DeepSeek V4.1 Flash vs DeepSeek V4 Pro
Two open-weight chat models on the same endpoint and API key, so switching between them is a one-word change. Below: what each costs for three realistic workloads, how they differ, and measured speed.
Inference APIs prices are read live from the price list.
- Cost: DeepSeek V4.1 Flash is cheaper in all three workloads, by 70–76%.
- Speed (measured): DeepSeek V4.1 Flash 0.5 s to first token and 152 tok/s; DeepSeek V4 Pro 0.64 s and 121 tok/s.
Side by side
| DeepSeek V4.1 Flash | DeepSeek V4 Pro | |
|---|---|---|
| Served by | Inference APIs | Inference APIs |
| Model author | DeepSeek | DeepSeek |
| Model id | deepseek-ai/DeepSeek-V4.1-Flash | deepseek-ai/DeepSeek-V4-Pro |
| Input price | $0.40 / 1M tokens | $1.72 / 1M tokens |
| Output price | $1.60 / 1M tokens | $5.15 / 1M tokens |
| Context window | 1M tokens | 1M tokens |
| Capabilities | Chat, Reasoning, Tool calling, JSON mode | Chat, Reasoning, Coding, Tool calling, JSON mode |
| Weights | Open | Open |
| Status | Available | Available |
| Limits | No per-minute or per-day request or token caps; usage draws on a prepaid balance | No per-minute or per-day request or token caps; usage draws on a prepaid balance |
| Time to first token | 0.5 s | 0.64 s |
| Output speed | 151.6 tokens / s | 121.4 tokens / s |
What three workloads cost
List prices applied to the same work. The cheaper side of each row is in bold.
| Workload | DeepSeek V4.1 Flash | DeepSeek V4 Pro | Difference |
|---|---|---|---|
| Chat assistant — 10,000 turns of 800 tokens in, 300 out | $8.00 | $29.21 | 73% |
| Long prompts or RAG — 10,000 requests of 8,000 in, 500 out | $40.00 | $163 | 76% |
| Generation-heavy — 10,000 requests of 500 in, 2,000 out | $34.00 | $112 | 70% |
DeepSeek V4.1 Flash is cheaper in all three workloads, by 70–76%. Reasoning models bill their thinking as output tokens, so real output counts run higher than the visible answer; treat the generation-heavy row as a floor for them.
When to choose which
- Time to first token matters: 0.5 s against 0.64 s in our measurement
- Cost is the deciding factor; it is cheaper in every workload above
- You want a DeepSeek model that answers quickly: in our measurement it thought for a few seconds where V4 Flash thought for twenty, and generated almost three times as fast
- You want the newest DeepSeek Flash model with a 1M-token context
- Cost-sensitive volume; V4 Flash is about a ninth of the price
- Hard reasoning and coding tasks where the Flash models fall short
- You want DeepSeek's largest V4 model without sending data to DeepSeek's own API
- Price matters more than raw output speed
Price, context and speed are measurable; answer quality on your task is not something a table can settle. Both take the same request, so the honest test is to run your own prompts through each in the playground.
Measured speed
Medians of three streamed runs on 2026-09-17, public endpoint, a prompt that asks for about 120 words. Time to first token is the first token of any kind, reasoning included; output speed counts every generated token from that point. Reasoning models then think before the visible answer starts: DeepSeek V4.1 Flash began answering after 3.45 s and DeepSeek V4 Pro after 1.25 s at default settings, which you can shorten with the reasoning controls on each model page. Expect ±30% with time of day. Method and raw numbers: speed measurements.
Trying both
Same endpoint, same key. Change one string:
for MODEL in "deepseek-ai/DeepSeek-V4.1-Flash" "deepseek-ai/DeepSeek-V4-Pro"; do
curl -s https://api.inferenceapis.com/v1/chat/completions \
-H "Authorization: Bearer $INFERENCE_API_KEY" -H "Content-Type: application/json" \
-d "{\"model\": \"$MODEL\", \"max_tokens\": 500, \"messages\": [{\"role\": \"user\", \"content\": \"Summarise the plot of Hamlet in two sentences.\"}]}" \
| jq -r '.model, .choices[0].message.content, .usage'
doneFAQ
Which is cheaper, DeepSeek V4.1 Flash or DeepSeek V4 Pro?
DeepSeek V4.1 Flash is cheaper in all three workloads, by 70–76%. The table above uses list prices: DeepSeek V4.1 Flash $0.40 / 1M tokens input, $1.60 / 1M tokens output; DeepSeek V4 Pro $1.72 / 1M tokens input, $5.15 / 1M tokens output.
How do I switch between them?
They are on the same endpoint and key. Change the model field from deepseek-ai/DeepSeek-V4.1-Flash to deepseek-ai/DeepSeek-V4-Pro and nothing else.
Why does DeepSeek V4.1 Flash use more output tokens than the visible answer?
It is a reasoning model: it thinks before it answers and the thinking is billed as output tokens. Budget for that in output-heavy workloads, and set max_tokens to a few hundred or more so the answer is not cut off.
Spotted a price or limit that has changed? Tell us and we will re-check the provider page.