Who this is for: AI developers, indie hackers, and engineering leads running production API workloads. On July 20, 2026, DeepSeek V4 graduated from preview to general availability (GA) — same 1.6T MoE architecture, but with agent/math/code upgrades and the first peak-valley pricing scheme in DeepSeek history. What you get: full timeline from April preview to GA, CSA/HCA/mHC/Muon architecture breakdown, benchmark tables vs. Claude Fable 5 and GPT-5.6 Sol, the 116x cost-performance gap, peak/off-peak rate tables, four savings tactics, and a July 24 migration runbook for retiring deepseek-chat. Context: local inference options in the ds4 / V4 Flash Mac decision guide; broader routing in the OpenRouter multi-model routing matrix.
TL;DR — 30-second verdict
deepseek-chat and deepseek-reasoner go offline — update to deepseek-v4-flash or deepseek-v4-pro now.After three months of preview access, most teams hit the same six decision blind spots when GA landed — not because V4 is unknown, but because the commercial packaging shifted:
deepseek-chat and deepseek-reasoner still work today but die on July 24 at 15:59 UTC. Any cron job or production service still using old model IDs will hard-fail.The sections below resolve each blind spot with official docs, benchmark tables, and migration code.
DeepSeek V4 preview shipped April 24, 2026 under MIT license. Today's GA release is that same model family graduating into production — with performance refinements and a formal pricing structure.
| Date | Event |
|---|---|
| April 24, 2026 | V4 preview + open weights (MIT): V4-Pro (1.6T) and V4-Flash (284B) |
| May 2026 | Production-tuned V4-Flash and V4-Pro; API generally available |
| June 2026 | V4-Pro permanent 75% price cut — output locked at $0.87/M tokens (off-peak baseline) |
| June 29, 2026 | Email to all API users: GA mid-July, first disclosure of peak-valley pricing |
| July 19, 2026 | GA gray-release to select developers; media reports "full version imminent" |
| July 20, 2026 | GA official launch (today) |
| July 24, 2026 | Legacy names deepseek-chat and deepseek-reasoner permanently retired (15:59 UTC) |
One-line summary: V4 preview was already strong. GA adds agent capability, math reasoning, and code generation refinements on top, plus the first disciplined commercial billing model DeepSeek has ever shipped.
Most models advertise 1M tokens on paper but choke in production — KV cache memory grows linearly with context length. DeepSeek V4 replaces the MLA design from V2/V3 with a hybrid attention stack that actually cuts serving costs.
| Spec | V4-Pro | V4-Flash |
|---|---|---|
| Total parameters | 1.6 trillion (1.6T) | 284 billion (284B) |
| Active per token | 49B (3% of total) | 13B (4.6% of total) |
| Transformer layers | 61 | 43 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output | 384K tokens | 384K tokens |
| Precision | FP4 (MoE experts) + FP8 (rest) | FP4 + FP8 mixed |
| Pretraining data | 33T+ tokens | 32T+ tokens |
| License | MIT | MIT |
CSA compresses KV sequences 4x via softmax-gated pooling, then uses an FP4 "lightning indexer" for top-k sparse selection (top-1024 on Pro, top-512 on Flash). A 128-token sliding window preserves recent context. At 1M tokens, V4-Pro uses only 27% of the inference FLOPs compared to DeepSeek V3.2.
HCA compresses tokens 128x and runs dense global attention over the compressed cache — capturing long-range dependencies CSA might miss. V4-Flash uses HCA in its first two layers, then alternates CSA/HCA; V4-Pro follows a similar pattern.
Combined effect: KV cache memory drops to 10% of V3.2 on V4-Pro (7% on V4-Flash). That is what makes 1M-token serving economically viable at API scale.
Standard residual connections (x = x + f(x)) degrade signal flow in very deep networks. mHC replaces them with a 4-channel residual stream governed by a doubly stochastic matrix (Birkhoff polytope constraint). Result: stable gradient propagation through 61 layers without sacrificing expressivity.
V4 was trained with the Muon optimizer instead of AdamW. Newton-Schulz orthogonalization conditions gradient steps, yielding faster convergence and more stable training runs at MoE scale.
