cd /news/artificial-intelligence/deepseek-v4-flash-vision-intelligenc… · home topics artificial-intelligence article
[ARTICLE · art-109855] src=artificialanalysis.ai ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

DeepSeek V4 Flash Vision Intelligence, Performance and Price Analysis

DeepSeek V4 Flash Vision (Reasoning, Max Effort), released by DeepSeek on August 21, 2026, scores 51 on the Artificial Analysis Intelligence Index, well above the median of 17, and is priced at $0.44 per 1M input tokens and $1.32 per 1M output tokens. The model supports text and image input, outputs text, has a 1M token context window, and generates output at 120 tokens per second, faster than the average of 109.

read5 min views8 publishedAug 25, 2026
DeepSeek V4 Flash Vision Intelligence, Performance and Price Analysis
Image: source

Model summary

DeepSeek V4 Flash Vision (Reasoning, Max Effort) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also faster than average, however very verbose. The model supports text and image input, outputs text, and has a 1M tokens context window.

DeepSeek V4 Flash Vision (Reasoning, Max Effort) scores 51 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (median: 17). When evaluating the Intelligence Index, it generated 130M tokens, which is very verbose in comparison to the median of 61M.

Pricing for DeepSeek V4 Flash Vision (Reasoning, Max Effort) is $0.44 per 1M input tokens (expensive, median: $0.25) and $1.32 per 1M output tokens (somewhat expensive, median: $0.91). In total, it cost $235.89 to evaluate DeepSeek V4 Flash Vision (Reasoning, Max Effort) on the Intelligence Index.

At 120 tokens per second, DeepSeek V4 Flash Vision (Reasoning, Max Effort) is faster than average (109).

Reasoning Yes This page shows the reasoning version of this model. A non-reasoning variant may also exist.
Input modality Supports: text and image
Output modality Supports: text
Context window 1M ~1500 A4 pages of size 12 Arial font

Metrics are compared against models of the same class:

  • Non-reasoning models → compared only with other non-reasoning models
  • Reasoning models → compared across both reasoning and non-reasoning
  • Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
  • Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:

  • <$0.15 per 1M tokens

  • $0.15–$1 per 1M tokens

  • $1 per 1M tokens Highlights

Intelligence #

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Intelligence Evaluations

Agentic real-world work tasks, (Elo-500)/2000

[𝜏³-Banking](/evaluations/tau3-banking)Updated

Agentic tool use

Agentic coding & terminal use

Coding

Humanity's Last ExamUpdated Reasoning & knowledge

Scientific reasoning

Physics reasoning

AA-Omniscience AccuracyUpdated Knowledge

1 - hallucination rate

AA-LCRUpdated Long context reasoning

Agentic knowledge work, Elo

Agentic SaaS workflows

Legal agentic work, criterion pass rate

Agentic business operations

Quantitative analysis on spreadsheets & documents

Instruction following

Long-horizon agentic tasks

Kubernetes incident root-cause analysis

Visual reasoning

AA-Omniscience

AA-Omniscience Index

Intelligence Index Comparisons #

Intelligence Index vs. Cost per Intelligence Index Task

Token Use #

Output Tokens per Intelligence Index Task

Cost #

Cost per Intelligence Index Task

Cost to Run Artificial Analysis Intelligence Index

Pricing: Cache Hit, Input, and Output

Context Window #

Context Window

Speed #

Measured by Output Speed (tokens per second)

Output Speed

Time per Intelligence Index Task

Latency #

Measured by Time (seconds) to First Token

Latency: Time To First Answer Token

End-to-End Response Time #

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Frequently Asked Questions #

Common questions about DeepSeek V4 Flash Vision (Reasoning, Max Effort)

DeepSeek V4 Flash Vision (Reasoning, Max Effort) was released on August 21, 2026.

DeepSeek V4 Flash Vision (Reasoning, Max Effort) was created by DeepSeek.

DeepSeek V4 Flash Vision (Reasoning, Max Effort) scores 51 on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 17).

DeepSeek V4 Flash Vision (Reasoning, Max Effort) generates output at 120.0 tokens per second (based on DeepSeek's API), which is above average compared to other reasoning models in a similar price tier (median: 109.0 t/s).

DeepSeek V4 Flash Vision (Reasoning, Max Effort) has a time to first token (TTFT) of 0.91s (based on DeepSeek's API), which is very competitive compared to other reasoning models in a similar price tier (median: 2.00s).

DeepSeek V4 Flash Vision (Reasoning, Max Effort) costs $0.44 per 1M input tokens (at the higher end, median: $0.25) and $1.32 per 1M output tokens (somewhat higher than average, median: $0.91), based on DeepSeek's API.

DeepSeek V4 Flash Vision (Reasoning, Max Effort) costs $0.44 per 1M input tokens and $1.32 per 1M output tokens (based on DeepSeek's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.23 per 1M tokens. Pricing may vary by provider. Compare provider pricing

When evaluated on the Intelligence Index, DeepSeek V4 Flash Vision (Reasoning, Max Effort) generated 130M output tokens, which is at the higher end compared to other reasoning models in a similar price tier (median: 61M).

Yes, DeepSeek V4 Flash Vision (Reasoning, Max Effort) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

DeepSeek V4 Flash Vision (Reasoning, Max Effort) supports text and image input.

DeepSeek V4 Flash Vision (Reasoning, Max Effort) supports text output.

Yes, DeepSeek V4 Flash Vision (Reasoning, Max Effort) supports image input and can analyze, describe, and answer questions about images.

Yes, DeepSeek V4 Flash Vision (Reasoning, Max Effort) is multimodal. It can process text and image input and generate text output.

DeepSeek V4 Flash Vision (Reasoning, Max Effort) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.

No, DeepSeek V4 Flash Vision (Reasoning, Max Effort) is proprietary. The model weights are not publicly available.

DeepSeek V4 Flash Vision (Reasoning, Max Effort) has 284 billion parameters.

DeepSeek V4 Flash Vision (Reasoning, Max Effort) achieves a score of 51 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, DeepSeek V4 Flash Vision (Reasoning, Max Effort) is available via API through 1 provider. [Compare API providers](/models/deepseek-v4-flash-vision/providers)

DeepSeek V4 Flash Vision (Reasoning, Max Effort) is available through 1 API provider. [Compare providers](/models/deepseek-v4-flash-vision/providers)
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @deepseek 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/deepseek-v4-flash-vi…] indexed:0 read:5min 2026-08-25 ·