Pick DeepSeek V4 for near-frontier coding at ~1/12 the cost or open mit-licensed weights you can self-host. Pick Step 3.7 Flash for a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows or scmp reported it 'outshines larger rivals' from deepseek and moonshot on some benchmarks despite its smaller active size. On a tight budget at scale, Step 3.7 Flash is the value pick.
DeepSeek V4 (DeepSeek) and Step 3.7 Flash (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 3.7 Flash is stepFun's 198B MoE vision-language model built for coding and search agents - a distinct Chinese lab with genuinely competitive open weights. They diverge most on price and context window — each quantified below from the models' real specs.
Key differences
Price: Step 3.7 Flash is about 3.3× cheaper on input ($0.2/$1.15 per 1M tokens vs $0.66/$1.98 per 1M tokens) — meaningful once you are processing millions of tokens a month.
Context window: DeepSeek V4 holds 3.8× more — 1M (~1,500 pages) vs 256K (~393 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
Recency: Step 3.7 Flash is the newer model by about 35 days (released May 29, 2026), usually meaning fresher training data and capabilities.
Specifications
Spec
DeepSeek V4
Step 3.7 Flash
Provider
DeepSeek (China)
StepFun (China)
Released
April 24, 2026
May 29, 2026
Context window
1M (~1,500 pages)
256K (~393 pages)
Price (in/out)
$0.66/$1.98 per 1M tokens
$0.2/$1.15 per 1M tokens
Open weight?
Yes — self-hostable
Yes — self-hostable
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 — China's open-weight price earthquake — near-frontier capability at roughly a twelfth of GPT-5.5's cost — and it carries the larger 1M context.
Open MIT-licensed weights you can self-host: DeepSeek V4 — DeepSeek V4 lists open MIT-licensed weights you can self-host among its strengths; Step 3.7 Flash does not.
No long-context surcharge: DeepSeek V4 — Its 1M window holds about 3.8× more than Step 3.7 Flash's 256K in a single prompt.
A 198B-parameter sparse MoE vision-language model (11B active) built specifically for agentic coding and search workflows: Step 3.7 Flash — DeepSeek V4 is comparatively weak here — trails the very best on hardest agentic coding
SCMP reported it 'outshines larger rivals' from DeepSeek and Moonshot on some benchmarks despite its smaller active size: Step 3.7 Flash — DeepSeek V4 is comparatively weak here — 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
Open weights (Apache 2.0) at a low per-token price: Step 3.7 Flash — At $0.2/$1.15 per 1M tokens it undercuts DeepSeek V4 ($0.66/$1.98 per 1M tokens), and that gap compounds at volume.
Lowest cost at scale: Step 3.7 Flash — At $0.2/$1.15 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Largest single-prompt input: DeepSeek V4 — Its 1M window is about 3.8× larger than Step 3.7 Flash's 256K, fitting roughly 1,500 pages in one prompt.
Which should you pick?
A cost-sensitive startup shipping high volume: Step 3.7 Flash — At $0.2/$1.15 per 1M tokens it undercuts DeepSeek V4, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases: DeepSeek V4 — Larger 1M window fits more in one prompt.
Anyone whose priority is near-frontier coding at ~1/12 the cost: DeepSeek V4 — It is specifically built for that.
Anyone whose priority is a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows: Step 3.7 Flash — 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 3.7 Flash: where it fits
StepFun's 198B MoE vision-language model built for coding and search agents - a distinct Chinese lab with genuinely competitive open weights. Released May 29, 2026 by StepFun, it is built for a 198B-parameter sparse MoE vision-language model (11B active) built specifically for agentic coding and search workflows, sCMP reported it 'outshines larger rivals' from DeepSeek and Moonshot on some benchmarks despite its smaller active size, open weights (Apache 2.0) at a low per-token price, and includes a 1.8B vision encoder for image understanding alongside text.
Its trade-offs: stepFun is a newer, less established lab than DeepSeek, Alibaba, or Moonshot, benchmark 'outshines rivals' claims are from press coverage of specific tests, not a full independent leaderboard sweep, and smaller ecosystem and less third-party documentation than the more established Chinese labs. At $0.2 in / $1.15 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
DeepSeek V4 and Step 3.7 Flash overlap enough that the right pick depends on your specific job. Step 3.7 Flash costs less per token; DeepSeek V4 holds the larger context; and each leads in its own area — DeepSeek V4 for near-frontier coding at ~1/12 the cost, Step 3.7 Flash for a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows. Rather than crowning one, run the same hard task through both once and let the results decide.
Frequently asked questions
Is DeepSeek V4 or Step 3.7 Flash better for coding?
Public SWE-Bench figures are not available for Step 3.7 Flash, 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 3.7 Flash leans toward a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, DeepSeek V4 or Step 3.7 Flash?
Step 3.7 Flash is cheaper — $0.66/$1.98 per 1M tokens vs $0.2/$1.15 per 1M tokens, roughly 3.3× apart on input.
Which has the bigger context window?
DeepSeek V4 — 1M vs 256K, about 3.8× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both DeepSeek V4 and Step 3.7 Flash together?
Yes — a multi-model platform like LumiChats gives you DeepSeek V4, Step 3.7 Flash 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 3.7 Flash?
Step 3.7 Flash — released May 29, 2026, about 35 days after DeepSeek V4.