DeepSeek V4 ships three inference modes. Official recommended sampling for all: temperature=1.0, top_p=1.0.
| Mode | Behavior | Best for |
|---|---|---|
| Non-think | No chain of thought; fastest response | Simple Q&A, routing, classification |
| Think High | Explicit reasoning in <redacted_thinking> blocks | Medium complexity tasks, code debugging |
| Think Max | Maximum reasoning effort; needs 384K+ context | Complex math, long-chain agent planning |
Core benchmark data from DeepSeek official docs and independent aggregators (each vendor used its own inference harness where noted):
| Benchmark | DeepSeek V4-Pro | Claude Fable 5 | GPT-5.6 Ultra | Claude Opus 4.8 |
|---|---|---|---|---|
| SWE-bench Verified | 80.6% | 96.0% | N/A | ~69% |
| SWE-bench Pro | 55.4% | 80.3% | 78.1% | 69.2% |
| LiveCodeBench (Pass@1) | 93.5% | 88.1% | 87.4% | 83.2% |
| Codeforces Elo | 3,206 | — | — | — |
| Terminal-Bench 2.1 | 83.9% | 88.0% | 85.1% | 82.7% |
Key takeaways:
Caveat: Benchmarks are vendor-reported unless independently reproduced. Cross-model harness differences (DeepSeek vs. Codex vs. Claude Code) mean treat scores as directional, not definitive. For live OpenRouter volume context, see the June 2026 OpenRouter rankings analysis.
Raw benchmark scores tell half the story. Artificial Analysis ran major models through industry-specific task indices. On the Strategy & Operations benchmark:
That is 116x cheaper for a roughly 24% score gap (31% relative). For high-volume production pipelines — nightly code review, bulk document summarization, agent loops — the math is hard to ignore even if Fable 5 wins on the hardest single-repo fixes.
| Dimension | DeepSeek V4-Pro | GPT-5.6 Sol | Claude Fable 5 |
|---|---|---|---|
| Open weights / MIT | Yes | No | No |
| Self-hostable | Yes | No | No |
| Context window | 1M tokens | Not publicly confirmed | 1M tokens |
| Best overall coding | Second tier (80.6% Verified) | Second tier (Terminal-Bench 85.1%) | Leads (96.0% Verified, 80.3% Pro) |
| Best algorithms / math | Leads (LiveCodeBench 93.5%) | Strong | — |
| Output cost (off-peak) | $0.87/M tokens | ~$15/M | ~$50/M |
| Output cost (peak) | $1.74/M tokens | — | — |
| Data sovereignty | Yes (self-host) | No | No |
| Agent orchestration | Strong; multi-agent support | Strong | Strongest |
Routing guidance:
For how Kimi K3 now stacks up against V4-Pro on parameter count and context, see the Kimi K3 open-source review.
GA's most debated change: time-based pricing where rates double during Beijing weekday peak hours. Think of it like time-of-use electricity pricing.
Peak hours (Beijing Time): weekdays, 09:00–12:00 and 14:00–18:00.
| Model | Item | Off-Peak | Peak |
|---|---|---|---|
| V4-Pro | Input (cache hit) | $0.0035 / 1M tokens | 2x |
| Input (cache miss) | $0.435 / 1M tokens | $0.87 / 1M | |
| Output | $0.87 / 1M tokens | $1.74 / 1M | |
| V4-Flash | Input (cache hit) | $0.0028 / 1M tokens | 2x |
| Input (cache miss) | $0.14 / 1M tokens | $0.28 / 1M | |
| Output | $0.28 / 1M tokens | $0.56 / 1M |
Even at peak, V4-Pro output ($1.74/M) is 8.6x cheaper than Claude Opus 4.8 ($15/M) and GPT-5.6 Sol (~$15/M). The surcharge is real; the baseline remains the market's best value.
Historical pricing context: the June permanent discount is covered in our OpenRouter June 2026 analysis, where V4-Flash already dominated daily token volume.
