The High-Efficiency Technical Specialist
DeepSeek V4 combines a one-million-token context, thinking and non-thinking modes, open weights and unusually low API prices. It is a serious engineering option—but choosing it means making explicit decisions about hosting, data jurisdiction, evaluation and operational ownership.
Strong capability per dollar, with a different operating model
DeepSeek should be evaluated as infrastructure, not as a cheaper consumer chatbot. Its value depends on task routing, deployment choice, model evaluation and whether the organization can manage the distinct legal and operational context.
Technical, efficient and configurable
DeepSeek is designed for teams comfortable choosing modes, APIs, weights and deployment architecture rather than relying on a single polished end-user product.
- Thinking and non-thinking modes
- Agent and coding orientation
- Open weights and hosted API
High-volume technical work
Coding, tool use, document processing, long-context analysis and workloads where token economics change the business case.
- Route simple work to Flash
- Use Pro for harder cases
- Exploit caching and concurrency
Control and economics justify ownership
Use it when your team can evaluate quality, design safeguards and operate the provider or self-hosted path responsibly.
- Benchmark on your own tasks
- Resolve data and jurisdiction questions
- Budget for model operations
V4-Pro and V4-Flash are the only models left
DeepSeek V4 is live through the hosted API and open-weight release. The legacy alias retirement executed on schedule: as of August 3, 2026 the pricing page no longer carries the deprecation notice, and neither `deepseek-chat` nor `deepseek-reasoner` appears on it. Only `deepseek-v4-flash` and `deepseek-v4-pro` are listed. Prices are unchanged since July 27 — but the pricing page now carries a pending peak-hours policy that doubles every billing item.
DeepSeek V4-Flash Efficient default
Thinking and non-thinking modes, designed for speed, economics and simple agent work. The April 24 news entry described the preview as 284B total and 13B active params; DeepSeek’s weights channel now states 304B params for the `DeepSeek-V4-Flash-0731` release. The parameter count moved on DeepSeek’s own two channels.
- `deepseek-v4-flash`
- 1M context
- 2,500 listed concurrency
DeepSeek V4-Pro Higher capability
A 1.6T-total, 49B-active model for stronger reasoning, coding, knowledge and agentic work.
- `deepseek-v4-pro`
- 1M context
- 500 listed concurrency
Dual API formats
The hosted service exposes an OpenAI-compatible endpoint at `https://api.deepseek.com` and an Anthropic-compatible endpoint at `https://api.deepseek.com/anthropic`, which auto-maps Claude model names: Opus to `deepseek-v4-pro`, Sonnet and Haiku to `deepseek-v4-flash`, and anything unmapped to `deepseek-v4-flash`.
- Lower migration friction
- Explicit base URLs
- Auto-mapping means an unrecognized name silently lands on Flash
Thinking control
Both models support thinking and non-thinking modes, selected with `{"thinking": {"type": "enabled"}}` or `"disabled"` in `extra_body`. Thinking is enabled by default, and `reasoning_effort` accepts "high" or "max".
- Thinking is the default, so opt out deliberately
- Use non-thinking for simple throughput
- High and max effort options
Open weights Released
DeepSeek published V4 weight collections and technical material, enabling self-managed deployment and research.
- Hosting control
- Model operations responsibility
- Hardware and quantization planning
Legacy aliases: retired Executed
DeepSeek retired `deepseek-chat` and `deepseek-reasoner` on schedule at 2026/07/24 15:59 UTC. The pricing page no longer carries the deprecation notice and neither alias appears anywhere on it. Anyone still sending those model strings is calling a dead API — migrate to `deepseek-v4-flash` or `deepseek-v4-pro`.
- Pin explicit V4 IDs
- Update tests and configuration
- Legacy strings now fail rather than degrade
Peak-hours pricing is pending Announced, undated
The pricing page states: “The DeepSeek API service will soon adopt a peak/off-peak pricing policy. During peak hours, prices will be 2x the regular prices, applicable to all billing items. The effective date will be subject to the official announcement.” Peak hours are stated as “9:00–12:00 and 14:00–18:00 (Beijing Time, UTC+8) daily.” No effective date is published, so every price below can double without further warning.
