Start free trial

IBM: Granite 4.2 8B

ibm-granite/granite-4-2-8b
CompareAPITry this model

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.

Modalities
In / out per 1M$0.06 / $0.15
Context128K
ReleasedAug 31, 2026

Providers

2 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
CoreWeavebf16$0.06$0.15$0.010.20s99 tps99.94%
DeepInfraus · bf16$0.06$0.25$0.011.00s16 tps99.32%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Granite 4.2 8B in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Granite 4.2 8B costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.06
per 1M tokens
Output
$0.15
per 1M tokens
Cache read
$0.01
per 1M cached tokens
Included in every pass
Granite 4.2 8B is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s10.0s20.0s30.0s40.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
DeepInfra (us) CoreWeave
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
DeepInfra (us) CoreWeave

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.41%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 98.19%
100% 88% 77% 65%
Oct 31, 6:10 PMNow

Apps

Tools that most often run Granite 4.2 8B, by tokens this week.

ESCRIBA-01-BibliotecaSV73.1% of tokens3.9BTolokaforge Evaluation12% of tokens633.9MKilo CodeCli Agent · 7% of tokens368.2MGPE Model Gateway5.7% of tokens299.2MCoreThink Neurosymbolic Reasoning Engine2.3% of tokens119.1M

Activity

44.0B tokens processed market-wide in the last month.

02.0B4.0B6.0B8.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens

FAQ

Which model id do I use for Granite 4.2 8B?
ibm-granite/granite-4.2-8b. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does Granite 4.2 8B hold?
131,072 tokens per request, of which up to 117,964 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Granite 4.2 8B cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.06 per 1M input tokens and $0.15 per 1M output tokens.
Who built Granite 4.2 8B?
IBM, in the Granite family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion