LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
ib

Granite 4.2 8B

ibm·ibm/granite-4.2-8b·GA·Open weights·granite series·NEW
Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Granite 4.2 8B by ibm is offered by 5 providers on this page. Its reference price is $0.10 per 1M input tokens and $0.15 per 1M output tokens. The lowest paid channel is OpenRouter at $0.06 / $0.25 per 1M, about 1.7× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Artificial Analysis rates it 11.1 on the Intelligence Index, with 22.4 for coding and 1.3 for agentic tasks. Against its lowest blended price of $0.107 per 1M, that is roughly 103 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 60 tokens per second, with 0.75s to the first token. Running one task of the Artificial Analysis suite costs about $0.0236, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 131,072 tokens, with an output limit of 131,072 tokens. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Specs & pricing

Input / output per 1M tokens
Reference price·CoreWeave
$0.10 / $0.15
Blended $0.11 · Cache read $0.05
Lowest paid·OpenRouterGateway
$0.06 / $0.25
Blended $0.11 · 1.7× spread
Context
131,072
Output limit
131,072
Knowledge cutoff
—
Released / updated
2026-08-31 / 2026-08-31
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text

Quality & performanceArtificial Analysis · Intelligence Index v4.3

Intelligence11.1
Value103
Coding22.4
Agentic1.3
Output speed60 tok/s
TTFT0.75 s
Cost per task$0.024
Value formulaIQ 11.1 ÷ min blended $0.107 = 103

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

Available at 5 providers5 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
OpenRouterGateway$0.06$0.25$0.015—131,072117,964
DevPass (LLM Gateway)Gateway$0.06$0.25$0.015—131,072131,072
Kilo GatewayGateway$0.06$0.25$0.015—131,072117,964
NanoGPTGateway$0.10$0.15$0.05—131,072117,964
CoreWeaveCloud$0.10$0.15$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.

Reasoning control

effort = noneeffort = loweffort = higheffort = mediumToggle (on / off)

Your usage cost

1OpenRouter$19.10
2DevPass (LLM Gateway)$19.10
3Kilo Gateway$19.10
4NanoGPT$21.50
5CoreWeave$21.50
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list $0.10Output list $0.15Min blended $0.11

Price history accumulates from each data sync; currently only 1 sample(s) (2026-10-13). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

Granite 4.2 8B (DeepInfra)same series$0.06 / $0.25ibGranite 4.0 Microsame series$0.017 / $0.11ibGranite-4.0-H-Microsame series$0.023 / $0.15Nemotron 3.5 Lightning 30B A3Bcheaper alternative$0 / $0Qwen3.7 Flashcheaper alternative$0.03 / $0.13Nemotron 3.5 Content Safetycheaper alternative$0 / $0GLM-4.6V-Flashcheaper alternative$0 / $0
Data partly from models.dev (MIT) · CoreWeave official docs ↗