- 2x on all billing items during peak
- Seven peak hours per day, Beijing time
- Effective date not yet announced
A build DeepSeek did not announce Partly unconfirmed
DeepSeek published `DeepSeek-V4-Flash-0731` on its own weights channel, stating 304B params and that it “is the official release of DeepSeek-V4-Flash, superseding the preview version.” There is no change-log entry after 2026/04/24 recording this. It is not confirmed that the hosted `deepseek-v4-flash` endpoint now serves the 0731 build — no DeepSeek docs page mentions “0731,” and the release date is a build string, not a stated date.
- Supersession is documented
- API-serving is inferred, not stated
- No change-log entry exists for it
Responses API coverage
DeepSeek states: “The Responses API currently only supports the `deepseek-v4-flash` model, and does not yet support the `deepseek-v4-pro` model. We will add support for the `deepseek-v4-pro` model in early August 2026.” Treat Pro support as pending, not shipped.
- Flash only, today
- Pro support promised for early August 2026
- Do not scope a Pro Responses integration on the promise
| Model | Listed input: cache hit | Input: cache miss | Output | Concurrency |
|---|---|---|---|---|
| V4-Flash | $0.0028 / 1M | $0.14 / 1M | $0.28 / 1M | 2,500 |
| V4-Pro | $0.003625 / 1M | $0.435 / 1M | $0.87 / 1M | 500 |
Use the least expensive mode that meets the task’s failure cost
DeepSeek’s product design rewards routing. Flash versus Pro and thinking versus non-thinking should be an evaluated policy, not a user preference.
Run this task suite on V4-Flash non-thinking, V4-Flash thinking and V4-Pro thinking. Compare exact-task success, latency, output tokens, retries and human correction time. Recommend a routing policy.
Complete this repository task with a maximum of 12 tool steps. Stop before any external network or deployment action. Report tests, files changed and unresolved risk.
Hosted API and open weights solve different problems
Open weights improve control but do not remove cost. They replace per-token pricing with infrastructure, model serving, security, monitoring and lifecycle work.
| Dimension | Hosted API | Self-managed weights |
|---|---|---|
| Time to start | Fast | Infrastructure project |
| Variable cost | Published token pricing | Compute, staffing and utilization |
| Data control | Provider architecture and terms | Organization controls environment |
| Scaling | Provider-managed within limits | Organization provisions capacity |
| Model updates | Provider-led | Organization tests and deploys |
| Observability | API-level signals | Full stack if implemented |
| Operational burden | Lower | Higher |
Context caching
Repeated prefixes can reduce input cost dramatically, making prompt architecture part of the economics.
- Keep stable instructions stable
- Measure actual cache hit rate
- Do not assume every request qualifies
User isolation
The API supports a user identifier for content-safety, KV-cache and scheduling isolation.
- Do not place personal data in the identifier
- Use stable internal pseudonyms
- Understand account-level limits
Concurrency planning
Published account-level limits differ between Pro and Flash and can create throughput architecture decisions.
- Model peak demand
- Handle 429 responses
- Request capacity expansion when justified
Thinking inside tool use is useful—and needs hard boundaries
DeepSeek’s agent direction began with V3.2 and continues with V4. The operational risk is an efficient model taking many inexpensive wrong steps before anyone notices.
Research this technical decision using only the supplied documentation and approved web domains. Maximum 10 tool calls. Cite every conclusion and stop if the sources conflict.
Implement the change, run the tests and inspect the diff. Maximum 15 tool steps. Do not modify deployment, credentials or network configuration. If blocked, report the exact evidence.
Return the result as the required JSON schema, then run an independent validation pass that checks completeness, allowed values and source coverage.
