On this page · 11 sections
- What changed on July 24, 2026
- The two-line rename, and the reasoning trap inside it
- The real API change: thinking mode is now a parameter
- What the switch does to your bill
- Is V4-Flash enough, or do you need V4-Pro?
- Migration checklist for remaining call sites
- India-specific considerations
- Common migration mistakes
- FAQ
- How eCorpIT can help
- References
Summary. At 15:59 UTC on July 24, 2026, DeepSeek permanently retired the two model names most production code used: deepseek-chat and deepseek-reasoner. DeepSeek said both would be inaccessible after that moment, with no grace period. Until then both names had routed to deepseek-v4-flash since the V4 preview shipped on April 24, 2026, so the fix is to name the model you actually want. DeepSeek still accepts deepseek-v4-flash but now serves it with V4.1-Flash under the name deepseek-flash (output at $0.60 per 1M tokens off-peak, $1.20 at peak), while deepseek-v4-pro costs $1.98 off-peak and $3.96 at peak per 1M output tokens; both have a 1M-token context window and a 384K maximum output. The trap is that deepseek-reasoner mapped to Flash, not Pro, so a blind swap silently downgrades any workload that relied on it for hard reasoning. This guide gives the exact model mapping, the thinking-mode parameter, the current prices, and a migration checklist for any call site still on a retired name.
Update, November 18, 2026: the retirement is now past, and DeepSeek has changed its line-up again since this guide first ran. On September 10, 2026 it released V4.1-Flash, a 552B-parameter model, and asked callers to use the model name deepseek-flash; deepseek-v4-flash is still accepted but is routed to V4.1-Flash and billed at the Flash price. deepseek-v4-pro remains available. Prices now use peak and off-peak rates, with off-peak at half the peak rate, and the tables below show the current figures.
If you run DeepSeek anywhere in production and still see errors on old model names, this is the cause. DeepSeek published the deprecation date in its change log on April 24, 2026, and repeated it on the V4 release notes and the pricing page. The cutoff has passed. The fix is small, but it touches model names, request parameters, and cost assumptions at the same time, which is exactly the combination that breaks quietly.
What changed on July 24, 2026
DeepSeek shipped the DeepSeek-V4 preview on April 24, 2026 and added two explicit model names to the API: deepseek-v4-pro and deepseek-v4-flash. The base URL did not change. At the time, according to DeepSeek's pricing page, the legacy names were kept alive only as compatibility aliases: deepseek-chat points to the non-thinking mode of deepseek-v4-flash, and deepseek-reasoner points to the thinking mode of the same Flash model.
That compatibility window closed on July 24, 2026 at 15:59 UTC. DeepSeek's V4 release note stated it plainly: deepseek-chat and deepseek-reasoner would be fully retired and inaccessible after that time. There was no automatic forward to V4-Pro, no fallback, and no soft-fail. A call that still names a retired model gets an error back, and any service that does not catch and re-route it throws user-facing failures.
Three facts decide how much work you have. First, if your code already names deepseek-v4-flash or deepseek-v4-pro, your calls still work, but DeepSeek now routes deepseek-v4-flash to V4.1-Flash and asks callers to use deepseek-flash, so update that name at your next release. Second, if your code still names deepseek-chat or deepseek-reasoner, those calls have failed since the cutoff and you must change the string now. Third, if you depended on deepseek-reasoner for its reasoning quality, renaming to deepseek-v4-flash keeps you on Flash-tier reasoning, and only naming deepseek-v4-pro moves you up.
