DeepSeek V4 Flash Vision Exp API pricing
DeepSeek · Budget · Apache 2.0 · released 2026-08. Prices in USD per 1 million tokens. Data snapshot: 2026-10-06.
The price we quote for DeepSeek V4 Flash Vision Exp has changed 5 times since 2026-08-23, most recently on 2026-09-29 when the quoted host changed (-51.0%); it is now the 81st cheapest of 143 Budget models. None of its 4 hosts undercuts the price we quote. No Arena score is published for it, so it carries no Efficiency score and cannot hold the FinOps Friendly badge.
- Input: $0.2156 per 1M tokens
- Output: $0.6468 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.0069 per 1M tokens
- Context window: 1M tokens
- Arena ELO: Not published
Market position
On blended price ($0.5174 per 1M tokens at 30% input, 70% output) it is cheaper than 44% of Budget models: 81st cheapest of 143. Across every category it is cheaper than 72% of priced text models in the catalogue: 81st cheapest of 285.
Licence, size and capabilities
DeepSeek V4 Flash Vision Exp 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 parameter count is not published. Listed capabilities: Text, Vision, Reasoning, Agents. Filling its 1M context window once costs $0.2156 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 4 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.
The price we quote is already the cheapest of the 4 hosts: DeepInfra at $0.2156 input / $0.6468 output per 1M tokens. It serves a quantized fp8 build, which is not the same product as the full-precision model. The dearest, Novita, charges 2.0x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| DeepInfra (price we quote) | $0.2156 | $0.6468 | fp8 |
| GMICloud | $0.44 | $1.32 | fp8 |
| SiliconFlow | $0.44 | $1.32 | fp8 |
| Novita | $0.44 | $1.32 | not declared |
List prices as published on 2026-10-06, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown.
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 | $46 – $65 |
| Knowledge Q&A | 2,000 / 800 | $66 – $95 |
| Meeting Summary | 10,000 / 1,200 | $272 – $293 |
| Marketing Content | 2,500 / 1,800 | $160 – $170 |
| Coding Task | 3,000 / 2,000 | $163 – $194 |
| Invoice Processing | 1,500 / 600 | $62 – $71 |
| Call Summary | 2,000 / 700 | $84 – $88 |
| Agent Workflow | 6,000 / 3,000 | $236 – $323 |
Price history
DeepSeek V4 Flash Vision Exp has been in our daily price archive since 2026-08-22. Its price series starts on 2026-08-23 at $0.22 input / $0.66 output per 1M tokens, because the earlier snapshots carried a data error that was corrected afterwards. The price we quote has changed 5 times since then, 2 of them a change of quoted host rather than a repricing. The latest change, on 2026-09-29, was -51.0% on the blended price (30% input, 70% output), to $0.2156 input / $0.6468 output (quoted host changed, not a repricing). Net of all changes, the blended price is -2.0% against 2026-08-23.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-09-29 | $0.44 / $1.32 | $0.2156 / $0.6468 | -51.0% (quoted host changed, not a repricing) |
| 2026-09-28 | $0.2156 / $0.6468 | $0.44 / $1.32 | +104.1% (quoted host changed, not a repricing) |
| 2026-09-27 | $0.22 / $0.66 | $0.2156 / $0.6468 | -2.0% |
| 2026-09-21 | $0.2156 / $0.6468 | $0.22 / $0.66 | +2.0% |
| 2026-09-18 | $0.22 / $0.66 | $0.2156 / $0.6468 | -2.0% |
Alternatives to DeepSeek V4 Flash Vision Exp
- Next cheaper Budget model: Llama 4 Maverick (Meta) at $0.513 blended, 1% less.
- Next more expensive: Qwen3.5-35B-A3B (Alibaba) at $0.549 blended, 6% more.
Other models from DeepSeek
The 8 nearest to DeepSeek V4 Flash Vision Exp in price, of 13 other DeepSeek models in the catalogue. Prices per 1M tokens, input then output.
- DeepSeek V4 Pro 0423: $0.2088 / $0.4176
- DeepSeek V3.2 Exp: $0.27 / $0.41
- DeepSeek V3.2: $0.28 / $0.42
- DeepSeek V3.1: $0.25 / $0.95
- DeepSeek V3.1 Terminus: $0.27 / $1.00
- DeepSeek V3: $0.2574 / $1.0287
- DeepSeek V3 0324: $0.29 / $1.14
- DeepSeek V4 Flash 0423: $0.001 / $1.28
All 14 DeepSeek models and prices
Common questions about DeepSeek V4 Flash Vision Exp pricing
- How much does DeepSeek V4 Flash Vision Exp cost?
- DeepSeek V4 Flash Vision Exp costs $0.2156 per 1M input tokens and $0.6468 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 2026-10-06.
- Which host is cheapest for DeepSeek V4 Flash Vision Exp?
- The price we quote is already the cheapest of the 4 hosts: DeepInfra at $0.2156 input / $0.6468 output per 1M tokens. It serves a quantized fp8 build, which is not the same product as the full-precision model. The dearest, Novita, charges 2.0x the cheapest. Host rates as listed on 2026-10-06.
- Does DeepSeek V4 Flash Vision Exp offer batch or cached pricing?
- Yes, for prompt caching only. Cache reads cost $0.0069 per 1M tokens, as listed on 2026-10-06. No batch pricing is published.
- What would DeepSeek V4 Flash Vision Exp cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $65 on DeepSeek V4 Flash Vision Exp at the list price quoted on 2026-10-06.
- Can DeepSeek V4 Flash Vision Exp be self-hosted?
- Yes. DeepSeek V4 Flash Vision Exp 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 Flash Vision Exp changed?
- DeepSeek V4 Flash Vision Exp has been in our daily price archive since 2026-08-22. Its price series starts on 2026-08-23 at $0.22 input / $0.66 output per 1M tokens, because the earlier snapshots carried a data error that was corrected afterwards. The price we quote has changed 5 times since then, 2 of them a change of quoted host rather than a repricing. The latest change, on 2026-09-29, was -51.0% on the blended price (30% input, 70% output), to $0.2156 input / $0.6468 output (quoted host changed, not a repricing). Net of all changes, the blended price is -2.0% against 2026-08-23.
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