InferIndex
Language, English, EN
Account

ModelsStepFunStep 3.7 Flash

Step 3.7 Flash

stepfun/step-3.7-flash33k context Compare →
MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.438
Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.438
Offers
21
Providers
14

Cheapest right now

Featherless

directYou buy access straight from the company that runs the model on its servers. · 33k

$0.438 blended / 1M tokens

No change7D
in
$0.20
out
$1.15
Cached input
–

Step 3.7 Flash costs from $0.438 per million tokens (at a 3:1 input:output mix): the lowest current price, at 8 providers, checked on ; 21 offers are listed.

Listed offers, by price

Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.

Offers not counted in cheapest, median or most expensive (13)

  • $0.438 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.438 · FlexAI via Eden AI · cannot be designated the cheapest
  • $0.438 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $0.438 · StepFun via Kilo Gateway · cannot be designated the cheapest
  • $0.438 · Glama via Glama · cannot be designated the cheapest
  • $0.438 · Martian via Martian · cannot be designated the cheapest
  • $0.438 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.438 · Novita via LLM Gateway · another route of the same provider
  • $0.438 · DeepInfra via LLM Gateway · cannot be designated the cheapest
  • $0.438 · Novita via Requesty · another route of the same provider
  • $0.438 · Novita via OpenRouter · another route of the same provider
  • $0.457 · Qiniu · cannot be designated the cheapest
  • $0.457 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest

Cheapest that confirms no training on your prompts. The provider's published policy: prompts are not used for training.

DeepInfra

Hugging Face · 262k

$0.438 blended / 1M tokens

in
$0.20
out
$1.15
Cached input
–

Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.

Cheapest offer and official list price, by day, 30 days
DayCheapest offerOfficial list price
2026-10-02$0.35, DeepInfra–
2026-10-03$0.438, Featherless–
2026-10-04$0.438, Featherless–
2026-10-05$0.438, Featherless–
2026-10-06$0.438, Featherless–
2026-10-07$0.438, Featherless–
2026-10-08$0.438, Featherless–
2026-10-09$0.438, Featherless–
2026-10-10$0.438, Featherless–
2026-10-11$0.438, Featherless–
2026-10-12$0.438, Featherless–
2026-10-13$0.438, Featherless–
2026-10-14$0.438, Featherless–
2026-10-15$0.438, Featherless–
2026-10-16$0.438, Featherless–
2026-10-17$0.438, Featherless–
2026-10-18$0.438, Featherless–
2026-10-19$0.438, Featherless–
2026-10-20$0.438, Featherless–
2026-10-21$0.438, Featherless–
2026-10-22$0.438, Featherless–
2026-10-23$0.438, Featherless–
2026-10-24$0.438, Featherless–
2026-10-25$0.438, Featherless–
2026-10-26$0.438, Featherless–
2026-10-27$0.438, Featherless–
2026-10-28$0.438, Featherless–
2026-10-29$0.438, Featherless–
2026-10-30$0.438, Featherless–
2026-10-31$0.438, Featherless–

Cheapest offerPromotional price

Offers

21 of 21 offers

Offers for Step 3.7 Flash, one row per offer, sorted by blended price.
RankProvider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.Input $/1MOutput $/1MBlended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.SignalsOffer
1 Featherless 0.20  1.15 0.438 – 33k
2 DeepInfravia Hugging Face 0.20  1.15 0.438 – 262k United States
3 EmpirioLabs AI 0.20  1.15 0.438 – 262k
4 Novita 0.20  1.15 0.438 fp8 262k
5 DeepInfravia Eden AI 0.20  1.15 0.438 – 262k United States Unverified. No public page for this offer: listed, not designated cheapest
6 FlexAIvia Eden AI 0.20  1.15 0.438 – 262k Unverified. No public page for this offer: listed, not designated cheapest
7 Novitavia Kilo Gateway 0.20  1.15 0.438 fp8 262k Unverified. No public page for this offer: listed, not designated cheapest
8 StepFunvia Kilo Gateway 0.20  1.15 0.438 fp8 256k Unverified. No public page for this offer: listed, not designated cheapest
9 Glama 0.20  1.15 0.438 – 256k Unverified. No public page for this offer: listed, not designated cheapest
10 Martian 0.20  1.15 0.438 – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
11 NanoGPT 0.20  1.15 0.438 – 262k Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists
12 Nous Portal 0.20  1.15 0.438 – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
13 Vercel AI Gateway 0.20  1.15 0.438 – –
14 ZenMux 0.20  1.15 0.438 – 256k
15 Novitavia LLM Gateway 0.20  1.15 0.438 fp8 – Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
16 DeepInfravia LLM Gateway 0.20  1.15 0.438 – – United States Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
17 Novitavia Requesty 0.20  1.15 0.438 fp8 262k Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
18 Novitavia OpenRouter 0.20  1.15 0.438 fp8 262k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
19 StepFunvia OpenRouter 0.20  1.15 0.438 fp8 256k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
20 Qiniu 0.203 1.22 0.457 – 256k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest · last confirmed 25 October 2026
21 ShengSuanYun 0.203 1.22 0.457 – 256k Unverified. No public page for this offer: listed, not designated cheapest

No training on promptsPrompts may be used for trainingTraining terms not published

backend not named. The router bills this price itself without naming who serves the model.

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method

Monthly cost for your workload

Computed by the API for the three cheapest offers, per 30-day month.
  1. Featherless$29.25per month
  2. DeepInfra$29.25per month+$0.00 vs the cheapest
  3. EmpirioLabs AI$29.25per month+$0.00 vs the cheapest

Host it yourself instead? See the break-even

Compare Step 3.7 Flash with

Related models

More from StepFun

All StepFun models

Same index family

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=stepfun/step-3.7-flash
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

Also works in Cursor and Codex: see the MCP page.