DeepSeek V4 vs Step 5 Preview
DeepSeek · China | StepFun · China · Updated June 2026
Quick verdict
Pick DeepSeek V4 for near-frontier coding at ~1/12 the cost or open mit-licensed weights you can self-host. Pick Step 5 Preview for sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents or 1m-token context window (64k max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available. Choose DeepSeek V4 if you need self-hosting or data privacy; Step 5 Preview if you want a managed API.
DeepSeek V4 (DeepSeek) and Step 5 Preview (StepFun) are two of the models people most often weigh against each other in 2026. DeepSeek V4 is china's open-weight price earthquake — near-frontier capability at roughly a twelfth of GPT-5.5's cost. Step 5 Preview is stepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October. They diverge most on price and open vs. closed weights — each quantified below from the models' real specs.
Key differences at a glance
- ▸Price: DeepSeek V4 is about 1.5× cheaper on input ($0.66/$1.98 per 1M tokens vs $1/$2.7 per 1M tokens) — modest, but it adds up at steady volume.
- ▸Context window: both advertise 1M (~1,500 pages). Tie on paper — test on your own long inputs, since usable recall varies by model.
- ▸Recency: Step 5 Preview is the newer model by about 5 months (released September 20, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
| Spec | DeepSeek V4 | Step 5 Preview |
|---|---|---|
| Provider | DeepSeek (China) | StepFun (China) |
| Released | April 24, 2026 | September 20, 2026 |
| Context window | 1M (~1,500 pages) | 1M tokens (~1,500 pages) |
| Price (in/out) | $0.66/$1.98 per 1M tokens | $1/$2.7 per 1M tokens |
| Open weight? | Yes — self-hostable | No — API only |
| Modalities | text, code | text, image, code |
| SWE-Bench Verified | 80.6% | Not published |
| MRCR v2 @ 1M | Not published | Not published |
Who wins what
Near-frontier coding at ~1/12 the cost
DeepSeek V4
At $0.66/$1.98 per 1M tokens it undercuts Step 5 Preview ($1/$2.7 per 1M tokens), and that gap compounds at volume.
Open MIT-licensed weights you can self-host
DeepSeek V4
Open weights make this possible at all — Step 5 Preview is API-only, so it cannot leave the vendor's servers.
No long-context surcharge
DeepSeek V4
China's open-weight price earthquake — near-frontier capability at roughly a twelfth of GPT-5.5's cost — and it runs cheaper at $0.66/$1.98 per 1M tokens.
Sparse MoE architecture — 600B total parameters, only 27B active per token — built for long-horizon agentic work across large codebases and documents
Step 5 Preview
DeepSeek V4 is comparatively weak here — trails the very best on hardest agentic coding
1M-token context window (64K max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available
Step 5 Preview
StepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October — and it is the newer of the two.
67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%)
Step 5 Preview
Step 5 Preview lists 67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%) among its strengths; DeepSeek V4 does not.
Lowest cost at scale
DeepSeek V4
At $0.66/$1.98 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Which should you pick?
A cost-sensitive startup shipping high volume
→ DeepSeek V4
At $0.66/$1.98 per 1M tokens it undercuts Step 5 Preview, and on millions of tokens that margin decides the monthly bill.
A team with data-privacy or self-hosting needs
→ DeepSeek V4
Open weights let you run it on your own hardware; Step 5 Preview is API-only.
Anyone whose priority is near-frontier coding at ~1/12 the cost
→ DeepSeek V4
It is specifically built for that.
Anyone whose priority is sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents
→ Step 5 Preview
That is its strongest area.
DeepSeek V4: where it fits
China's open-weight price earthquake — near-frontier capability at roughly a twelfth of GPT-5.5's cost. Released April 24, 2026 by DeepSeek, it is built for near-frontier coding at ~1/12 the cost, open MIT-licensed weights you can self-host, no long-context surcharge, and highest LiveCodeBench result.
Its trade-offs are real: this generic 'V4' entry mirrors DeepSeek V4-Pro's specs - see DeepSeek V4-Pro and DeepSeek V4-Flash for DeepSeek's actual named product tiers, trails the very best on hardest agentic coding, and text/code focused, less multimodal. At $0.66 in / $1.98 out per million tokens, it sits in the budget price band.
Step 5 Preview: where it fits
StepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October. Released September 20, 2026 by StepFun, it is built for sparse MoE architecture — 600B total parameters, only 27B active per token — built for long-horizon agentic work across large codebases and documents, 1M-token context window (64K max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available, 67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%), and scores 44 on the Artificial Analysis Intelligence Index, ranking 27th of 653 models tracked.
Its trade-offs: trails closed frontier models on coding — 67.7% on DeepSWE v1.1 vs GPT-6 Astra's 74.1% and Claude Opus 5's 74.0%, open weights were promised for October 15, 2026 but hadn't shipped as of this writing — API-only for now despite the open-weight roadmap, a 'Preview' release, not StepFun's finished flagship — positioning and pricing may change once weights ship, and stepCodeBench and DeepSWE figures are StepFun's own reported numbers, not yet independently reproduced at scale. At $1 in / $2.7 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
The defining split here is open vs. closed. DeepSeek V4 gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Step 5 Preview gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Want both DeepSeek V4 and Step 5 Preview without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.
See pricingFrequently asked questions
Is DeepSeek V4 or Step 5 Preview better for coding?
Public SWE-Bench figures are not available for Step 5 Preview, so the honest test is your own repository — run an identical real bug through both. By design, DeepSeek V4 leans toward near-frontier coding at ~1/12 the cost while Step 5 Preview leans toward sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, DeepSeek V4 or Step 5 Preview?
DeepSeek V4 is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Step 5 Preview is API-metered at $1/$2.7 per 1M tokens. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
Which has the bigger context window?
Both advertise 1M (~1,500 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.
Can I use both DeepSeek V4 and Step 5 Preview together?
Yes — a multi-model platform like LumiChats gives you DeepSeek V4, Step 5 Preview and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, DeepSeek V4 or Step 5 Preview?
Step 5 Preview — released September 20, 2026, about 5 months after DeepSeek V4.
Related comparisons
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.