Context
262K
Max output
256K
Serving providers
3
Cheapest input
$0.20 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis and Hugging Face leaderboards
Speed & latency
Output speed
88 t/s
tokens / second
Time to first token
2.75s
latency
Headline indices
39.6
of 100
21.7
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
APEX Agents15%default
Automation Bench0.1default
CritPt2%default
EvalComputeProxy435.3default
GDPval1017.7default
GPQA Diamond81%default
Harvey Lab0.7default
Humanity's Last Exam21%default
IFBench67%default
IT-Bench SRE30%default
Long-Context Reasoning70%default
MMMU-Pro75%default
Omniscience-37.3default
Omniscience Accuracy0.3default
Omniscience Non Hallucination0.2default
SciCode40%default
SWE-bench Pro56%default
TerminalBench Hard36%default
TerminalBench v2.139%default
τ-bench Banking12%default
τ²-bench99%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
NovitaCheapest$0.20$1.151
EndpointStd inStd outCached inBatch in / outModel ID
StandardCheapest$0.20$1.15$0.04novita/stepfun/step-3.7-flash
DeepInfraCheapest$0.20$1.151
OpenRouterCheapest$0.20$1.151

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.500$1.00$1.50Jul 19Aug 28$1.15$0.200

Cost calculator

estimate your monthly spend on this model
$132
estimated / month

Model IDs

copy the exact identifier for your platform
novita/stepfun/step-3.7-flashdeepinfra/stepfun-ai/Step-3.7-Flashstepfun/step-3.7-flash

Frequently asked questions

Step 3.7 Flash pricing, context and availability

How much does Step 3.7 Flash cost?

Step 3.7 Flash costs $0.20 per 1M input tokens and $1.15 per 1M output tokens at its cheapest provider via Novita.

What is the context window of Step 3.7 Flash?

Step 3.7 Flash accepts up to 262K tokens of context and can return up to 256K output tokens.

Which providers serve Step 3.7 Flash?

Step 3.7 Flash is available from 3 serving providers, each with its own pricing and model ID. Novita is currently the cheapest.

What can Step 3.7 Flash do?

Step 3.7 Flash supports image input (vision), tool use, reasoning, prompt caching and structured output.

Other Other models

compare pricing across the Other lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI