Granite 4.1 8B
IBM Granite · Open weights · Released Apr 30, 2026 · ibm-granite/granite-4.1-8b
131K contextToolsStructured outputPrompt cachingOpen weights
Available from 1 providerUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| CWCoreWeave | $0.05 | $0.10 | $0.05 | 131K | bf16 | 0.41s | 118 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 44 hours ago
Pricing variants · USD / MTok in / out
STANDARD
$0.05 / $0.10
per MTok in / out
CACHE READ $0.05
About
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...
Specifications
Context window131,072
Max output131,072
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedApr 30, 2026
TokenizerOther
WeightsHugging Face ↗
Open weights
safetensors
Embed badge
[](https://modelindex.ai/models/ibm-granite/granite-4.1-8b)Sources
OpenRouter API4 minutes ago
AGGREGATORHugging Face4 minutes ago
COMMUNITYModelIndex benchmarks44 hours ago
MEASUREDVerified 4 minutes ago · list prices, not negotiated rates.