Granite 4.2 8B API Pricing 2026

Compare pricing, benchmarks, and providers for Granite 4.2 8B. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Granite 4.2 8B was released on August 31, 2026. Pricing starts at $0.060 per million input tokens and $0.150 per million output tokens. The model supports a context window of up to 131K tokens. API access is available through IBM.

Context Window
131K
tokens
Pricing
Input$0.060
Output$0.150
Cached$0.015
per 1M tokens
Speed
Output65 tok/s
TTFT0.50s
median latency
Capabilities
ToolsCaching

Granite 4.2 8B is priced at $0.060 per million input tokens and $0.150 per million output tokens. It has a context window of 131,072 tokens. It is available from 3 providers, with DeepInfra the cheapest at $0.060 per million input tokens. It runs at roughly 65 tokens per second with a 0.50s time to first token. On benchmarks, Granite 4.2 8B scores Intelligence 5.1 (0th percentile), GPQA 63.1 (57th percentile). Over the past ~90 days its cheapest input price has fallen 40%, from $0.100 to $0.060 per million tokens.

Pricing Comparison

Compare Granite 4.2 8B with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
IB
IBM
$0.060
$0.150
—
—
63.1
131,072
Try
$0.050
$0.700
—
—
—
-
Try
$0.056
$0.224
—
—
—
131,072
Try
$0.059
$0.059
—
—
—
4,096
Try
$0.060
$0.240
—
—
—
300,000
Try
$0.060
$0.120
—
—
—
262,144
Try
$0.060
$0.240
—
—
—
262,144
Try
$0.060
$0.300
—
—
—
-
Try
$0.060
$0.200
—
—
—
131,072
Try
$0.060
$0.060
—
—
—
131,072
Try
$0.060
$0.060
—
—
—
8,192
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Granite 4.2 8B is available from multiple providers with different pricing and availability.

3
Providers
$0.060
Cheapest Input/M
$0.150
Cheapest Output/M
DeepInfra
Best Price

Provider Pricing

3 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
DeepInfra
DeepInfra
Best Price
$0.060
$0.250
$0.015
-
-
C
CoreWeave
Best Price
$0.060
$0.150
$0.015
-
100.0%
OpenRouter
OpenRouter
Best Price
$0.060
$0.150
$0.015
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Granite 4.2 8B perform? Vote based on your experience.

Cost vs. Quality

Compare Granite 4.2 8B's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Detailed Benchmark Scores

Intelligence
5.1 (0th pct)
Coding
-
Math
-
MMLU Pro
-
GPQA
63.1 (57th pct)
LiveCodeBench
-
AIME
-
Aider
-
Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try Granite 4.2 8B

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Granite 4.2 8B directly in your browser.

Open Playground

Frequently Asked Questions

Granite 4.2 8B costs $0.000060 per 1,000 input tokens and $0.000150 per 1,000 output tokens.
Granite 4.2 8B is available from 3 providers. DeepInfra offers the best price.
DeepInfra offers Granite 4.2 8B at $0.060 per million input tokens.
Granite 4.2 8B scores Intelligence 5.1 (0th percentile), GPQA 63.1 (57th percentile). Only benchmarks with published data for this model are shown.
Yes. Over the past ~90 days, the cheapest input price for Granite 4.2 8B has dropped 40%, from $0.100 to $0.060 per million tokens.
We compare Granite 4.2 8B with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All IBM Models

See pricing for all IBM models.

View all IBM models →