Compare DeepSeek V3.1 Fast from DeepSeek and Step 3.7 Flash from StepFun on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
DeepSeek V3.1 Fast
Step 3.7 FlashThe model provider is the Sophon platform. DeepSeek V3.1 Fast is the high-TPS speed version of DeepSeek V3.1. Hybrid thinking mode: By modifying the chat template, a single model can simultaneously support both thinking and non-thinking modes. Smarter tool usage: Through post-training optimization, the model’s performance in tool utilization and agent tasks has improved significantly.
step-3.7-flash is stepfun's flagship inference model, designed for high-complexity tasks that require deep reasoning and fast execution. It excels at decomposing multi-step problems, performing tool calls, and maintaining consistency across massive datasets. It is the preferred choice for complex workloads such as long-context agents, advanced software engineering, and end-to-end research automation.
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
Step 3.7 Flash: $1.32/M output tokens; DeepSeek V3.1 Fast: $3.288/M. Use the cost calculator above to estimate your own workload.
DeepSeek V3.1 Fast: 0.2s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
DeepSeek V3.1 Fast accepts 163,000 and Step 3.7 Flash accepts 256,000 input tokens.
DeepSeek V3.1 Fast at 150.0 tok/s and Step 3.7 Flash at 32.6 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
DeepSeek V3.1 Fast accepts text input and supports tool calling, function calling and structured outputs; Step 3.7 Flash accepts text, image and video input.
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Related model match-ups readers also look at.