Step 3.7 Flash vs MiMo V2.6 Pro

rates, context and capabilities side by side on the impossibl api, and what the same workload costs on each.

the models at a glance: base rates, context window and modalities
specificationStep 3.7 Flash

stepfun/step-3.7-flash

MiMo V2.6 Pro

xiaomi/mimo-v2.6-pro

input · usd / 1m tok$0.20$0.435
output · usd / 1m tok$1.15$0.87
context window262.14ktokens1.05mtokens
modalities · in → out

takes text and image in, gives text out

takes text and image in, gives text out

pricing

base api rates by model
base api rates · usd per 1m tokensStep 3.7 Flash

stepfun/step-3.7-flash

MiMo V2.6 Pro

xiaomi/mimo-v2.6-pro

input$0.20$0.435
output$1.15$0.87
cache read$0.04$0.0036

the estimate below prices one workload at these rates on every model.

specifications

published specifications by model
as publishedStep 3.7 Flash

stepfun/step-3.7-flash

MiMo V2.6 Pro

xiaomi/mimo-v2.6-pro

creatorStepFunXiaomi
model typeText generationText generation
context window262,144tokens1,048,576tokens
input

takes text and image in, gives text out

takes text and image in, gives text out

outputtexttext
tool callingnot verifiednot verified
releasedmay 29, 2026not published
endpoint/v1/chat/completions/v1/chat/completions

unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.

benchmarks

benchmark scores by model, primary tested configuration
primary configurationStep 3.7 Flash

stepfun/step-3.7-flash

MiMo V2.6 Pro

xiaomi/mimo-v2.6-pro

intelligence index · gateway rank19.5#77 of 10846.3#14 of 108
omniscience-37.3#73 of 848.4#23 of 84
gpqa80.9%#56 of 80
not measured
humanity’s last exam21.4%#58 of 87
49.4%#6 of 87
tau298.5%
not measured
mmmu-pro75.3%
not measured
aa-lcr73.7%
86.3%
ifbench67.3%
not measured
scicode43.9%
60.9%
terminal-bench hard35.6%
not measured
itbench30.3%
not measured
apex-agents14.8%
not measured
tau banking12.0%
not measured
critpt2.3%
26.6%
automationbench partialnot measured58.6%
analystagentnot measured37.5%
gdp.pdf all-passnot measured19.2%
multilingual lcrnot measured18.3%

Step 3.7 Flash source ↗MiMo V2.6 Pro source ↗

each column describes the tested configuration named under the model; performance and costs can differ on impossibl. a score one model was not measured on is left blank rather than scored zero. indices are ranked against every model on the gateway with one. last checked 2026-10-14.

estimate your cost

one token workload, priced on every model at the published rates, in usd. change the numbers to match yours.

token workload

total input, including cached tokens

include billable reasoning tokens

the same token usage in each request

a subset of total input, never additional tokens

Step 3.7 Flash

stepfun/step-3.7-flash

estimated usage cost

$0.775

1,000 requests × (1,000 uncached input × $0.20 + 500 output × $1.15) / 1,000,000 = $0.775

base rates; no context pricing tiers are published.

MiMo V2.6 Pro

xiaomi/mimo-v2.6-pro

estimated usage cost

$0.87

1,000 requests × (1,000 uncached input × $0.435 + 500 output × $0.87) / 1,000,000 = $0.87

base rates; no context pricing tiers are published.

estimates use published impossibl api usage rates. configured billing adjustments, funding fees, taxes, and custom workspace rates are excluded and may change the final amount.

image and audio usage, cache creation, and additional tool charges are excluded. reasoning tokens count as billable output, even when they are not visible in the response.

summary

Step 3.7 Flash and MiMo V2.6 Pro are available through the Impossibl API. they share the /v1/chat/completions endpoint; the model identifier selects the model for a request.

Step 3.7 Flash is created by StepFun. It has a 262,144-token context window. Base API pricing (USD): $0.20 per million input tokens; $1.15 per million output tokens.

MiMo V2.6 Pro is created by Xiaomi. It has a 1,048,576-token context window. Base API pricing (USD): $0.435 per million input tokens; $0.87 per million output tokens.

Step 3.7 Flash →MiMo V2.6 Pro →

this page compares Step 3.7 Flash vs MiMo V2.6 Pro as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes.

view the source catalog ↗comparison as markdown ↗report a correction →