Phi-4
Input price$0.07
Output price$0.14
IBMText
granite-4.2-8b
granite-4.2-8b is IBM's model at $0.06 input and $0.25 output per million tokens, with a 131K context window. On a typical 3:1 input-to-output mix that blends to roughly $0.11 per million tokens, placing it in the budget band of the 79 models tracked here — cheaper than 92% of them.
Context window131K
Input price$0.06 / 1M
Output price$0.25 / 1M
Output speed130 tok/s
Quality score77
Data updatedUpdated Sep 2026
Price verified2026-09-16 · OpenRouter
Price noteCache-hit input is $0.015 / 1M tokens; Apache-2.0 licensed, so self-hosting is an option
By price, granite-4.2-8b ranks 5th cheapest of 79 on input and 11th on output. Its quality score of 77 ranks 73rd of 79, and on value (quality score ÷ output price) it ranks 12th of 79. Its blended rate sits 97% below the catalog average.
In real billing terms: a support chatbot handling 50,000 turns a month (2,000 input / 500 output tokens each) costs about $12 per month on granite-4.2-8b, while a RAG workload of 20,000 queries (8,000 input / 800 output tokens each) runs about $14. Because output is priced 4.2× input here, long-generation tasks scale cost fastest — cap output length before you optimise anything else.
A 131K context window holds roughly 175 pages of A4 text (at ~750 tokens per page), ranking 58th of 79 here. That covers typical RAG and multi-turn chat, though book-length inputs still need retrieval and chunking. Output runs at about 130 tok/s (28th fastest of 79), fast enough for real-time interaction and high-throughput batches.
We track 1 IBM models, and granite-4.2-8b's blended rate sits 0% above that provider's average. If your task tolerates a little less headroom, qwen3.7-flash (Alibaba) blends about 49% cheaper at a quality score of 82, and is worth benchmarking first. Going the other way, mercury-2.5-preview scores 82 on quality for about 37% less.
Estimated monthly cost
Monthly API spend across four common workloads, next to the cheapest model we track.
| Workload | Usage assumption | This model | Cheapest model |
|---|---|---|---|
| Support chatbot | 2,000 input / 500 output tokens per turn, 50,000 turns per month | $12 | $3.00 |
| RAG document Q&A | 8,000 input / 800 output tokens per query, 20,000 queries per month | $14 | $3.84 |
| Coding assistant | 12,000 input / 2,000 output tokens per request, 10,000 requests per month | $12 | $3.20 |
| Batch summarization | 4,000 input / 400 output tokens per item, 200,000 items per month | $68 | $19 |
Derived directly from the rates on this page. Excludes prompt caching, batch discounts and free tiers.
How it compares
The alternatives worth benchmarking alongside it, from the same dataset.
| Model | Provider | Blended /1M | Quality | Price delta |
|---|---|---|---|---|
| granite-4.2-8b | IBM | $0.11 | 77 | — |
| qwen3.7-flashCheaper option | Alibaba | $0.055 | 82 | -49% |
| mercury-2.5-previewHigher quality | Inception | $0.068 | 82 | -37% |
| Phi-4-miniBest value overall | Microsoft | $0.025 | 68 | -77% |
Best for
CodingChatbotAffordableFast
Modalities
Text
Where it fits — and where it doesn't
Good fit
- Coding: writing, refactoring and debugging across multi-file project context.
- Chat and support: natural multi-turn conversation for user-facing products.
- High throughput and real-time UX: 130 tok/s keeps streamed responses feeling instant.
- High-volume, cost-sensitive batch work: low rates suit classification, tagging and summarization at scale.
Poor fit
- Hard reasoning: a quality score of 77 is on the low side here; pick a stronger model for complex planning or maths.
- Image understanding: this model is text-only, so vision tasks need a multimodal alternative.
Frequently asked questions
How much does the granite-4.2-8b API cost?
granite-4.2-8b costs $0.06 per million input tokens and $0.25 per million output tokens. On a 3:1 input-to-output mix that blends to about $0.11 per million tokens.
What does granite-4.2-8b cost per month?
It depends on volume. Using the four worked scenarios on this page: a support chatbot runs about $12/month, RAG document Q&A about $14/month, a coding assistant about $12/month, and batch summarization about $68/month. Plug your own token counts into the cost calculator for a tailored figure.
How large is the granite-4.2-8b context window?
131K tokens — roughly 175 pages of A4 text at ~750 tokens per page, ranking 58th of the 79 models tracked here.
granite-4.2-8b or qwen3.7-flash — which is better value?
qwen3.7-flash blends to about $0.055 per million tokens versus $0.11 for granite-4.2-8b — roughly 49% cheaper — at a quality score of 82 against 77. If that quality gap does not show up on your task, take the cheaper one; if it does, stay with granite-4.2-8b. Benchmark both on your own data before deciding.
What is granite-4.2-8b best suited for?
Tagged use cases: coding, chatbot, cheap, fast. Coding: writing, refactoring and debugging across multi-file project context. Less suitable: Hard reasoning: a quality score of 77 is on the low side here; pick a stronger model for complex planning or maths.
How current is this granite-4.2-8b pricing?
Pricing here was last verified on 2026-09-16 against OpenRouter. llmprice.app runs a daily collection job, but providers can change rates between runs — confirm against IBM's official pricing page before you commit.
Estimate the real cost of this model
Bring tokens per request and monthly volume into the calculator to compare total model costs.
Related models
Continue by provider and use case.
View model
mercury-2.5-preview
Input price$0.04
Output price$0.15
gpt-5.6-luna
Input price$0.2
Output price$1.2
Pricing, speed and quality scores change over time. Confirm official documentation before production use.