Skip to content

Model Library

IBMReleased April 29, 2026

Granite 4.1 8B

IBM · Released April 29, 2026

View public research Browse the library

Intelligence score

7

At a glance

Intelligence
7
Speed
123.3tokens/sec
Latency
840mstime to first token
Input price
$0.05per 1M tokens
Output price
$0.10per 1M tokens
Context window
130Ktokens
Parameters
8billions

Summary

Comparison summary

Granite 4.1 8B scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6). Granite 4.1 8B generates output at 123.3 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). Granite 4.1 8B costs $0.05 per 1M input tokens (very competitive, median: $0.15) and $0.10 per 1M output tokens (very competitive, median: $0.32), based on the median across providers serving the model.

Specifications

Technical specifications

Model nameGranite 4.1 8B
ProviderIBM
Release dateApril 29, 2026
Intelligence score7
Speed123.3 tokens/sec
Latency (TTFT)0.84s
Input price$0.05 / 1M tokens
Output price$0.10 / 1M tokens
Context window130,000 tokens
Parameters8B
ReasoningNo
Input modalitiestext
Output modalities—
Open weightsYes
LicenseApache 2
API availability—
SourceModel Intelligence legacy profile: granite-4-1-8b

Pricing

Token prices

Price per 1M tokens

Granite 4.1 8B, as listed in the catalog record

Input $0.05 and output $0.10 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$0.05
  2. Output$0.10

Model Intelligence legacy profile: granite-4-1-8b

FAQ · 19

Frequently asked questions

Granite 4.1 8B was released on April 29, 2026.

Granite 4.1 8B was created by IBM.

Granite 4.1 8B scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6).

Granite 4.1 8B generates output at 123.3 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).

Granite 4.1 8B has a time to first token (TTFT) of 0.84s (based on the median across providers serving the model), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.54s).

Granite 4.1 8B costs $0.05 per 1M input tokens (very competitive, median: $0.15) and $0.10 per 1M output tokens (very competitive, median: $0.32), based on the median across providers serving the model.

Granite 4.1 8B costs $0.05 per 1M input tokens and $0.10 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.06 per 1M tokens. Pricing may vary by provider.

No, Granite 4.1 8B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Granite 4.1 8B supports text input.

Granite 4.1 8B supports text output.

No, Granite 4.1 8B does not support image input. It can only process text.

No, Granite 4.1 8B is not multimodal. It only supports text input.

Granite 4.1 8B has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, Granite 4.1 8B is open weights. The model weights are publicly available and can be downloaded for self-hosting.

Granite 4.1 8B has 8 billion parameters.

Granite 4.1 8B is released under the Apache 2.0 license. This license allows commercial use.

Granite 4.1 8B achieves a score of 7 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Granite 4.1 8B is available via API through 1 provider.

Granite 4.1 8B is available through 1 API provider.