StepFun: Models Intelligence, Performance & Price

Name: Intelligence
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

StepFun

This analysis is intended to support you in choosing the best model provided by StepFun for your use-case.

Most Intelligent

Step 5 Preview

Step 3.7 Flash

Step 3.5 Flash 2603

Step 3.5 Flash

Intelligence Index

Total 4 models

Fastest

Step 5 Preview

189 t/s

Step 3.5 Flash 2603

183 t/s

Step 3.5 Flash

178 t/s

Step 3.7 Flash

111 t/s

Output speed

Total 4 models

Lowest Price

Step 3.5 Flash 2603

$0.06

Step 3.5 Flash

$0.06

Step 3.7 Flash

$0.18

Step 5 Preview

$0.54

Blended price (per 1M tokens)

Total 4 models

StepFun offers 4 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.

For intelligence, the top models on StepFun are Step 5 Preview (44), Step 3.7 Flash (19), and Step 3.5 Flash 2603 (17).
For output speed, the fastest models are Step 5 Preview (189 t/s), Step 3.5 Flash 2603 (183 t/s), and Step 3.5 Flash (178 t/s). Speed varies significantly across models, with a 71% difference between the fastest and slowest.
For latency, Step 5 Preview (11.82s), Step 3.5 Flash 2603 (14.28s), and Step 3.5 Flash (14.54s) offer the lowest time to first answer token.
For pricing, Step 3.5 Flash 2603 ($0.06), Step 3.5 Flash ($0.06), and Step 3.7 Flash ($0.18) offer the lowest blended prices per 1M tokens. Prices vary up to 8.4x across models.
For context window size, Step 5 Preview (1M), Step 3.7 Flash (256k), and Step 3.5 Flash 2603 (256k) support the largest context windows on StepFun.
Step 5 Preview offers the best combination of intelligence and speed. For cost optimization, Step 3.5 Flash 2603 provides the most competitive pricing.

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Price

USD per 1M tokens (blended) · Lower is better

Intelligence Evaluations

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Estimate (independent evaluation forthcoming)

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Evaluations

Evaluations measured independently by Artificial Analysis · AA-PersonalityBench scores are percentile ranks from 1 to 100

AA-Briefcase v1.1

Agentic knowledge work, Elo

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AutomationBench-AA

Agentic SaaS workflows

GDPval-AA v2.1

Agentic real-world work tasks, Elo

Humanity's Last Exam

Reasoning & knowledge

GDP.pdf

Professional document reasoning, All-pass

Terminal-Bench 4.0

Agentic coding & terminal use

AA-LCR v1.1

Long context reasoning

SciCodeUnder review

Coding

CritPt

Physics reasoning

Terminal-Bench-Science 0.1New

Agentic scientific research workflows in a terminal

FrontierCode 1.1New

Agentic software engineering in open-source repositories

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

Harvey LAB-AA v1.1Updated

Legal agentic work, Hallucination-Gated All-Pass Rate

No data available

EnterpriseOps-Gym-AA

Agentic business operations

AA-3DNew

Agentic interactive 3D experiences, Elo

Code2Video-AANew

Product and brand videos designed in code, Elo

ITBench-AA

Kubernetes incident root-cause analysis

MLCR-AAUpdated

Medical long context reasoning

MMMU-Pro

Visual reasoning

AA-PersonalityBench: Expressiveness ScoreNew

Rich, varied, well-crafted language

AA-PersonalityBench: Organization ScoreNew

Well-structured, scannable, answer-first

AA-PersonalityBench: Transparency ScoreNew

Truthful, acknowledges uncertainty, non-sycophantic

AA-PersonalityBench: Slop ScoreNew

Use of filler and generic language

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

Pareto line

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Context Window

Context window: tokens limit · Higher is better

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Pricing

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

Pareto line

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Performance Summary

Output Speed vs. Price

Output speed: output tokens per second · USD per 1M tokens (blended)

Most attractive quadrant

Pareto line

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output tokens per second · Higher is better

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Latency

Measured by Time (seconds) to First Token

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Cache Behaviour

Cache Hit Rate

Share of cacheable input tokens served from cache · Median of the last four weeks, updated Oct 26, 2026

The share of cacheable input tokens served from the provider's prompt cache, measured during multi-turn agentic coding sessions. We regularly measure each endpoint and report a representative rate based on recent measurements. Higher values mean more of the input is billed at the cheaper cache-hit price, where the provider offers one, which lowers the effective cost of agentic workloads. For further details, see our methodology page.

