IBM
EfficientRETIREDAUTO PROFILEPriced via OpenRouter

Granite 4.0 Micro

text->text

Granite 4.0 Micro is a compact variant, chosen for high throughput and low cost rather than absolute capability. Available via IBM. 131,000-token context. Budget pricing.

Granite 4.0 Micro is a efficient AI model from IBM. It costs $0.0170 per million input tokens and $0.1120 per million output tokens (blended $0.0455/M), with a 131,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.0170/M
per million input tokens
OUTPUT
$0.1120/M
per million output tokens
BLENDED 70/30
$0.0455/M

0.0%over 91 days · hover to read

Granite 4.0 Micro — blended price

Reconstructed from 91 days of recorded rate-card changes. Prices hold flat between changes because that is what a posted price does — no value here is interpolated.

CONTEXT
131,000
tokens

The last price on OpenRouter's listing; the model left the feed by 3 Nov 2026.

What it is good at
  • Sub-second latency
  • Affordable at scale
  • Good for routing & classification
Typical use cases
  • Routing & classification
  • Bulk summarisation
  • Realtime chat UX

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from IBM

See all 5 →

Price history

1 recorded change
Recorded price changes for Granite 4.0 Micro, newest first
DateRateWasNowChange
16 May 2026Output$0.1100$0.1120+1.8%

Rates per million tokens, as published by the provider or its router listing. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.

Frequently asked questions

How much does Granite 4.0 Micro cost?

Granite 4.0 Micro costs $0.0170 per million input tokens and $0.1120 per million output tokens, for a blended reference rate of $0.0455 per million tokens.

What is Granite 4.0 Micro's context window?

Granite 4.0 Micro supports up to 131,000 tokens of context in a single request.

What is Granite 4.0 Micro best for?

Granite 4.0 Micro is well suited to Sub-second latency, Affordable at scale and Good for routing & classification.

Who makes Granite 4.0 Micro?

Granite 4.0 Micro is developed and served by IBM.

Terms used on this page