Step 3.7 Flash APITESTEDOPEN WEIGHTS256K context
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model.
Pricing & specs mirror our live pricing as of July 2026 (pay-as-you-go). Coding score is our own measured result.
✅ First-party tested — we ran Step 3.7 Flash on our 9-task coding suite
Missed: LFU cache, quicksort fix. Executed against hidden tests at real billed cost — full results · how we test.
What is Step 3.7 Flash?
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
Step 3.7 Flash pricing
Pay-as-you-go on DataLLM Lab — these are our live list prices (identical to the pricing page):
| Model | Input / 1M | Output / 1M | Cache read | Cache write | Context |
|---|---|---|---|---|---|
| Step 3.7 Flash | $0.20 | $1.15 | $0.04 | — | 256K |
On output price, Step 3.7 Flash is cheaper than 58% of the 309 models in the catalog.
What Step 3.7 Flash costs per month
| Workload | Tokens in / out (monthly) | Est. cost |
|---|---|---|
| Support chatbot | 40M / 12M | $21.80 |
| RAG / knowledge base | 200M / 20M | $63.00 |
| Coding agent | 80M / 25M | $44.75 |
| Batch extraction | 150M / 8M | $39.20 |
| Content generation | 20M / 40M | $50.00 |
Estimate your own monthly cost
Cost = input price × input volume + output price × output volume. The same five workloads run on every model page, so any two compare directly.
Step 3.7 Flash vs alternatives
| Model | Input / 1M | Output / 1M | Context | Our test |
|---|---|---|---|---|
| Step 3.7 Flash | $0.20 | $1.15 | 256K | 7/9 |
| Step 3.5 Flash | $0.10 | $0.30 | 262K | — |
| Qwen3.6 Flash | $0.19 | $1.13 | 1M | — |
| MiniMax-01 | $0.20 | $1.10 | 1M | — |
| Qwen3 Next 80B A3B Instruct | $0.09 | $1.10 | 262K | — |
Specs
| Model ID | stepfun/step-3.7-flash |
| Modality | text+image+video->text (input: text, image, video) |
| Context window | 256,000 tokens |
| Max output | 256,000 tokens |
| Tool / function calling | ✅ Yes |
| Structured output (JSON) | ✅ Yes |
| Released | 2026-05-28 |
| Open weights | ✅ stepfun-ai/Step-3.7-Flash |
How to call Step 3.7 Flash
from openai import OpenAI
client = OpenAI(base_url="https://api.datallmlab.com/v1", api_key="YOUR_DATALLM_LAB_KEY")
resp = client.chat.completions.create(
model="stepfun/step-3.7-flash",
messages=[{"role": "user", "content": "Hello"}],
# supports tools=[...] and tool_choice
)
print(resp.choices[0].message.content)curl https://api.datallmlab.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"stepfun/step-3.7-flash","messages":[{"role":"user","content":"Hello"}]}'import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.datallmlab.com/v1", apiKey: process.env.DATALLM_KEY });
const r = await client.chat.completions.create({
model: "stepfun/step-3.7-flash",
messages: [{ role: "user", content: "Hello" }],
});
console.log(r.choices[0].message.content);The same key routes Step 3.7 Flash and 300+ other models — switch models by changing one string. How OpenAI-compatible APIs work.
Prompting tips for Step 3.7 Flash
- State the goal, not every step. Step 3.7 Flash reasons internally — give it the objective, constraints and success criteria and let it plan the approach; over-scripting each step tends to lower quality. Turn effort up for hard problems.
- Huge 256K context — but anchor the ask. You can paste whole documents or codebases; models attend most to the start and end, so put the key instruction at the top and restate it after long inputs.
- It reads images. Send image parts alongside your text and ask for specific outputs (named JSON fields, a table, "what changed") rather than "describe this".
- Give it real tools. Pass a
tools=[...]schema instead of asking it to "pretend" — let Step 3.7 Flash emit tool calls, execute them, and feed results back for the next turn. - Constrain JSON with a schema. Use
response_format/ structured outputs rather than "reply in JSON" to get valid, parseable objects every time.
Tips are derived from Step 3.7 Flash's actual capabilities — context window, tool & JSON support, modality and price tier — not generic advice.
Open-source tools for Step 3.7 Flash
Popular open-source projects for running and building with Step 3.7 Flash — star counts pulled from GitHub (July 2026).
Listed by GitHub stars; inclusion is by ecosystem relevance (inference engines, agent frameworks and SDKs), not affiliation. Stars change — see each repo for current numbers.
Migrating to Step 3.7 Flash
Coming from OpenAI or another gateway? On an OpenAI-compatible setup the only changes are base_url → https://api.datallmlab.com/v1 and model → stepfun/step-3.7-flash. Messages, streaming, tool calls and the rest of your code stay the same. Routing & failover guide.
Self-host or use the API?
Step 3.7 Flash ships open weights (stepfun-ai/Step-3.7-Flash), so you can run it yourself. Most teams still use the API: no GPU to provision or keep warm, no inference ops, and instant access across multiple providers with automatic failover. Self-host when data residency or fixed per-token economics matter most.
Rate limits & reliability
Rate limits here are the DataLLM Lab gateway's, not the upstream vendor's. On 429 (rate limited) or 503 (provider busy), retry with exponential backoff. See the error-code guide and failover setup.
Related reading
Call Step 3.7 Flash with one key
300+ models behind one OpenAI-compatible endpoint — better prices, better uptime, no subscriptions.
Get an API keyCompare pricingFrequently asked questions
What is Step 3.7 Flash?
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It accepts text, image, video input with a 256K-token context window and was released on 2026-05-28. On DataLLM Lab it is callable through one OpenAI-compatible endpoint.
How much does Step 3.7 Flash cost?
On DataLLM Lab it is $0.20 per 1M input tokens and $1.15 per 1M output tokens, with cached input at $0.04/1M — cheaper than about 58% of the 309-model catalog on output price. Pay-as-you-go, no subscription.
What is the context window of Step 3.7 Flash?
256K tokens, with up to 256K max output tokens.
Is Step 3.7 Flash open source?
Yes — open weights are published on Hugging Face (stepfun-ai/Step-3.7-Flash). You can self-host it or call it via DataLLM Lab.
How do I call the Step 3.7 Flash API?
Point any OpenAI SDK at https://api.datallmlab.com/v1 and set model to "stepfun/step-3.7-flash". One DataLLM Lab key routes this model and 300+ others; no code changes beyond the base URL and model string.
How did Step 3.7 Flash score in real testing?
In our executed 9-task coding benchmark it scored 7/9 (missed: LFU cache, quicksort fix), averaging 31.6s per task at ~$4.74 per 1,000 tasks (real billed cost). See our methodology for scope and limits.