Model comparisons
DeepSeek V4 Flash bills 66% less than DeepSeek V4 Pro per million output tokens. Tier prices, request fields and limits side by side.
DeepSeek V4 Flash chat through an OpenAI-compatible endpoint. It takes up to 1,048,576 tokens of text and returns up to 65,536, with low or high reasoning effort, up to 128 tool definitions, JSON response format and SSE streaming.
View model details →View sample outputs →DeepSeek V4 Pro chat through an OpenAI-compatible endpoint. It takes up to 1,048,576 tokens of text and returns up to 384,000, with low or high reasoning effort (high by default), up to 128 tool definitions and JSON response format.
View model details →View sample outputs →Compare
Start with the input you have, the result you want and your budget. These are the differences that affect that choice.
Compare the published examples, then try the same input on both models with matching settings.
The Spicy Index and Freedom Score for both models, from the same daily calculation as the leaderboards.
| Measure | DeepSeek V4 Flash | DeepSeek V4 Pro |
|---|---|---|
| Spicy Index | 76.3 | 79.0 |
| Freedom Score | 88.9 | 88.6 |
| Evidence | Tested 5 of 5 probe types · 24 runs | Tested 5 of 5 probe types · 22 runs |
| Range if the rest pass | 88.9–88.9 | 88.6–88.6 |
| Price | $0.66 per 1M mixed tokens (3 input : 1 output) | $1.98 per 1M mixed tokens (3 input : 1 output) |
| Reviews | Read the DeepSeek V4 Flash review | Read the DeepSeek V4 Pro review |
Current price
A start price answers a different question than the one you have. These are the tiers both models publish, matched setting for setting, in US dollars per billed unit with no conversion step in between.
Swipe horizontally to compare all fields.
| Tier | DeepSeek V4 Flash | DeepSeek V4 Pro | Difference |
|---|---|---|---|
| Input | $0.44 / 1 million tokens | $1.32 / 1 million tokens | DeepSeek V4 Flash −66% |
| Cached input | $0.014 / 1 million tokens | $0.044 / 1 million tokens | DeepSeek V4 Flash −68% |
| Output | $1.32 / 1 million tokens | $3.96 / 1 million tokens | DeepSeek V4 Flash −66% |
Arithmetic on the published rates at each model's own default setting, not a quote. The console prices your actual settings before a request is accepted.
About this comparison
Every row here is read from the JSON Schema the endpoint validates against, so it matches what the API will really accept rather than a feature list written by hand.
Swipe horizontally to compare all fields.
| Controls and limits | DeepSeek V4 Flash | DeepSeek V4 Pro |
|---|---|---|
| Supported tasks | chat | chat |
| Input context | 1,048,576 tokens | 1,048,576 tokens |
| Maximum output | 65,536 tokens | 384,000 tokens |
| Tool calling | Yes | Yes |
| Execution | Synchronous, with streaming | Synchronous, with streaming |
| Request timeout | 60 minutes | 60 minutes |
| Availability | Live | Live |
Do low-filter models allow every request?
Two separate facts sit behind these labels. The first is what we do, which is nothing: no platform content filter, and no maturity flag to set on a request. The second is what each model does on its own, and that is the only part that varies between these two.
DeepSeek V4 Flash
We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.
Usage note Submit only material you are authorized to handle. Do not use it to invade privacy, impersonate a real person, or create sexual content involving minors.
DeepSeek V4 Pro
We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.
Usage note Use only authorized material. Do not invade privacy, impersonate a real person, or create sexual content involving minors.
Use these content labels to shortlist models, then open each model page for available examples and content-test details.
The label never changes your obligations. Age, consent, real-person likeness and the law where you operate stay with you, and SpicyAPI does not inspect each request.
Can I swap the model ID without changing the request body?
The task lifecycle is shared; the body is not. Each endpoint publishes its own JSON Schema and the API validates against that, so this is the list to reconcile before a switch.
How to choose
DeepSeek V4 Pro can return more in one reply: up to 384,000 tokens against the other model's ceiling.
Compare
The model identifiers are deepseek/v4-flash/chat and deepseek/v4-pro/chat, and both go in the same field of the same request.
Both return the response on the chat request. With streaming enabled, read the stream until it finishes; there is no media task to poll.
Both use the same submit-and-track flow, but their required inputs may differ. Check each model page before switching.
One key, one balance, one set of spend caps. Both bill to the same account in US dollars, and the per-key daily, monthly and lifetime limits apply to whichever one you call.
Questions developers ask
DeepSeek V4 Flash costs 66% less per million output tokens. Compare the input and cache rates below for longer conversations. Prices may change; check the estimate shown for your actual settings before submitting.
DeepSeek V4 Flash allows 60 minutes per task and DeepSeek V4 Pro allows 60. Those are ceilings rather than typical times — most requests finish far sooner — but they are what your own client timeout has to survive.
Prices and capabilities shown here come from the current public model catalogue. Check each model page for its latest inputs and examples.
Related comparisons