After two verification passes, commit to the strongest supported answer. Do not continue rechecking unless new evidence appears.
Eight habits for extracting the economic advantage safely
DeepSeek rewards engineering discipline: explicit routing, structured outputs, hard agent limits and evaluation on the organization’s real tasks.
Pin explicit V4 IDs
The retirement executed at 2026/07/24 15:59 UTC. `deepseek-chat` and `deepseek-reasoner` are gone; any call still using them is hitting a dead API. Send `deepseek-v4-flash` or `deepseek-v4-pro`.
Route by task
Flash for throughput; Pro when measured quality gains justify it.
Use non-thinking deliberately
Do not pay reasoning latency for transformations that schemas can validate.
Exploit stable prefixes
Design repeated context to benefit from caching without hiding changing instructions.
Set hard agent limits
Maximum steps, budget, tools and stop conditions belong in the task contract.
Evaluate cultural and political domains
Test behavior on topics relevant to your users and markets, not only code benchmarks.
Separate hosted and self-managed risk
The same model can create different legal and security profiles by deployment.
Measure correction cost
Include retries and human review when comparing providers.
The risk profile belongs in the architecture decision
Technical capability does not answer questions about jurisdiction, hosted-service data handling, political behavior, licensing or operational responsibility.
Data jurisdiction
Hosted API use may not meet every sovereignty, contractual or regulatory requirement.
Political sensitivity
Evaluate behavior on politically sensitive and culturally specific topics relevant to your markets.
Provider concentration
Do not build a critical system without model abstraction, fallback and exit planning.
Open-weight operations
Self-hosting transfers patching, serving, scaling, safety and monitoring to the organization.
Long-context confidence
A 1M window does not guarantee full coverage, reliable retrieval or balanced attention.
Agent loops
Cheap tokens can make runaway verification or tool loops inexpensive but still operationally harmful.
Alias retirement executed
The 2026/07/24 15:59 UTC retirement of `deepseek-chat` and `deepseek-reasoner` has happened. Neither alias is listed on the pricing page any more. This is no longer a migration deadline to plan for—it is a live outage for anything that still sends those strings.
Weights can move under a fixed model ID
DeepSeek published `DeepSeek-V4-Flash-0731` (304B params) on its weights channel as “the official release of DeepSeek-V4-Flash, superseding the preview version,” which had 284B total and 13B active params. There is no change-log entry after 2026/04/24, and it is not confirmed that the API endpoint serves the 0731 build—no docs page mentions “0731.” Either way, a model ID whose underlying weights may change without a change-log entry is a reproducibility problem, and pinning the ID does not protect you from it. Re-run your evaluation suite on a schedule, not only on a version bump.
Dated announcements are not live status
DeepSeek’s archival pages still say the aliases “will be discontinued” and “will be fully retired” in the future tense, ten days after the fact. Read the live pricing and reference pages for status and confirm against the API; read the news and change-log entries as history.
Price volatility
A published peak/off-peak policy is pending: 2x the regular prices during peak hours, applicable to all billing items, with the effective date “subject to the official announcement.” Peak hours are stated as 9:00–12:00 and 14:00–18:00 Beijing time daily. Real cost also depends on cache behavior, output length and correction work.
| Risk decision | Hosted API question | Self-managed question |
|---|---|---|
| Data | Where is content processed and retained? | Who can access model inputs, logs and infrastructure? |
| Security | What provider and network controls apply? | How are serving stack and weights protected? |
| Safety | What provider policies and isolation apply? | What filters, evaluation and abuse controls will you operate? |
| Reliability | What are limits, SLAs and fallback options? | How will you scale and recover? |
| Lifecycle | How are provider upgrades communicated? | Who owns model testing and rollout? |
First-party evidence behind this guide
These DeepSeek documentation, pricing and weights pages anchor the current V4, price, API and migration claims. All were re-checked on August 3, 2026. The pricing page is the evidence that the alias retirement executed—the notice and both alias names are gone from it.
AI Mindset