DeepSeek V4 Flash 0423 API pricing
DeepSeek · Budget price tier · MIT · released 2026-04. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $22.50 on DeepSeek V4 Flash 0423; the next cheaper model in the Budget price tier for this workload, LFM3-1.7B, does it for $22.00. The price we quote for DeepSeek V4 Flash 0423 has changed 48 times since 2026-08-15, most recently by -1.1% on 2026-11-11; it is now the 29th cheapest of 160 models in the Budget price tier. Buying from StreamLake rather than at the price we quote lowers the token price by about 8%, for a quantized fp8 build. It holds the FinOps Friendly badge: top-40% Arena quality, top-30% Efficiency, not among the dearest 30%, and no stability flag.
- Input: $0.09 per 1M tokens
- Output: $0.18 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.018 per 1M tokens
- Context window: 1M tokens
- Arena ELO: 1432 as of 2026-11-08
Market position
On blended price ($0.153 per 1M tokens at 30% input, 70% output) it is cheaper than 82% of models in the Budget price tier: 29th cheapest of 160. Across every price tier it is cheaper than 91% of priced text models in the catalogue: 29th cheapest of 303. Its Arena ELO of 1432 ranks 64th of the 160 models that carry one, above 60% of them. With an Arena score of 1432, DeepSeek V4 Flash 0423 clears OptimNow's Standard working quality threshold: Standard (Arena 1420+), used for meeting summary, invoice processing and call summary. Each threshold is a distance below the best ranked model, which scores 1530 on Arena scores as of 8 Nov 2026.
Licence, size and capabilities
DeepSeek V4 Flash 0423 is open source: its weights are published under MIT, 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 284B parameters. Listed capabilities: Text, Reasoning, Agents. Filling its 1M context window once costs $0.09 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 13 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: StreamLake at $0.0826 input / $0.1652 output per 1M tokens, 8% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp8 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $20.65 there against $22.50 at the price we quote, a difference of $1.85 a month. The dearest, Azure, charges 3.2x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| StreamLake | $0.0826 | $0.1652 | fp8 |
| DeepInfra (price we quote) | $0.09 | $0.18 | fp8 |
| GMICloud (price we quote) | $0.091 | $0.182 | fp8 |
| Wafer | $0.12 | $0.17 | mxfp4 |
| Venice | $0.0966 | $0.1925 | not declared |
| Fireworks | $0.105 | $0.21 | not declared |
| SiliconFlow | $0.13 | $0.28 | fp8 |
| Baidu | $0.14 | $0.28 | fp8 |
| AtlasCloud | $0.14 | $0.28 | fp4 |
| Parasail | $0.14 | $0.28 | fp8 |
| Relace | $0.05 | $0.45 | fp4 |
| Mancer 2 | $0.15 | $0.50 | fp8 |
| Azure | $0.21 | $0.56 | not declared |
List prices as published on 2026-11-12, 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. These listings are promotional rates, below the host's standard rate: StreamLake's, 41% off; GMICloud's, 35% off; and Venice's, 30% off.
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 | $16 – $23 |
| Knowledge Q&A | 2,000 / 800 | $22 – $32 |
| Meeting Summary | 10,000 / 1,200 | $104 – $112 |
| Marketing Content | 2,500 / 1,800 | $51 – $55 |
| Coding Task | 3,000 / 2,000 | $52 – $63 |
| Invoice Processing | 1,500 / 600 | $21 – $24 |
| Call Summary | 2,000 / 700 | $29 – $31 |
| Agent Workflow | 6,000 / 3,000 | $78 – $108 |
Price history
DeepSeek V4 Flash 0423 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.0657 input / $0.1313 output per 1M tokens. The price we quote has changed 48 times since then, 4 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-11, was -1.1% on the blended price (30% input, 70% output), to $0.09 input / $0.18 output. Net of all changes, the blended price is +37.1% against 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-11-11 | $0.091 / $0.182 | $0.09 / $0.18 | -1.1% |
| 2026-10-28 | $0.05 / $0.45 | $0.091 / $0.182 | -53.1% (quoted host changed, not a repricing) |
| 2026-10-27 | $0.091 / $0.182 | $0.05 / $0.45 | +113.3% (quoted host changed, not a repricing) |
| 2026-10-14 | $0.05 / $1.28 | $0.091 / $0.182 | -83.0% (quoted host changed, not a repricing) |
| 2026-10-13 | $0.03 / $1.28 | $0.05 / $1.28 | +0.7% |
43 earlier changes are not listed.
