DeepSeek V3 vs DeepSeek V4 Flash Vision Exp
DeepSeek V3 costs 1.4x less per output token than DeepSeek V4 Flash Vision Exp ($0.9594 vs $1.32 per million). Updated October 22, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.9594
- Coding
- No data
- Overall
- 56.4
- Output $/M
- $1.32
DeepSeek V3 or DeepSeek V4 Flash Vision Exp: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick DeepSeek V3 for output tokens 1.4x cheaper ($0.9594 vs $1.32 per million).
No benchmark has tested both yet. DeepSeek V3 has results on Aider polyglot, SWE-bench Lite and GPQA Diamond (Epoch AI run); DeepSeek V4 Flash Vision Exp on LiveBench coding, AA Coding Index and SciCode. Compare them on price and context instead.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only DeepSeek V4 Flash Vision Exp has a AA Intelligence Index result, 34.8.
Directional only
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Flash Vision Exp has a AA Agentic Index result, 47.5.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V3 has a Design Arena: websites result, 1120.
Directional only
Long documents
Listed context window
DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3
DeepSeek V3 $0.0008, DeepSeek V4 Flash Vision Exp $0.0011 per turn.
List prices
At a glance
- Coding index
- DeepSeek V3 not benchmarked, DeepSeek V4 Flash Vision Exp not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- DeepSeek V3 $0.9594 against DeepSeek V4 Flash Vision Exp $1.32 per million output tokens, 1.4x apart.
- Context window
- DeepSeek V3 takes 164K tokens, DeepSeek V4 Flash Vision Exp 1.05M.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index5 boards measured
| Benchmark | DeepSeek V3 | DeepSeek V4 Flash Vision Exp | Leader |
|---|---|---|---|
| Aider polyglot | 70.2% | Not measured | Only DeepSeek V3 measured |
| SWE-bench Lite | 30.7% | Not measured | Only DeepSeek V3 measured |
| LiveBench coding | Not measured | 37.6% | Only DeepSeek V4 Flash Vision Exp measured |
| AA Coding Index | Not measured | 65.0 | Only DeepSeek V4 Flash Vision Exp measured |
| SciCode | Not measured | 49.7% | Only DeepSeek V4 Flash Vision Exp measured |
| Neither model has a result on the other 34 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | DeepSeek V3 | DeepSeek V4 Flash Vision Exp | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 34.8 | Only DeepSeek V4 Flash Vision Exp measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | DeepSeek V3 | DeepSeek V4 Flash Vision Exp | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 47.5 | Only DeepSeek V4 Flash Vision Exp measured |
| LiveBench research | Not measured | 69.2% | Only DeepSeek V4 Flash Vision Exp measured |
| LiveBench browser | Not measured | 64.0% | Only DeepSeek V4 Flash Vision Exp measured |
| LiveBench long agentic | Not measured | 39.0% | Only DeepSeek V4 Flash Vision Exp measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | DeepSeek V3 | DeepSeek V4 Flash Vision Exp | Leader |
|---|---|---|---|
| LiveBench reasoning | Not measured | 85.4% | Only DeepSeek V4 Flash Vision Exp measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 91.3% | Only DeepSeek V4 Flash Vision Exp measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 34.5% | Only DeepSeek V4 Flash Vision Exp measured |
| GPQA Diamond (Epoch AI run) | 71.2% | Not measured | Only DeepSeek V3 measured |
| Kagi LLM Benchmark | 52.3% | Not measured | Only DeepSeek V3 measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | DeepSeek V3 | DeepSeek V4 Flash Vision Exp | Leader |
|---|---|---|---|
| OTIS Mock AIME | 48.9% | Not measured | Only DeepSeek V3 measured |
| Neither model has a result on the other 12 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards measured
| Benchmark | DeepSeek V3 | DeepSeek V4 Flash Vision Exp | Leader |
|---|---|---|---|
| Design Arena: websites | 1120 | Not measured | Only DeepSeek V3 measured |
| Design Arena: UI components | 1090 | Not measured | Only DeepSeek V3 measured |
| Design Arena: game dev | 1053 | Not measured | Only DeepSeek V3 measured |
| Design Arena: data viz | 1089 | Not measured | Only DeepSeek V3 measured |
| Design Arena: 3D | 1086 | Not measured | Only DeepSeek V3 measured |
| Design Arena: all code categories | 1108 | Not measured | Only DeepSeek V3 measured |
| Design Arena: SVG | 976 | Not measured | Only DeepSeek V3 measured |
| LiveBench design | Not measured | 70.7% | Only DeepSeek V4 Flash Vision Exp measured |
| Neither model has a result on the other 1 board here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | DeepSeek V3 | DeepSeek V4 Flash Vision Exp | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 79.5% | Only DeepSeek V4 Flash Vision Exp measured |
| Long context reasoning (AA-LCR) | Not measured | 81.3% | Only DeepSeek V4 Flash Vision Exp measured |
| DTBench | 62.7% | Not measured | Only DeepSeek V3 measured |
| LMCA | 15.2% | Not measured | Only DeepSeek V3 measured |
| Neither model has a result on the other 42 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
DeepSeek V3 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | DeepSeek V3 | DeepSeek V4 Flash Vision Exp |
|---|---|---|
| Maker | DeepSeek | DeepSeek |
| Weights | Open weights | Open weights |
| Released | December 26, 2024 | August 21, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.2887 | $0.44 |
| Output $/Mtok | $0.9594 | $1.32 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3 better than DeepSeek V4 Flash Vision Exp for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3 for output tokens 1.4x cheaper ($0.9594 vs $1.32 per million).
Which is cheaper, DeepSeek V3 or DeepSeek V4 Flash Vision Exp?
DeepSeek V3 costs $0.2887 per million input tokens and $0.9594 per million output tokens; DeepSeek V4 Flash Vision Exp costs $0.44 and $1.32. Cost per solved task is known for neither of them.
Which has the bigger context window, DeepSeek V3 or DeepSeek V4 Flash Vision Exp?
DeepSeek V4 Flash Vision Exp, with 1.05M tokens against 164K.
Has any benchmark tested both DeepSeek V3 and DeepSeek V4 Flash Vision Exp?
No benchmark has tested both yet. DeepSeek V3 has results on Aider polyglot, SWE-bench Lite and GPQA Diamond (Epoch AI run); DeepSeek V4 Flash Vision Exp on LiveBench coding, AA Coding Index and SciCode. Compare them on price and context instead. Data as of October 22, 2026.