ibm-granite Open weights

Granite 4.1 8B pricing & benchmarks

Released Apr 30, 2026 · served by 1 provider

Input / 1M tokens$0.050
Output / 1M tokens$0.100
Context window131K
Cached input$0.050
Coding index9.5
1M in + 300K out$0.08

What Granite 4.1 8B is

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

Providers and prices for Granite 4.1 8B

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
CoreWeavecheapest $0.050 $0.100 131K bf16 100.0%

FAQ

How much does the Granite 4.1 8B API cost?

$0.050 per 1M input tokens and $0.100 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.08.

Is Granite 4.1 8B free?

No. It is a paid model starting at $0.050 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Granite 4.1 8B?

CoreWeave at $0.050 input / $0.100 output per 1M tokens (bf16 quantization).

Can I self-host Granite 4.1 8B?

Yes — weights are published as ibm-granite/granite-4.1-8b on Hugging Face, so you can run it on your own hardware.