DeepSeek V4 vs Step 3.7 Flash
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 3.7 Flash for a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows or scmp reported it 'outshines larger rivals' from deepseek and moonshot on some benchmarks despite its smaller active size. On a tight budget at scale, Step 3.7 Flash is the value pick.
DeepSeek V4 (DeepSeek) and Step 3.7 Flash (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 3.7 Flash is stepFun's 198B MoE vision-language model built for coding and search agents - a distinct Chinese lab with genuinely competitive open weights. They diverge most on price and context window — each quantified below from the models' real specs.
Key differences at a glance
▸Price: Step 3.7 Flash is about 3.3× cheaper on input ($0.2/$1.15 per 1M tokens vs $0.66/$1.98 per 1M tokens) — meaningful once you are processing millions of tokens a month.
▸Context window: DeepSeek V4 holds 3.8× more — 1M (~1,500 pages) vs 256K (~393 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
▸Recency: Step 3.7 Flash is the newer model by about 35 days (released May 29, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
Spec
DeepSeek V4
Step 3.7 Flash
Provider
DeepSeek (China)
StepFun (China)
Released
April 24, 2026
May 29, 2026
Context window
1M (~1,500 pages)
256K (~393 pages)
Price (in/out)
$0.66/$1.98 per 1M tokens
$0.2/$1.15 per 1M tokens
Open weight?
Yes — self-hostable
Yes — self-hostable
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
China's open-weight price earthquake — near-frontier capability at roughly a twelfth of GPT-5.5's cost — and it carries the larger 1M context.
Open MIT-licensed weights you can self-host
DeepSeek V4
DeepSeek V4 lists open MIT-licensed weights you can self-host among its strengths; Step 3.7 Flash does not.
No long-context surcharge
DeepSeek V4
Its 1M window holds about 3.8× more than Step 3.7 Flash's 256K in a single prompt.
A 198B-parameter sparse MoE vision-language model (11B active) built specifically for agentic coding and search workflows
Step 3.7 Flash
DeepSeek V4 is comparatively weak here — trails the very best on hardest agentic coding
SCMP reported it 'outshines larger rivals' from DeepSeek and Moonshot on some benchmarks despite its smaller active size
Step 3.7 Flash
DeepSeek V4 is comparatively weak here — 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
Open weights (Apache 2.0) at a low per-token price
Step 3.7 Flash
At $0.2/$1.15 per 1M tokens it undercuts DeepSeek V4 ($0.66/$1.98 per 1M tokens), and that gap compounds at volume.
Lowest cost at scale
Step 3.7 Flash
At $0.2/$1.15 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Largest single-prompt input
DeepSeek V4
Its 1M window is about 3.8× larger than Step 3.7 Flash's 256K, fitting roughly 1,500 pages in one prompt.
Which should you pick?
A cost-sensitive startup shipping high volume
→ Step 3.7 Flash
At $0.2/$1.15 per 1M tokens it undercuts DeepSeek V4, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases
→ DeepSeek V4
Larger 1M window fits more in one prompt.
Anyone whose priority is near-frontier coding at ~1/12 the cost
→ DeepSeek V4
It is specifically built for that.
Anyone whose priority is a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows
→ Step 3.7 Flash
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 3.7 Flash: where it fits
StepFun's 198B MoE vision-language model built for coding and search agents - a distinct Chinese lab with genuinely competitive open weights. Released May 29, 2026 by StepFun, it is built for a 198B-parameter sparse MoE vision-language model (11B active) built specifically for agentic coding and search workflows, sCMP reported it 'outshines larger rivals' from DeepSeek and Moonshot on some benchmarks despite its smaller active size, open weights (Apache 2.0) at a low per-token price, and includes a 1.8B vision encoder for image understanding alongside text.
Its trade-offs: stepFun is a newer, less established lab than DeepSeek, Alibaba, or Moonshot, benchmark 'outshines rivals' claims are from press coverage of specific tests, not a full independent leaderboard sweep, and smaller ecosystem and less third-party documentation than the more established Chinese labs. At $0.2 in / $1.15 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
DeepSeek V4 and Step 3.7 Flash overlap enough that the right pick depends on your specific job. Step 3.7 Flash costs less per token; DeepSeek V4 holds the larger context; and each leads in its own area — DeepSeek V4 for near-frontier coding at ~1/12 the cost, Step 3.7 Flash for a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows. Rather than crowning one, run the same hard task through both once and let the results decide.
Want both DeepSeek V4 and Step 3.7 Flash 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.
Is DeepSeek V4 or Step 3.7 Flash better for coding?
Public SWE-Bench figures are not available for Step 3.7 Flash, 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 3.7 Flash leans toward a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, DeepSeek V4 or Step 3.7 Flash?
Step 3.7 Flash is cheaper — $0.66/$1.98 per 1M tokens vs $0.2/$1.15 per 1M tokens, roughly 3.3× apart on input.
Which has the bigger context window?
DeepSeek V4 — 1M vs 256K, about 3.8× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both DeepSeek V4 and Step 3.7 Flash together?
Yes — a multi-model platform like LumiChats gives you DeepSeek V4, Step 3.7 Flash 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 3.7 Flash?
Step 3.7 Flash — released May 29, 2026, about 35 days after DeepSeek V4.
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.