text model comparison
DeepSeek-V4-Pro vs Step 5 Preview
DeepSeek-V4-Pro and Step 5 Preview are both current text models, from DeepSeek and StepFun. Step 5 Preview is 24% cheaper per 1M input tokens than DeepSeek-V4-Pro, $1 vs $1.32. Both accept 1,000,000 tokens of context.
Data verified October 13, 2026 · Dataset 2026-10-13
Side by side
Standard-tier prices in effect today. The better value in each row is highlighted.
| Fact | DeepSeek-V4-Pro | Step 5 Preview |
|---|---|---|
| Price per 1M input tokens | $1.32 | $1 (better) |
| Price per 1M output tokens | $3.96 | $2.70 (better) |
| Cost of 10M input and 2M output tokens | $21.12 | $15.40 (better) |
| Arena Text | 1465 Elo (#29 of 49) | Not measured |
| GPQA Diamond | 91.7% (#19 of 40) | Not measured |
| FrontierMath Tiers 1-3 (v2) | 64.6% (#26 of 40) | Not measured |
| SimpleQA Verified | 52.9% (#18 of 36) | Not measured |
| Provider | DeepSeek | StepFun |
| Release date | August 13, 2026 | Not reported |
| Access | API and open weights | API only |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output | 384,000 tokens | 64,000 tokens |
| Input | text | text, image, video |
| Output | text | text |
When to choose each
DeepSeek-V4-Pro
Best for
- Agentic coding and terminal tasks
- Long-context jobs that need very long outputs
Watch out for
- The recorded rates are peak-hour prices (01:00 to 04:00 and 06:00 to 10:00 UTC on weekdays)
- No image input on the DeepSeek API, where the cheaper deepseek-flash has it
- DeepSeek had planned to retire it in September before extending service, so check its status before a long commitment
Step 5 Preview
Best for
- Long-context agentic coding and finance work
Watch out for
- A preview: StepFun publishes no release date, parameter count or benchmark scores for it
- Output tokens are billed including the reasoning trace, and output is capped at 64K tokens
DeepSeek-V4-Pro vs Step 5 Preview FAQ
Which is cheaper, DeepSeek-V4-Pro or Step 5 Preview?
Step 5 Preview is 24% cheaper per 1M input tokens than DeepSeek-V4-Pro, $1 vs $1.32. For 10M input and 2M output tokens, DeepSeek-V4-Pro costs $21.12 and Step 5 Preview $15.40 at standard rates.
Which has the larger context window, DeepSeek-V4-Pro or Step 5 Preview?
Both accept 1,000,000 tokens of context.
Can I run DeepSeek-V4-Pro or Step 5 Preview myself?
DeepSeek-V4-Pro is released as open weights you can run yourself; Step 5 Preview is available through its provider's API only.
Related comparisons
- DeepSeek-V4-Pro vs Gemini 3.6 Flash
- DeepSeek-V4-Pro vs GLM-5.3
- DeepSeek-V4-Pro vs GLM-5.3-Flash
- DeepSeek-V4-Pro vs Grok 4.20
- DeepSeek-V4-Pro vs Grok 4.3
- DeepSeek-V4-Pro vs Mistral Large 4
- DeepSeek-V4-Pro vs Muse Glimmer
- DeepSeek-V4-Pro vs Muse Spark 1.3
- DeepSeek-V4-Pro vs Nemotron 3.5 Lightning
- Grok 4.20 vs Step 5 Preview
Production evaluation
Choosing between DeepSeek-V4-Pro and Step 5 Preview?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty