DeepSeek · Released Apr 24, 2026DeepSeek V4 Flash
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work.
- Capability
- 146.1ECI · #71 of 148
- Input
- $0.14per 1M tokens
- Output
- $0.28per 1M tokens
- Context
- 1M384K max output
What it costs
- Input
- $0.14per million tokens
- Output
- $0.28per million tokens
- Blended (3:1)
- $0.175cheaper than 79% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.42 |
| Team assistant25M input + 5M output tokens | $4.90 |
| Production app250M input + 50M output tokens | $49.00 |
Median of 42 paid API providers on models.dev.
Independent benchmarks
#71 of 148 scored models
The shaded band is Epoch AI’s confidence range (143.6–147.9); the tick marks the median scored model.
Scores from Epoch AI, run independently of DeepSeek.
The details
- Lab
- DeepSeek
- Released
- Apr 24, 2026
- Knowledge cutoff
- May 2025
- Context window
- 1,000,000 tokens
- Max output
- 384,000 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- Always on
- Tool calling
- Yes
- Structured output
- Yes
- Weights
- Open weights
- Availability
- 48 API providerslisted on models.dev
What DeepSeek claims
Published by the lab at launch. Settings vary, so compare these only with care.
| Benchmark | Score | Setting | Source |
|---|---|---|---|
| SWE-Bench Verified | 79 resolved | — | Source |
| MMLU-Pro | 86.2 EM | preview checkpoint; max effort | Source |
| SimpleQA-Verified | 34.1 | preview checkpoint; max effort | Source |
| Chinese SimpleQA | 78.9 | preview checkpoint; max effort | Source |
| GPQA Diamond | 88.1 | preview checkpoint; max effort | Source |
| Humanity's Last Exam | 34.8 | preview checkpoint; max effort; without tools | Source |
| LiveCodeBench | 91.6 | preview checkpoint; max effort | Source |
| Codeforces | 3052 rating | preview checkpoint; max effort | Source |
| HMMT | 94.8 | preview checkpoint; max effort | Source |
| IMOAnswerBench | 88.4 | preview checkpoint; max effort | Source |
| MathArena Apex | 33 | preview checkpoint; max effort | Source |
| MathArena Apex Shortlist | 85.7 | preview checkpoint; max effort | Source |
More from DeepSeek
About DeepSeek V4 Flash
How much does DeepSeek V4 Flash cost?
DeepSeek V4 Flash costs $0.14 input / $0.28 output per million tokens (median across 42 API providers). At a 3:1 input-to-output mix that is $0.175 per million tokens, cheaper than 79% of the 360 priced models we track.
What is the context window of DeepSeek V4 Flash?
DeepSeek V4 Flash accepts up to 1,000,000 tokens per request and can write up to 384,000 tokens in one response.
How good is DeepSeek V4 Flash?
Epoch AI gives DeepSeek V4 Flash a Capabilities Index score of 146.1 (likely range 143.6–147.9), ranking it #71 of 148 models Epoch has scored.
Is DeepSeek V4 Flash open source?
Yes. DeepSeek publishes the weights, so it can be downloaded and self-hosted.
What inputs does DeepSeek V4 Flash support?
DeepSeek V4 Flash accepts text and replies in text. It is a reasoning model, supports tool calling and can return structured JSON output.
When was DeepSeek V4 Flash released?
DeepSeek released DeepSeek V4 Flash on Apr 24, 2026. Its training data runs to May 2025.
What are the best alternatives to DeepSeek V4 Flash?
The closest current models from other labs on capability, price and release date are Qwen3.5 Flash (Alibaba (Qwen), ECI 144.0, $0.10 / $0.40), Gemma 4 31B IT (Google, ECI 142.8, $0.14 / $0.40), GPT-5.4 nano (OpenAI, ECI 145.8, $0.20 / $1.25) and MiniMax-M2.7 (MiniMax, ECI 145.9, $0.30 / $1.20).