Start free trial

StepFun: Step 5 Preview

stepfun/step-5-preview
CompareAPITry this model

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters).

Modalities
In / out per 1M$1.00 / $2.70
Context1M
ReleasedOct 8, 2026

Providers

4 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
StepFunfp8$1.00$2.70$0.101.27s122 tps100%
inference.netfp4$1.00$2.70$0.051.74s142 tps99.96%
DeepInfraus · fp8$1.00$2.70$0.100.56s43 tps98.06%
Featherlessfp4$1.00$2.70$0.103.07s37 tps96.81%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Step 5 Preview in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Step 5 Preview costs pay-as-you-go elsewhere, not what you pay here.

Input
$1.00
per 1M tokens
Output
$2.70
per 1M tokens
Cache read
$0.10
per 1M cached tokens
Included in every pass
Step 5 Preview is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s25.0s50.0s75.0s100.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DeepInfra (us) StepFun Featherless inference.net
0 tok/s200 tok/s400 tok/s600 tok/s800 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DeepInfra (us) StepFun Featherless inference.net

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.84%
Oct 16, 11:00 AMNow
Availability over the last 24 hoursAvailability 99.77%
100% 97% 93% 90%
Oct 18, 11:00 AMNow

Apps

Tools that most often run Step 5 Preview, by tokens this week.

Hermes AgentPersonal Agent · 34.9% of tokens3186.8BKilo CodeCli Agent · 25.7% of tokens2344.4BOpenClawPersonal Agent · 18.1% of tokens1654.8BClineIde Extension · 13.7% of tokens1249.7BStepCodeCli Agent · 7.6% of tokens695.3B

Activity

20305.1B tokens processed market-wide in the last month.

01000.0B2000.0B3000.0B4000.0B
Oct 8Oct 9Oct 10Oct 11Oct 12Oct 13Oct 14Oct 15Oct 16Oct 17Oct 18Oct 19
Tokens

FAQ

Which model id do I use for Step 5 Preview?
stepfun/step-5-preview. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Step 5 Preview hold?
1,048,576 tokens per request, of which up to 64,000 can be the response.
What can it accept and return?
Input: text, image, video. Output: text.
What does Step 5 Preview cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $1.00 per 1M input tokens and $2.70 per 1M output tokens.
Who built Step 5 Preview?
StepFun, in the Step family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion