DeepSeek model product
DeepSeek-V4-Flash
DeepSeek-V4-Flash is an experimental multimodal model that accepts text and image inputs and produces text.
Updated Oct 23, 2026. Default version: DeepSeek-V4-Flash-Vision-Exp
LLMBoard Score71.9DeepSeek-V4-Flash-Vision-Exp
Coverage20%7 benchmark families
Context window1MTokens
Official input price$0.15DeepSeek API
DeepSeek-V4-Flash Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
DeepSeek-V4-Flash Benchmark Results
Benchmark scores for DeepSeek-V4-Flash-Vision-Exp.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkDSBench-Hard | Score63.60% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkZEROBench | Score0.35 points | Rank06 | Participants15 | Percentile64.29% | EvidenceC | Evaluated |
| BenchmarkDeepSWE | Score59.30% | Rank07 | Participants13 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkNL2Repo | Score57.70% | Rank07 | Participants25 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score83.90% | Rank17 | Participants48 | Percentile65.96% | EvidenceC | Evaluated |
| BenchmarkAgents' Last Exam | Score27.30% | Rank19 | Participants24 | Percentile21.74% | EvidenceC | Evaluated |
| BenchmarkLiveBench instruction (2026-06-25) | Score70.96 score | Rank20 | Participants43 | Percentile54.76% | EvidenceB | EvaluatedN/A |
| BenchmarkAutomationBench | Score25.70% | Rank21 | Participants27 | Percentile23.08% | EvidenceC | Evaluated |
| BenchmarkLiveBench reasoning (2026-06-25) | Score85.40 score | Rank21 | Participants43 | Percentile52.38% | EvidenceB | EvaluatedN/A |
| BenchmarkLiveBench math (2026-06-25) | Score87.81 score | Rank26 | Participants43 | Percentile40.48% | EvidenceB | EvaluatedN/A |
DeepSeek-V4-Flash Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
DeepSeek-V4-Flash Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.15 input, $0.60 output per 1M
- Official provider
- DeepSeek
- Lowest third-party
- From $0.14 input, $0.28 output per 1M via OpenCode
- Tracked offerings
- 18
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAMD | Provider model IDDeepSeek-V4-Flash-Vision-Exp | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderOpenCode | Provider model IDdeepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderDeepSeek | Provider model IDdeepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| ProviderEden AI | Provider model IDdeepseek/deepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| ProviderEden AI | Provider model IDdeepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| ProviderCommandCode | Provider model IDdeepseek/deepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDdeepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.155 | Output / 1M$0.62 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDdeepseek/deepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.2156 | Output / 1M$0.6468 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDdeepseek/deepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.2156 | Output / 1M$0.6468 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDdeepseek/deepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.2156 | Output / 1M$0.6468 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDdeepseek/deepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.2156 | Output / 1M$0.6468 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDdeepseek/deepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.22 | Output / 1M$0.66 | Context1M | Updated |
| ProviderCrossModel | Provider model IDdeepseek/deepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context1M | Updated |
| ProviderOfox | Provider model IDdeepseek/deepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.44 | Output / 1M$1.32 | Context1M | Updated |
| ProviderDeep Infra | Provider model IDdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp | Regionglobal | Input / 1M$0.44 | Output / 1M$1.32 | Context1M | Updated |
| ProviderHugging Face | Provider model IDdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp | Regionglobal | Input / 1M$0.44 | Output / 1M$1.32 | Context1M | Updated |
| ProviderSiliconFlow | Provider model IDdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp | Regionglobal | Input / 1M$0.44 | Output / 1M$1.32 | Context1M | Updated |
| ProviderAI/ML API | Provider model IDdeepseek/deepseek-v4-flash-vision-exp | Regionglobal | Input / 1M$0.44 | Output / 1M$1.32 | Context1M | Updated |
DeepSeek-V4-Flash Runtime Performance
Provider-specific output speed and catalog latency for DeepSeek-V4-Flash-Vision-Exp. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
DeepSeek-V4-Flash Specifications
Technical details for the model's default version.
- Version
- DeepSeek-V4-Flash-Vision-Exp
- Released
- Aug 21, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 1M
- Max output
- 1M
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Unknown
DeepSeek-V4-Flash Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionDeepSeek-V4-Flash-Vision-Exp | Released | LLMBoard71.90 | ParametersN/A | Context1M | Max output1M | Open weightsNo | LicenseUnknown |
| VersionDeepSeek-V4-Flash-0731 | Released | LLMBoardN/A | Parameters304B | Context1M | Max output1M | Open weightsYes | LicenseMIT |
| VersionDeepSeek-V4-Flash-0423 | Released | LLMBoardN/A | Parameters284B | Context1M | Max output1M | Open weightsYes | LicenseMIT |
| VersionDeepSeek-V4-Flash-Max | Released | LLMBoardN/A | Parameters284B | Context1M | Max output1M | Open weightsYes | LicenseMIT |
Models similar to DeepSeek-V4-Flash
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
DE
DeepSeek-V4-Pro
DeepSeek
DE
DeepSeek-V4.1
DeepSeek
DE
DeepSeek-V3.2
DeepSeek
DE
DeepSeek-R1
DeepSeek
DE
DeepSeek-V3.1
DeepSeek
DE
DeepSeek-V3
DeepSeek
What is DeepSeek-V4-Flash?
Key information about DeepSeek-V4-Flash and its available data.
DeepSeek-V4-Flash-Vision-Exp is an experimental vision-understanding model available through the DeepSeek API as `deepseek-v4-flash-vision-exp`. It supports text and image inputs, text output, thinking mode, JSON output, tool calls, the Responses API, and the Anthropic API.
Data as of 2026-10-22.
FAQ
Common questions about DeepSeek-V4-Flash.
When was DeepSeek-V4-Flash released?
DeepSeek-V4-Flash's default version was released on Aug 21, 2026.
How much does DeepSeek-V4-Flash cost?
DeepSeek-V4-Flash's official API price is $0.15 per million input tokens and $0.60 per million output tokens via DeepSeek. The lowest tracked third-party offer starts at $0.14 input and $0.28 output via OpenCode.
Who created DeepSeek-V4-Flash?
DeepSeek-V4-Flash was created by DeepSeek.
What is the context window for DeepSeek-V4-Flash?
The default version has a 1M token context window.
Is DeepSeek-V4-Flash open weight?
No. The default version is not marked as having publicly available weights.