. No Arena score is published for it, so it carries no Efficiency score and cannot hold the FinOps Friendly badge.
- Input: $0.15 per 1M tokens
- Output: $0.60 per 1M tokens
- Batch API (in/out): $0.112 / $0.336 per 1M tokens
- Prompt-cache read: $0.003 per 1M tokens
- Context window: 1M tokens
- Arena ELO: Not published
Market position
On blended price ($0.465 per 1M tokens at 30% input, 70% output) it is cheaper than 46% of Budget models: 74th cheapest of 144, tied with 4 others. Across every category it is cheaper than 73% of priced text models in the catalogue: 74th cheapest of 282, tied with 4 others.
Licence, size and capabilities
DeepSeek V4.1 Flash is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token. Its published size is 8B parameters. Listed capabilities: Text, Vision, Reasoning, Agents. Filling its 1M context window once costs $0.15 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 29 different hosts. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
Cheapest host: Decart at $0.09 input / $0.18 output per 1M tokens, 67% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp4 build, which is not the same product as the full-precision model. The dearest, Venice, charges 6.1x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| Decart | $0.09 | $0.18 | fp4 |
| Sail Research | $0.09 | $0.30 | fp4 |
| DeepInfra | $0.14 | $0.42 | fp8 |
| Relace | $0.0224 | $0.60 | not declared |
| StreamLake | $0.147 | $0.588 | fp8 |
| DeepSeek (model maker, price we quote) | $0.15 | $0.60 | not declared |
| InferenceNet | $0.10 | $0.66 | fp8 |
| Baidu | $0.1647 | $0.6588 | fp8 |
| DigitalOcean | $0.165 | $0.66 | not declared |
| CoreWeave | $0.20 | $0.65 | fp8 |
| GMICloud | $0.18 | $0.72 | fp8 |
| Morph | $0.028 | $0.80 | fp8 |
| AtlasCloud | $0.192 | $0.768 | fp8 |
| Novita | $0.195 | $0.78 | fp8 |
| OpenInference | $0.0202 | $0.891 | fp4 |
| Phala | $0.21 | $0.84 | not declared |
| Cloudflare | $0.10 | $0.90 | not declared |
| Wafer | $0.10 | $0.99 | not declared |
| Ionstream | $0.27 | $1.10 | not declared |
| Makora | $0.27 | $1.15 | fp8 |
| Crusoe | $0.29 | $1.20 | fp8 |
| BaseTen | $0.30 | $1.20 | fp8 |
| Alibaba | $0.30 | $1.20 | not declared |
| Together | $0.30 | $1.20 | not declared |
| SiliconFlow | $0.30 | $1.20 | fp8 |
| Modal | $0.30 | $1.20 | not declared |
| Parasail | $0.30 | $1.20 | fp8 |
| Fireworks | $0.30 | $1.20 | not declared |
| Venice | $0.30 | $1.20 | fp8 |
List prices as published on 2026-10-14, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown. These hosts do not all serve the model at the same numeric precision, so the cheapest is not a like-for-like substitute for the dearest.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where DeepSeek publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $39 – $53 |
| Knowledge Q&A | 2,000 / 800 | $57 – $78 |
| Meeting Summary | 10,000 / 1,200 | $141 – $222 |
| Marketing Content | 2,500 / 1,800 | $138 – $146 |
| Coding Task | 3,000 / 2,000 | $143 – $165 |
| Invoice Processing | 1,500 / 600 | $32 – $59 |
| Call Summary | 2,000 / 700 | $44 – $72 |
| Agent Workflow | 6,000 / 3,000 | $208 – $270 |
Price history
DeepSeek V4.1 Flash entered our daily price archive on 2026-09-11; tracking began on 2026-08-15. It listed at $0.15 input / $0.60 output per 1M tokens that day. The price we quote has changed 17 times since then, 12 of them a change of quoted host rather than a repricing. The latest change, on 2026-10-12, was -50.0% on the blended price (30% input, 70% output), to $0.15 input / $0.60 output (quoted host changed, not a repricing). Net of all changes, the blended price is back where it started on 2026-09-11.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-10-12 | $0.30 / $1.20 | $0.15 / $0.60 | -50.0% (quoted host changed, not a repricing) |
| 2026-10-08 | $0.05 / $1.20 | $0.30 / $1.20 | +8.8% (quoted host changed, not a repricing) |
| 2026-10-07 | $0.0435 / $1.32 | $0.05 / $1.20 | -8.8% |
| 2026-10-06 | $0.30 / $1.20 | $0.0435 / $1.32 | +0.8% |
| 2026-10-05 | $0.003 / $2.40 | $0.30 / $1.20 | -44.7% (quoted host changed, not a repricing) |
12 earlier changes are not listed.
Alternatives to DeepSeek V4.1 Flash
- Next cheaper Budget model: DeepSeek V4 Flash 0731 (DeepSeek) at $0.4528 blended, 3% less.
- Next more expensive: Llama 4 Scout (Meta) at $0.467 blended, under 1% more.
Other models from DeepSeek
The 8 nearest to DeepSeek V4.1 Flash in price, of 13 other DeepSeek models in the catalogue. Prices per 1M tokens, input then output.
- DeepSeek V4 Flash 0423: $0.091 / $0.182
- DeepSeek V3.2 Exp: $0.27 / $0.41
- DeepSeek V4 Flash 0731: $0.016 / $0.64
- DeepSeek V4 Flash Vision Exp: $0.2156 / $0.6468
- DeepSeek V3.2: $0.259 / $0.80
- DeepSeek V3: $0.32 / $0.89
- DeepSeek V3.1: $0.25 / $0.95
- DeepSeek V3.1 Terminus: $0.27 / $1.00
All 14 DeepSeek models and prices
Common questions about DeepSeek V4.1 Flash pricing
- How much does DeepSeek V4.1 Flash cost?
- DeepSeek V4.1 Flash costs $0.15 per 1M input tokens and $0.60 per 1M output tokens. That is the model maker's own rate (DeepSeek). Prices as listed on 2026-10-14.
- Which host is cheapest for DeepSeek V4.1 Flash?
- Cheapest host: Decart at $0.09 input / $0.18 output per 1M tokens, 67% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp4 build, which is not the same product as the full-precision model. The dearest, Venice, charges 6.1x the cheapest. Host rates as listed on 2026-10-14.
- Does DeepSeek V4.1 Flash offer batch or cached pricing?
- Yes, both. Batch API pricing is $0.112 per 1M input tokens and $0.336 per 1M output tokens, and prompt-cache reads cost $0.003 per 1M tokens, as listed on 2026-10-14.
- What would DeepSeek V4.1 Flash cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $53 on DeepSeek V4.1 Flash at the list price quoted on 2026-10-14.
- Can DeepSeek V4.1 Flash be self-hosted?
- Yes. DeepSeek V4.1 Flash is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token.
- Has the price of DeepSeek V4.1 Flash changed?
- DeepSeek V4.1 Flash entered our daily price archive on 2026-09-11; tracking began on 2026-08-15. It listed at $0.15 input / $0.60 output per 1M tokens that day. The price we quote has changed 17 times since then, 12 of them a change of quoted host rather than a repricing. The latest change, on 2026-10-12, was -50.0% on the blended price (30% input, 70% output), to $0.15 input / $0.60 output (quoted host changed, not a repricing). Net of all changes, the blended price is back where it started on 2026-09-11.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server