The two-line rename, and the reasoning trap inside it
For most callers the migration is a single field. Keep your base_url, keep your API key, and change the model string. The mapping below is the whole change for a non-thinking chat workload.
| Legacy model name | Routed to (until July 24, 2026) | What to set now |
|---|---|---|
deepseek-chat |
deepseek-v4-flash, non-thinking mode |
deepseek-flash with thinking disabled |
deepseek-reasoner |
deepseek-v4-flash, thinking mode |
deepseek-flash (same tier) or deepseek-v4-pro (higher tier) |
The second row is where teams lose quality without noticing. deepseek-reasoner was the name you reached for when you wanted chain-of-thought reasoning, and many teams assume the "reasoner" lineage was DeepSeek's strongest model. Under V4 that alias resolved to Flash thinking mode, which is the 284B-parameter model with 13B active parameters, not the 1.6T-parameter Pro model. If a straight rename to deepseek-v4-flash is good enough, keep it and enjoy the lower bill. If that workload was carrying real reasoning load, evaluate deepseek-v4-pro before you decide, because the alias was never a promise of the top tier. Teams already thinking in terms of routing by cost and difficulty will recognise this pattern from our LLM hybrid-routing and API-spend framework.
The real API change: thinking mode is now a parameter
Under the legacy names, reasoning was a separate model: you picked deepseek-reasoner to get chain-of-thought and deepseek-chat to skip it. V4 unifies both into one model with a toggle, so the mode moves out of the model name and into the request body. This is the part of the migration that is easy to miss, because renaming the model is not enough if your old code encoded "reasoning" purely by model choice.
DeepSeek's thinking-mode guide documents the switch. In the OpenAI-compatible format, you pass {"thinking": {"type": "enabled"}} or {"thinking": {"type": "disabled"}}, and the toggle defaults to enabled. With the OpenAI SDK, the flag travels inside extra_body:
from openai import OpenAI
client = OpenAI(api_key="<DeepSeek API Key>", base_url="https://api.deepseek.com")
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Explain the migration in one paragraph."}],
reasoning_effort="high",
extra_body={"thinking": {"type": "enabled"}},
)
reasoning = response.choices[0].message.reasoning_content
answer = response.choices[0].message.content
Two behaviours will surprise anyone porting old code. Thinking mode ignores temperature, presence_penalty, and frequency_penalty; DeepSeek keeps them accepted for compatibility but they have no effect, so a temperature=0 habit no longer does what you think. top_p now depends on the model: on deepseek-flash it applies only in thinking mode, within 0.95 to 1.0, while on deepseek-v4-pro it is ignored in thinking mode. And the chain-of-thought comes back in a separate reasoning_content field alongside content. For plain chat turns you can drop reasoning_content from later context, but for tool-calling turns you must pass it back on every following request, or the API returns a 400 error. Effort is tunable too, through reasoning_effort set to low, high or max; a request for medium is treated as high.
What the switch does to your bill
DeepSeek bills per 1M tokens and prices cache-hit input, cache-miss input, and output separately. The table below is the full current price and capability sheet for both V4 models, taken from DeepSeek's pricing page as of November 18, 2026. DeepSeek now charges peak and off-peak rates: off-peak is half the peak rate, and peak hours are 01:00 to 04:00 and 06:00 to 10:00 UTC on weekdays, excluding Chinese public holidays.
| Attribute | deepseek-flash (V4.1-Flash) | deepseek-v4-pro |
|---|---|---|
| Input, 1M tokens (cache hit) | $0.003 off-peak, $0.006 peak | $0.022 off-peak, $0.044 peak |
| Input, 1M tokens (cache miss) | $0.15 off-peak, $0.30 peak | $0.66 off-peak, $1.32 peak |
| Output, 1M tokens | $0.60 off-peak, $1.20 peak | $1.98 off-peak, $3.96 peak |
| Context window | 1M tokens | 1M tokens |
| Maximum output | 384K tokens | 384K tokens |
| Total / active parameters | 552B / 8B input, 16B output | 1.6T / 49B |
| Concurrency limit | 2500 | 500 |
The prices are low even against a market that has fallen fast in 2026, and they are the reason so many teams route bulk work here in the first place; the same cost logic drives the wider shift covered in our note on Chinese open models and enterprise AI cost. Two numbers change your monthly estimate the most: output tokens and whether your prompts hit the cache. To make the Flash-versus-Pro gap concrete, the table below converts the per-token output prices into monthly output cost at three volumes. Each cell shows off-peak / peak cost. It is arithmetic on the listed prices, not a quote.