Alternatives to DeepSeek V4 Flash 0423
1 of the 4 comparable models below costs less than DeepSeek V4 Flash 0423: Gemma 4 26B A4B undercuts it by 39%, and scores 2 Arena points higher.
- Next cheaper model in the Budget price tier: Ministral 3 8B 2512 (Mistral) at $0.15 blended, 2% less.
- Next more expensive: Solar Mini 4 (upstage) at $0.155 blended, 1% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against DeepSeek V4 Flash 0423.
- GPT-5.6 Luna (OpenAI): $0.20 in / $1.20 out per 1M, Arena ELO 1431 (488% more expensive, 1 ELO point lower)
- Gemma 4 26B A4B (Google): $0.08 in / $0.10 out per 1M, Arena ELO 1434 (39% cheaper, 2 ELO points higher)
- Mistral Large 3 2512 (Mistral): $0.50 in / $1.50 out per 1M, Arena ELO 1429 (684% more expensive, 3 ELO points lower)
- Qwen3.8 27B (Alibaba): $0.15 in / $1.875 out per 1M, Arena ELO 1436 (787% more expensive, 4 ELO points higher)
- Cheapest within 15 Arena points: Gemma 4 26B A4B (Google), 39% cheaper, 2 ELO points higher, out of 44 models in that band.
- Highest Arena ELO within 20% of this price: DeepSeek V4 Flash 0423 itself has the highest score of the 4 models priced within 20% of it.
Other models from DeepSeek
The 8 nearest to DeepSeek V4 Flash 0423 in price, of 13 other DeepSeek models in the catalogue. Prices per 1M tokens, input then output.
- DeepSeek V4 Flash 0731: $0.0434 / $0.30
- DeepSeek V4.1 Flash: $0.022 / $0.40
- DeepSeek V3.2: $0.26 / $0.38
- DeepSeek V3.2 Exp: $0.27 / $0.41
- DeepSeek V4.1 Flash 1017: $0.15 / $0.60
- 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 Flash 0423 pricing
- How much does DeepSeek V4 Flash 0423 cost?
- DeepSeek V4 Flash 0423 costs $0.09 per 1M input tokens and $0.18 per 1M output tokens at DeepInfra, the host whose rate we quote. DeepInfra serves a quantized fp8 build, which is not the same product as the full-precision model. Prices as listed on 2026-11-12.
- Which host is cheapest for DeepSeek V4 Flash 0423?
- Cheapest host: StreamLake at $0.0826 input / $0.1652 output per 1M tokens, 8% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp8 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $20.65 there against $22.50 at the price we quote, a difference of $1.85 a month. The dearest, Azure, charges 3.2x the cheapest. Host rates as listed on 2026-11-12.
- Does DeepSeek V4 Flash 0423 offer batch or cached pricing?
- Yes, for prompt caching only. Cache reads cost $0.018 per 1M tokens, as listed on 2026-11-12. No batch pricing is published.
- What would DeepSeek V4 Flash 0423 cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $23 on DeepSeek V4 Flash 0423 at the list price quoted on 2026-11-12.
- Can DeepSeek V4 Flash 0423 be self-hosted?
- Yes. DeepSeek V4 Flash 0423 is open source: its weights are published under MIT, 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 Flash 0423 changed?
- DeepSeek V4 Flash 0423 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.0657 input / $0.1313 output per 1M tokens. The price we quote has changed 48 times since then, 4 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-11, was -1.1% on the blended price (30% input, 70% output), to $0.09 input / $0.18 output. Net of all changes, the blended price is +37.1% against 2026-08-15.
Its weights are published, which changes what you may run yourself: the cost gap between open weights and proprietary APIs.
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