Model comparison
DeepSeek V4 Flash vs DeepSeek V4 Pro
Price history, scores and specs for both models, line by line. Every value shows where it came from and when we last confirmed it.
Accounts
DeepSeek V4 Flash
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work.
Accounts
DeepSeek V4 Pro
Open MoE flagship with million-token context for coding and long agent runs.
Quick take
Where each one leads
- DeepSeek V4 Flash costs less to send text to: $0.090 per million tokens, against $0.887 per million tokens for DeepSeek V4 Pro.
- DeepSeek V4 Flash costs less per word it writes: $0.180 per million tokens, against $1.77 per million tokens for DeepSeek V4 Pro.
- DeepSeek V4 Flash scores higher on the Artificial Analysis Intelligence Index: 24.4 to 12.6.
- DeepSeek V4 Pro scores higher on the Artificial Analysis Coding Index: 59.4 to 56.2.
- More people run DeepSeek V4 Flash through OpenRouter than DeepSeek V4 Pro right now.
Each line comes from a checked value in the tables below. Pick on your workload: price and usage matter for high volume, context and scores for long documents and agent loops.
Price history
Prices side by side, day by day
- DeepSeek V4 Flash
- DeepSeek V4 Pro
- DeepSeek V4 Flash
- DeepSeek V4 Pro
Prices are the listed OpenRouter base rates in US dollars. A day we could not confirm is left out of the line, never filled in.
Price
What each one costs now
| Measure | DeepSeek V4 Flash | DeepSeek V4 Pro |
|---|---|---|
| Input price | $0.090 per million tokens Leads | $0.887 per million tokens |
| Output price | $0.180 per million tokens Leads | $1.77 per million tokens |
Scores
Benchmarks, with source and date
| Measure | DeepSeek V4 Flash | DeepSeek V4 Pro |
|---|---|---|
| Artificial Analysis Intelligence Index | 24.4 Leads | 12.6 |
| Artificial Analysis Coding Index | 56.2 | 59.4 Leads |
| Artificial Analysis Agentic Index | 26.3 | 26.3 |
| Design Arena rating (Elo) | 1,204 | 1,239 Leads |
Specs
Context, modalities and tool use
| Measure | DeepSeek V4 Flash | DeepSeek V4 Pro |
|---|---|---|
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Reads | Text | Text |
| Writes | Text | Text |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
| Open weights | Yes | Yes |
| Listed since | 24 Apr 2026 | 24 Apr 2026 |
Usage
How much each one is used
| Measure | DeepSeek V4 Flash | DeepSeek V4 Pro |
|---|---|---|
| Tokens served on OpenRouter in a day | 335.4B Leads (for 10 Nov 2026) | 90.6B (for 10 Nov 2026) |
| Requests on OpenRouter in a day | 47.7M Leads (for 10 Nov 2026) | 3.4M (for 10 Nov 2026) |
| Tool calls on OpenRouter in a day | 5.7M Leads (for 10 Nov 2026) | 861.6K (for 10 Nov 2026) |
| Token usage, last 7 days | Down 11% on the week before (for 10 Nov 2026) | Down 6% on the week before Leads (for 10 Nov 2026) |
- DeepSeek V4 Flash
- DeepSeek V4 Pro
How this works
One link, either order
This link stays the same whichever order you name the two models in, so you can share it as it is. A line appears only when at least one model has a value we confirmed from a source; values we have not confirmed are left out, never guessed. To add a third record of any type, use the open comparison. Read how we check facts.