| Monthly output tokens | deepseek-flash (V4.1-Flash) | deepseek-v4-pro |
|---|---|---|
| 10M | $6.00 / $12.00 | $19.80 / $39.60 |
| 100M | $60.00 / $120.00 | $198.00 / $396.00 |
| 1B | $600.00 / $1,200.00 | $1,980.00 / $3,960.00 |
Pro costs roughly 3.3 times Flash on output and about 4.4 times on cache-miss input. That ratio, not the absolute price, is the decision: if Flash clears your quality bar, Pro is money spent for reasoning you did not need. A token counter helps you estimate before you commit, and our LLM token counter guide walks through sizing a workload. For teams comparing DeepSeek against United States frontier vendors on unit economics, the pattern sits alongside our analysis of GPT-5.6 inference cost for enterprise AI.
Is V4-Flash enough, or do you need V4-Pro?
DeepSeek positions the two models by size and job. Per the V4 release notes, V4-Pro carries 1.6T total parameters with 49B active and is aimed at agentic coding, reasoning, and broad world knowledge, while V4-Flash carries 284B total with 13B active and is the fast, cheap option whose reasoning "closely approaches" Pro. DeepSeek says Pro leads open-source models on agentic coding benchmarks and trails only Gemini-3.1-Pro on world knowledge among the models it compared.
Treat vendor benchmark claims as marketing until you re-run them on your own tasks. Independent write-ups of V4 report V4-Pro near the top of coding leaderboards, with DataCamp and model directories such as OpenRouter covering the released specs and scores, but the numbers move a lot between harnesses, and a self-reported score is not an independent one. The practical test is cheaper than the debate: take the ten hardest real prompts your product actually sends, run them through Flash and Pro at equal effort, and compare outputs and latency. If Flash holds, you save roughly 70 per cent on output. This is the same build-your-own-eval discipline we use when comparing coding models, as in our Grok 4.5 enterprise coding-agent evaluation.
The strategic backdrop matters for a stability decision. DeepSeek built V4 to run on domestic silicon rather than restricted United States chips. As Wei Sun, principal analyst at Counterpoint Research, told CNN, running V4 on Huawei and Cambricon hardware "allows AI systems to be built and deployed without relying solely on Nvidia, which is why V4 could ultimately have an even bigger impact than R1." The market reaction was calmer than the R1 shock of 2025. Ivan Su, senior equity analyst at Morningstar, told CNN: "V4 is simply a follow-through on that same trend, and trends don't make headlines the way shocks do." For a buyer, a boring, well-funded release on independent supply chains is a good sign for API longevity.
Migration checklist for remaining call sites
Work through these in order. Each step is small, and the whole thing is a half-day for a typical service.
- Grep every repository, notebook, and environment config for the strings
deepseek-chatanddeepseek-reasoner. Include prompt templates, evaluation scripts, and infrastructure as code, not just application code.
- Decide the target per call site. Default chat and high-volume paths go to
deepseek-v4-flash. Reasoning-heavy or agentic paths get evaluated againstdeepseek-v4-probefore you choose.
- Move the reasoning decision into the request body. Set
extra_body={"thinking": {"type": "enabled"}}where you previously useddeepseek-reasoner, and disable it where you useddeepseek-chat. Addreasoning_effortif you want low,highormax.
- Fix parameter assumptions. Remove reliance on
temperature,top_p,presence_penalty, andfrequency_penaltyin thinking mode, since they are ignored, except that top_p still applies on deepseek-flash within 0.95 to 1.0.
- Handle
reasoning_content. Read it from responses, and for tool-calling loops pass it back on every subsequent request to avoid the 400 error.