Cost per Task vs. Cache Hit Rate

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026

Most attractive quadrant

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

End-to-End Response Time

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time vs. Price

End-to-end response time: end-to-end seconds to output 500 tokens · USD per 1M tokens (blended)

Most attractive quadrant

Pareto line

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).


									Further Analysis
Step 5 Preview	1M	Open	44	$1.03	191	1.26	14.34	10.46	Model Provider
Step 3.7 Flash	256k	Open	19*	--	112	2.57	24.96	17.91	Model Provider
Step 3.5 Flash 2603	256k	Proprietary	17*	--	183	3.35	17.02	10.93	Model Provider
Step 3.5 Flash	256k	Open	17*	--	178	3.34	17.34	11.21	Model Provider

Key definitions

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Frequently Asked Questions

Common questions about StepFun

StepFun offers 4 models that we track: Step 5 Preview, Step 3.7 Flash, Step 3.5 Flash 2603, and Step 3.5 Flash.

The most intelligent model available on StepFun is Step 5 Preview with an Intelligence Index score of 44.

The fastest model on StepFun by output speed is Step 5 Preview at 189.0 tokens per second.

The model with the lowest time to first answer token on StepFun is Step 5 Preview at 11.82s. Lower latency means faster initial response time.

The most affordable model on StepFun by blended price is Step 3.5 Flash 2603 at $0.06 per 1M tokens (7:2:1 cache hit/input/output ratio).

Prices on StepFun vary up to 8x across models, from $0.06 per 1M tokens for Step 3.5 Flash 2603 to $0.54 per 1M tokens for Step 5 Preview.

Yes, StepFun offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.

Yes, all 4 models on StepFun support JSON mode for structured output.

Yes, all 4 models on StepFun support function calling (tool use).

Yes, StepFun offers 4 reasoning models: Step 5 Preview, Step 3.7 Flash, Step 3.5 Flash 2603, and Step 3.5 Flash. Reasoning models use extended thinking to work through complex problems before providing an answer.

Yes, 3 of 4 models on StepFun are open weight models: Step 5 Preview, Step 3.7 Flash, and Step 3.5 Flash.

Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.

When choosing a model on StepFun, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.

StepFun: Models Intelligence, Performance & Price

Most Intelligent

Fastest

Lowest Price

Intelligence

Speed

Price

Intelligence Evaluations

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Intelligence Index vs. Price

Price-Quality Variance

Context Window

Context Window

Context Window for RAG

Context Window

Pricing

Intelligence Index vs. Price

Price-Quality Variance

Performance Summary

Output Speed vs. Price

Output Speed

Price

Speed

Output Speed

Output Speed

Model Performance Representation

Latency

Latency: Time To First Answer Token

Time to First Answer Token

Cache Behaviour

Cache Hit Rate

What Cache Hit Rate Shows

Cost per Task vs. Cache Hit Rate

Cost per Intelligence Index Task

End-to-End Response Time

End-to-End Response Time vs. Price

Price

Key definitions

Context Window

Frequently Asked Questions

What models does StepFun offer?

What is the most intelligent model on StepFun?

What is the fastest model on StepFun?

Which model has the lowest latency on StepFun?

What is the cheapest model on StepFun?

How much do prices vary across models on StepFun?

Is StepFun OpenAI compatible?

Does StepFun support JSON mode?

Does StepFun support function calling?

Does StepFun offer reasoning models?

Does StepFun offer open weight models?

Does StepFun's performance change over time?

How do I choose a model on StepFun?