Deadline: July 24, 2026, 15:59 UTC (July 24, 23:59 Beijing time). Legacy model names deepseek-chat and deepseek-reasoner will permanently stop responding.
| Old model name | New equivalent | Notes |
|---|---|---|
deepseek-chat | deepseek-v4-flash (non-thinking) | Drop-in for most chat use cases |
deepseek-reasoner | deepseek-v4-flash (thinking mode) | Or upgrade to deepseek-v4-pro for stronger reasoning |
OpenAI SDK (Python):
from openai import OpenAI
client = OpenAI(
api_key="your_deepseek_api_key",
base_url="https://api.deepseek.com"
)
# Old (stops working July 24)
# response = client.chat.completions.create(
# model="deepseek-chat",
# messages=[{"role": "user", "content": "Hello"}]
# )
# New — non-thinking (replaces deepseek-chat)
response = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello"}]
)
# New — thinking mode (replaces deepseek-reasoner)
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Solve this step by step..."}],
extra_body={
"thinking": {"type": "enabled", "budget_tokens": 8000}
}
)
Anthropic SDK (Python): V4 supports both OpenAI ChatCompletions and Anthropic Messages formats. Base URL unchanged; update the model name only.
import anthropic
client = anthropic.Anthropic(
api_key="your-deepseek-api-key",
base_url="https://api.deepseek.com"
)
message = client.messages.create(
model="deepseek-v4-pro",
max_tokens=4096,
messages=[{"role": "user", "content": "What changed in the V4 GA release?"}]
)
deepseek-chat and deepseek-reasoner. Any hit must migrate before July 24, 15:59 UTC.DeepSeek V4 GA is one of the most important open-model milestones of 2026. CSA/HCA attention, mHC, and Muon training are genuine engineering — not parameter inflation. At roughly one-tenth to one-hundredth the cost of closed frontier models, V4-Pro delivers the strongest open-weight coding performance on SWE-bench Verified, real 1M context, and MIT-licensed weights you can self-host.
It does not beat Claude Fable 5 on the hardest repo work, and GPT-5.6 Sol still leads terminal-heavy agents. Peak-valley pricing adds operational complexity for 24/7 pipelines. But for teams where cost, data sovereignty, or long-context agents matter, V4-Pro remains the default evaluation target.
Running DeepSeek V4 agent workflows in production — OpenClaw Gateway, multi-model hybrid routing, or peak-aware batch schedulers — on a local MacBook hits three structural bottlenecks:
For stable V4-Pro + multi-model agent stacks, MACCOME Mac cloud hosts provide real macOS, SSH handoff, and isolated environments so agents run 24/7 on dedicated nodes. Public plans: Mac mini cloud rental rates.
Dates to bookmark: July 20 (GA live) → July 24, 15:59 UTC (legacy endpoints retired).
Sources: DeepSeek official docs, arXiv:2606.19348, HuggingFace Model Hub, LLMReference, Artificial Analysis, MangoMind Blog. Benchmarks as reported July 20, 2026.
FAQ
What is DeepSeek peak-valley pricing?
GA introduces time-based rates that double during Beijing weekday peaks (09:00–12:00 and 14:00–18:00). Off-peak V4-Pro output is $0.87/M; peak is $1.74/M. V4-Flash off-peak output is $0.28/M; peak is $0.56/M.
How do I migrate from deepseek-chat before July 24?
Replace deepseek-chat with deepseek-v4-flash (non-thinking) and deepseek-reasoner with deepseek-v4-flash thinking mode or deepseek-v4-pro. Legacy names stop working July 24, 2026 at 15:59 UTC (23:59 Beijing time).
Is DeepSeek V4 better than GPT-5.6 Sol?
Depends on the task. GPT-5.6 Sol leads Terminal-Bench 2.1 (85.1% vs 83.9%). V4-Pro leads LiveCodeBench (93.5%) and matches the best open-weight SWE-bench Verified score (80.6%). On cost, V4-Pro output at $0.87/M is roughly 17x cheaper than GPT-5.6 Sol at ~$15/M.
What are the three DeepSeek V4 reasoning modes?
Non-think (fast, no chain of thought), Think High (explicit reasoning for medium tasks), and Think Max (maximum effort, needs 384K+ context). Recommended sampling: temperature=1.0, top_p=1.0 for all modes.
Can I self-host DeepSeek V4?
Yes — both V4-Pro (1.6T) and V4-Flash (284B) ship under MIT with 1M context. Production self-hosting needs high-memory GPU clusters. For Mac-based local inference, see the ds4 / V4 Flash decision guide.
How do I run DeepSeek V4 agents 24/7 in production?
Deploy agent gateways on a dedicated Mac cloud host to avoid laptop sleep interrupting long sessions. See MACCOME Mac cloud rental plans for node configs and pricing.