Selector retired June 30, 2026, after routing to mimo-v2.5-pro from June 1. Historical launch pricing below is not a current offer.
Regions
API cluster/account specific; no residency or jurisdiction guarantee inferred.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Historical text inference
Input · up to 256K input1
$1.00
1M tokens
Historical text inference
Output · up to 256K input1
$3.00
1M tokens
Historical text inference
Cache read · up to 256K input1
$0.20
1M tokens
Historical text inference
Cache write · up to 256K input1
$0.00
1M tokens
Historical text inference
Input · 256K–1M input2
$2.00
1M tokens
Historical text inference
Output · 256K–1M input2
$6.00
1M tokens
Historical text inference
Cache read · 256K–1M input2
$0.40
1M tokens
Historical text inference
Cache write · 256K–1M input2
$0.00
1M tokens
Rate conditions
March 18, 2026 launch price; direct model selector retired June 30, 2026. Not a current offer. Tier: up to 256K input. Cache-write zero was a limited-time offer; no exact promotion end established.
March 18, 2026 launch price; direct model selector retired June 30, 2026. Not a current offer. Tier: 256K–1M input. Cache-write zero was a limited-time offer; no exact promotion end established.
March 18, 2026 launch price; direct model selector retired June 30, 2026. Not a current offer. Tier: up to 256K input. Cache-write zero was a limited-time offer; no exact promotion end established.
March 18, 2026 launch price; direct model selector retired June 30, 2026. Not a current offer. Tier: 256K–1M input. Cache-write zero was a limited-time offer; no exact promotion end established.
Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Caching reviewed 14 Oct 2026
OpenRouter (no active route)
xiaomi/mimo-v2-pro
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected
No verified cache rate for this endpoint. An empty rate is not a zero charge.
What the measurements say
PinchBench (avg.)
Xiaomi MiMo · provider-reported
81%
Historical March 18, 2026 release-page result. Agent benchmarks depend on the evaluation framework and tools; provider chart reports percentages except Elo-labeled metrics. Not independently rerun, not a live rank and not a score for later V2.5/V2.6 or preview builds.
Historical March 18, 2026 release-page result. Agent benchmarks depend on the evaluation framework and tools; provider chart reports percentages except Elo-labeled metrics. Not independently rerun, not a live rank and not a score for later V2.5/V2.6 or preview builds.
Historical March 18, 2026 release-page result. Agent benchmarks depend on the evaluation framework and tools; provider chart reports percentages except Elo-labeled metrics. Not independently rerun, not a live rank and not a score for later V2.5/V2.6 or preview builds.
Historical March 18, 2026 release-page result. Agent benchmarks depend on the evaluation framework and tools; provider chart reports percentages except Elo-labeled metrics. Not independently rerun, not a live rank and not a score for later V2.5/V2.6 or preview builds.
Historical March 18, 2026 release-page result. Agent benchmarks depend on the evaluation framework and tools; provider chart reports percentages except Elo-labeled metrics. Not independently rerun, not a live rank and not a score for later V2.5/V2.6 or preview builds.
Historical March 18, 2026 release-page result. Agent benchmarks depend on the evaluation framework and tools; provider chart reports percentages except Elo-labeled metrics. Not independently rerun, not a live rank and not a score for later V2.5/V2.6 or preview builds.
Historical March 18, 2026 release-page result. Agent benchmarks depend on the evaluation framework and tools; provider chart reports percentages except Elo-labeled metrics. Not independently rerun, not a live rank and not a score for later V2.5/V2.6 or preview builds.
Historical March 18, 2026 release-page result. Agent benchmarks depend on the evaluation framework and tools; provider chart reports percentages except Elo-labeled metrics. Not independently rerun, not a live rank and not a score for later V2.5/V2.6 or preview builds.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Inferred closed-weight classification for this exact hosted MiMo release from the original release description and developer public-weight inventory. The matching weights were not found. Later MiMo V2.5/V2.6 language weights and MiMo V2.5 ASR are explicitly public and are not substituted for this release; public MiMo-Audio components do not establish public weights for the separate TTS service.
