DeepSeek V3 vs DeepSeek V4 Flash 0731
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on September 30, 2026· 217 models
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions.
- Reasoning estimated
- Speed estimated
- Input
- Output
- Context
- 164 K tokens
- Max output
- 16 K
- Input, $ per 1M tokens
- $0.257
- Output, $ per 1M tokens
- $1.03
- Cache read, $ per 1M
- $0.028
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- 12/01/2025
- Knowledge cutoff
- 2025-09
- API id
- deepseek/deepseek-chat
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
- Reasoning estimated
- ▲
- Speed estimated
- ▲
- Input
- Output
- Context
- ▲1 M tokens
- Max output
- ▲944 K
- Input, $ per 1M tokens
- ▲$0.018
- Output, $ per 1M tokens
- ▲$0.320
- Cache read, $ per 1M
- $0.018
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- ▲07/31/2026
- Knowledge cutoff
- 2025-05
- API id
- deepseek/deepseek-v4-flash-0731
Which is the better API choice: DeepSeek V3 vs DeepSeek V4 Flash 0731?
- DeepSeek V4 Flash 0731: cheapest input (93% less than DeepSeek V3)
- DeepSeek V4 Flash 0731: cheapest output
- DeepSeek V4 Flash 0731: largest context (1 M)
- DeepSeek V4 Flash 0731: the newest (07/31/2026)
- DeepSeek V4 Flash 0731: most reasoning (estimated)
- DeepSeek V4 Flash 0731: the fastest (estimated)
DeepSeek V4 Flash 0731 costs 93% less on input and 69% less on output than DeepSeek V3 ($0.018 / $0.320 versus $0.257 / $1.03 per million tokens). DeepSeek V4 Flash 0731 accepts more context (1 M). On capabilities, DeepSeek V4 Flash 0731 has a reasoning mode.
What would your product cost?
Estimate the monthly cost with your app's real volume. List prices, no cache or batch discounts.
With DeepSeek V4 Flash 0731 you save $6.43 a month versus DeepSeek V3 (81% less).
The 6 cheapest for this scenario (chat, last 12 months)
- 1Lyria 3 Pro Preview Google$0.00
- 2Lyria 3 Clip Preview Google$0.00
- 3Qwen3.7 Flash Qwen$0.97
- 4DeepSeek V4 Flash 0731 DeepSeek$1.55
- 5Ministral 3 3B 2512 Mistral$1.90
- 6Qwen3.5-Flash Qwen$2.02
Paste your prompt: tokens and cost per model
Rough estimate (about 4 characters per token). Nothing is sent to any server.
Cost of sending it 1,000 times (input only)
- 1DeepSeek V4 Flash 0731 DeepSeek$0.001
- 2DeepSeek V3 DeepSeek$0.020
- 3Claude Sonnet 5.5 Anthropic$0.152
- 4Claude Sonnet 5 Anthropic$0.152
- 5Claude Opus 5.5 Anthropic$0.304
- 6Claude Opus 5 Anthropic$0.380
- 7Claude Fable 5.1 Anthropic$0.760
- 8Claude Fable 5 Anthropic$0.760
Popular comparisons
- Claude Sonnet 5.5 vs GPT-6.1 Sol
- Claude Sonnet 5.5 vs Gemini 3.8 Flash
- Claude Sonnet 5.5 vs DeepSeek V4.1 Flash
- Claude Sonnet 5.5 vs Grok 4.7
- GPT-6.1 Sol vs Gemini 3.8 Flash
- GPT-6.1 Sol vs DeepSeek V4.1 Flash
- GPT-6.1 Sol vs Grok 4.7
- Gemini 3.8 Flash vs DeepSeek V4.1 Flash
- Gemini 3.8 Flash vs Grok 4.7
- DeepSeek V4.1 Flash vs Grok 4.7
Frequently asked questions
Which is the better API choice: DeepSeek V3 vs DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 costs 93% less on input and 69% less on output than DeepSeek V3 ($0.018 / $0.320 versus $0.257 / $1.03 per million tokens). DeepSeek V4 Flash 0731 accepts more context (1 M). On capabilities, DeepSeek V4 Flash 0731 has a reasoning mode.
Which is cheaper: DeepSeek V3 and DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 is cheaper: $0.018 per million input tokens and $0.320 per million output tokens, versus $0.257 / $1.03 for DeepSeek V3.
Which has more context: DeepSeek V3 and DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 accepts 1 M tokens of context; DeepSeek V3 accepts 164 K.
Which is newer: DeepSeek V3 and DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 was released on 07/31/2026; DeepSeek V3 on 12/01/2025.
What would 10,000 requests a month cost with DeepSeek V3 and DeepSeek V4 Flash 0731?
With 1,500 input and 400 output tokens per request: DeepSeek V3: $7.98; DeepSeek V4 Flash 0731: $1.55 a month, at list price.
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.