Granite 3.1 8B Instruct
Granite 3.1 8B Instruct is IBM's enterprise-tuned 8B parameter model, released in December 2024 as part of the Granite 3 series. The 3.1 revision expanded context from 4K to 128K tokens — a meaningful upgrade for RAG pipelines that need to ingest long documents in a single pass. IBM benchmarks show strong structured-output and tool-use performance, making it a reasonable pick for enterprise extraction and function-calling workloads where a smaller footprint matters. Licensed Apache 2.0, so commercial deployment carries no royalty friction. Primary hosting is IBM's watsonx.ai; Together AI and Replicate offer broader spot pricing if you need to avoid IBM Cloud lock-in.
No pricing data available for this model yet.
Not enough history to display chart. View full history →
No benchmark data available.
Questions developers ask
How much does it cost to run Granite 3.1 8B Instruct for 100M tokens?▾
Pricing varies by provider. Use the workload calculator to get an accurate estimate for your specific usage pattern.
What is the cheapest provider for Granite 3.1 8B Instruct?▾
No pricing data is available yet. Check back after the next scrape run.
What context window does Granite 3.1 8B Instruct support?▾
Granite 3.1 8B Instruct supports a context window of 131,072 tokens. Individual providers may cap this lower.
What's the cheapest way to run Granite 3.1 8B Instruct?▾
Compare provider prices in the table above and consider using prompt caching if supported.
Is there a free tier for Granite 3.1 8B Instruct?▾
Free tiers vary by provider and change frequently. Check each provider's current pricing page for trial credits or free-tier limits. The prices shown on this page reflect paid API access.
How much does Granite 3.1 8B Instruct cost for 1M tokens?▾
Pricing data for Granite 3.1 8B Instruct is not yet available. Check back after the next data refresh.
Keep exploring
No hosted pricing scraped for this model yet. Methodology · Raw data