DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Flash is a text model from DeepSeek. The snapshot records a release date of 2026-04. Context window: 1M tokens. Maximum output: 384K tokens. Input: text. Output: text. Capabilities recorded: reasoning, tool calls, open weights.
Directory snapshot 2026-10-26 · Chinese dossier: 完整中文页
Official list price
CNY / 1M TOKENSOfficial list price in the directory snapshot: ¥1 input and ¥2 output per 1M tokens, in CNY. Relay prices below are what individual sites listed; they can be lower or higher, and they are not official prices.
Relay coverage
24 SITES24 sites in our public directory listed this model ID in the 2026-10-26 snapshot. Listed relay price range: ¥0.046691–¥1 per 1M input tokens. A listing means the model appeared on the site's public model list; it is not proof that the site serves the genuine model.
| Site | Domain | Relay price / 1M | Verification |
|---|---|---|---|
| A6api | a6api.com | ¥0.046691 | enterprise |
| 灵算 | lingsuan.si | ¥0.1 | enterprise |
| 木易(MueMod) | muemod.top | ¥0.1 | enterprise |
| CodeKey | codekey.ai | ¥0.14–¥0.3 | personal |
| 9527code | 9527.codes | ¥0.15–¥0.9 | enterprise |
| 银河算力实验室 | inai.top | ¥0.15 | enterprise |
| LinoRoute | linoroute.com | ¥0.18–¥0.45 | personal |
| MX-AI | mxzzz.xyz | ¥0.3–¥0.6 | enterprise |
| HubCore | hubcore.cn | ¥0.3 | enterprise |
| DragonAPI | newapi.dragon3api.com | ¥0.3 | enterprise |
| Token-AI | tken.lol | ¥0.3–¥0.5 | enterprise |
| 模方 | api.modelscube.com | ¥0.308 | personal |
| OmniaKey | omniakey.com | ¥0.335822 | enterprise |
| FluxToken | fluxtoken.ai | ¥0.36 | enterprise |
| 镜核 AI | ai.17nas.com | ¥0.38–¥0.5 | — |
| 天天中转站 | apitiantian.com | ¥0.4 | enterprise |
| Volt | voltapi.ai | ¥0.4 | personal |
| Aivoza | aivoza.com | ¥0.4 | — |
| MuskAI | api.muskapi.cc | ¥0.43 | enterprise |
| niccom | niccom.com.cn | ¥0.45 | enterprise |
| 8sToken | 8stoken.com | ¥0.5 | enterprise |
| PackyCode | packyapi.ai | ¥0.5 | enterprise |
| Token 88 | t8api.com | ¥0.5 | enterprise |
| API快连 | apikl.ai | ¥0.5–¥1 | enterprise |
How to verify this model on a relay
THREE STEPS- Send a short request to the relay and read the
modelfield in the response. It must match the ID you sent; a different ID is a mapping, not necessarily a substitution. - Run the same prompt against a known-good endpoint and compare prompt-token counts. A large, repeatable gap points at a different tokenizer or a different backend.
- Run the seven checks. Billing, context retention, error shape, parameter compliance, tools, and streaming each produce evidence you can quote.
Same publisher
DeepSeekQuestions
FAQWhat is the context window of DeepSeek V4 Flash?
The snapshot records 1,000,000 tokens.
How much does DeepSeek V4 Flash cost?
Official list price: ¥1 input / ¥2 output per 1M tokens in CNY, per the directory snapshot. 24 relay sites listed it at ¥0.046691–¥1 per 1M input tokens.
Is a relay really serving DeepSeek V4 Flash?
A model ID in a response is not proof. The seven-check detection compares tokenizer ratios, billing, error shape, parameter compliance, tools, and streaming against the advertised family. Run it on a key you can afford to spend, and treat one run as a spot check, not 24/7 monitoring.
Specifications and prices come from the 2026-10-26 public directory snapshot. We do not publish IQ scores or structured-output claims for models where we have no reliable data.