- If you call DeepSeek through the Anthropic-format endpoint at
https://api.deepseek.com/anthropic, useoutput_config.effortfor effort control instead ofreasoning_effort.
- Re-run your evaluation set on the explicit model name you now call, and add an alert that fails loudly on an unknown-model error so a missed call site cannot fail silently.
India-specific considerations
For teams in India, two points sit on top of the technical migration. DeepSeek bills in United States dollars, so an Indian team carries currency risk on top of usage: the same 100M output tokens that cost $60 off-peak or $120 at peak on Flash convert at the prevailing rupee rate, and a weaker rupee raises the effective bill even when token usage is flat. Budget in dollars, and hedge if the spend is material.
The larger question is data governance. DeepSeek's API is operated from China, so sending customer data to it is a cross-border transfer, and India's Digital Personal Data Protection Act, 2023 turns that into a compliance decision rather than a purely technical one. Before you route personal data to any overseas model, map what leaves the country and why, and design for consent and data-minimisation from the start. Our DPDP engineering playbook for Indian startups covers the controls that make this defensible, and the broader adoption pattern appears in our look at Chinese AI models and United States enterprise token share.
Common migration mistakes
The failures cluster in four places. Renaming deepseek-reasoner to deepseek-v4-flash and assuming you kept top-tier reasoning is the most expensive, because the quality drop is invisible until output degrades. Leaving temperature in a thinking-mode call and expecting deterministic output is the second, since the parameter is silently ignored. Dropping reasoning_content inside a tool-calling loop is the third, and it produces a hard 400 rather than a silent issue. The fourth is scope: teams patch the main service and forget a cron job, a data pipeline, or a staging config that still names a retired model and has been erroring since the cutoff.
FAQ
How eCorpIT can help
eCorpIT is a Gurugram software organisation with senior-led engineering teams that ship and maintain production AI systems. We help teams migrate LLM integrations without downtime: auditing every call site, moving reasoning into the right V4 tier, wiring up evaluations so a quality drop cannot slip through, and modelling the cost change before you commit. If a DeepSeek workload still calls a retired or legacy model name, or you want a second opinion on Flash versus Pro for your traffic, contact us and we will scope it with you.
References
- DeepSeek API Docs, "Models & Pricing." https://api-docs.deepseek.com/quick_start/pricing
- DeepSeek API Docs, "Change Log." https://api-docs.deepseek.com/updates
- DeepSeek API Docs, "DeepSeek V4 Preview Release," April 24, 2026. https://api-docs.deepseek.com/news/news260424
- DeepSeek API Docs, "Thinking Mode." https://api-docs.deepseek.com/guides/thinking_mode
- CNN Business, "China's AI upstart DeepSeek drops new model. Will it make waves like last year?", April 24, 2026. https://www.cnn.com/2026/04/24/tech/chinas-ai-deepseek-v4-intl-hnk
- Hugging Face, "DeepSeek-V4 open weights collection." https://huggingface.co/collections/deepseek-ai/deepseek-v4
- OpenRouter, "DeepSeek V4 Flash - API pricing and benchmarks." https://openrouter.ai/deepseek/deepseek-v4-flash
- DataCamp, "DeepSeek V4: Features, Benchmarks, and Comparisons." https://www.datacamp.com/blog/deepseek-v4
- Enterprise DNA, "DeepSeek API: Migrate Before July 24 or Integrations Break." https://enterprisedna.co/resources/news/deepseek-api-migration-july-24-deadline-2026/
- Developers Digest, "DeepSeek Retires deepseek-chat and deepseek-reasoner on July 24: Your V4 Migration Guide." https://www.developersdigest.tech/blog/deepseek-chat-to-v4-migration-guide
- WaveSpeed, "DeepSeek V4 API Migration: Update Model Names Before July." https://wavespeed.ai/posts/blog-deepseek-v4-model-name-migration/
_Last updated: November 18, 2026._