LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
ib

Granite 4.1 8B

ibm-granite·ibm-granite/granite-4.1-8b·GA·Open weights·granite series
Granite 4.1 8B is a long-context instruct model capable of enhanced tool calling, instruction following, and chat capabilities.

Granite 4.1 8B by ibm-granite is currently listed from a single provider. Its reference price is $0.05 per 1M input tokens and $0.10 per 1M output tokens.

Artificial Analysis rates it 6.4 on the Intelligence Index, with 9.5 for coding. Against its lowest blended price of $0.063 per 1M, that is roughly 102 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 108 tokens per second, with 0.76s to the first token.

The context window is 131,072 tokens, with an output limit of 131,072 tokens. It supports tool use and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice.

Specs & pricing

Input / output per 1M tokens
Reference price·Weights & Biases
$0.05 / $0.10
Blended $0.063 · Cache read $0.05
Lowest paid·Weights & BiasesCloud
$0.05 / $0.10
Blended $0.063
Context
131,072
Output limit
131,072
Knowledge cutoff
—
Released / updated
2026-04-29 / 2026-04-29
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence6.4
Value102
Coding9.5
Agentic—
Output speed108 tok/s
TTFT0.76 s
Value formulaIQ 6.4 ÷ min blended $0.063 = 102

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Weights & BiasesCloud$0.05$0.10$0.05—131,072131,072

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Weights & Biases$15.00
The cheapest paid channel is the only channel.

Related models

ibGranite 4.2 8Bsame series$0.10 / $0.15ibGranite 4.0 Microsame series$0.017 / $0.112ibGranite-4.0-H-Microsame series$0.017 / $0.112Llama 4 Maverick 17B 128E Instruct FP8cheaper alternative$0 / $0Lyria 3 Clip Previewcheaper alternative$0 / $0Lyria 3 Pro Previewcheaper alternative$0 / $0

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.10$02026-08-052026-08-132026-08-05 · Input list $0.052026-08-06 · Input list $0.052026-08-07 · Input list $0.052026-08-08 · Input list $0.052026-08-09 · Input list $0.052026-08-10 · Input list $0.052026-08-11 · Input list $0.052026-08-12 · Input list $0.052026-08-13 · Input list $0.052026-08-05 · Output list $0.102026-08-06 · Output list $0.102026-08-07 · Output list $0.102026-08-08 · Output list $0.102026-08-09 · Output list $0.102026-08-10 · Output list $0.102026-08-11 · Output list $0.102026-08-12 · Output list $0.102026-08-13 · Output list $0.102026-08-05 · Min blended $0.0632026-08-06 · Min blended $0.0632026-08-07 · Min blended $0.0632026-08-08 · Min blended $0.0632026-08-09 · Min blended $0.0632026-08-10 · Min blended $0.0632026-08-11 · Min blended $0.0632026-08-12 · Min blended $0.0632026-08-13 · Min blended $0.063
Data partly from models.dev (MIT) · Weights & Biases official docs ↗