Granite 4.2 8B
by Ibm Granite · ibm-granite/granite-4.2-8b · #41 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.06
per 1M tokens
Output
$0.25
per 1M tokens
Blended (3:1)
$0.107
3 input : 1 output
Cache read
$0.015
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Granite 4.2 8B with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.107 | $0.00637 | — |
| 50% | $0.091 | $0.00412 | −35% |
| 90% | $0.077 | $0.00232 | −64% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.000105 | $0.105 |
| Document summary | 8,000 | 1,000 | $0.00073 | $0.73 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0023 | $2.30 |
| Long-context analysis | 150,000 | 5,000 | $0.0102 | $10.25 |
Performance
Intelligence Index
11.8
AA composite quality
Coding Index
22.4
Math Index
—
Agentic Index
3.7
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Specs
Context window
131K
tokens
Max output
118K
tokens
Input modalities
text
Tokenizer
Other