Models

Step 3.7 Flash

stepfun ↗ · 262K ctx · 4 providers · updated 2026-08-04 22:15 UTC

Cheapest
$0.438 via OpenRouter
Avg price
$0.438 /1M
providers
4
Tokens (24h)
196B
Volume (24h)
$85.6K est.
(3 × $0.200 + $1.15) ÷ 4 = $0.438/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.200, 3:1 $0.438, 1:1 $0.675, output only $1.15 per 1M.

The board shows this model's cheapest measured offer ($0.438/1M); the smaller figure under it is the mean of the 4 offers listed below ($0.438/1M). Add those up and divide — it matches. 24h token volume (196B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here. Cross-check — Vercel AI Gateway: 5.26% of gateway token volume, —% of spend (2026-08-04; share-of-traffic, daily, data CC BY 4.0).

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
openrouter-best OpenRouter $0.200$1.15 API-measured
deepinfra HuggingFace Router $0.200$1.15 189ms 153 API-measured
novita-ai Novita AI $0.200$1.15 API-measured
requesty Requesty $0.200$1.15 API-measured

Volume trend

457B 30d d-29 · 204B tokensd-28 · 234B tokensd-27 · 192B tokensd-26 · 170B tokensd-25 · 159B tokensd-24 · 172B tokensd-23 · 157B tokensd-22 · 134B tokensd-21 · 117B tokensd-20 · 103B tokensd-19 · 105B tokensd-18 · 106B tokensd-17 · 112B tokensd-16 · 101B tokensd-15 · 106B tokensd-14 · 123B tokensd-13 · 308B tokensd-12 · 457B tokensd-11 · 390B tokensd-10 · 244B tokensd-9 · 205B tokensd-8 · 193B tokensd-7 · 227B tokensd-6 · 266B tokensd-5 · 325B tokensd-4 · 282B tokensd-3 · 202B tokensd-2 · 178B tokensd-1 · 175B tokensd-0 · 196B tokens

Last 30 days: 204B → 196B (-4%); range 101B–457B tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/step-3.7-flash.json. Free reuse requires attribution to tkx.org.

About

Step 3.7 Flash is an AI model served by multiple inference providers on AI model marketplaces, known for its role in natural language processing tasks. It falls under the organization tag "stepfun" on the serving platform.

AI-generated summary from public information — is this yours?

FAQ

How much does Step 3.7 Flash cost?

Cheapest measured offer right now: $0.2/1M input, $1.15/1M output via openrouter-best — across 4 tracked providers, refreshed hourly.

Who serves Step 3.7 Flash?

4 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is Step 3.7 Flash used?

Step 3.7 Flash routed 196B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings