impulse

Granite 3.1 8B Instruct

Open weights
API id granite-3.1-8b-instruct
Input / 1M
$0.03
at Replicate
Output / 1M
$0.25
at Replicate
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Replicate, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.03$0.25

What it costs a month

At Replicate list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$27.75
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$23.40
  • Coding agent1,000 requests a day, 40K in / 2K out$51.00
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$132
Use your own numbers

Where to run it

1 host serve Granite 3.1 8B Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
ReplicateInference
granite-3.1-8b-instruct
$0.03 / $0.25

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Apache-2.0
Runtimes: Ollama, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Replicate.

Smaller IBM models

No cheaper IBM model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Granite 4.2 8B
    IBM · on W&B Inference
    $0.06 / $0.15
    Has every key capability
    3% less
  • DeepSeek V4.1 Flash Fast
    DeepSeek · on Refuseless
    $0.05 / $0.15
    Has every key capability
    12% less
  • Code Llama 7B
    Meta · on LlamaGate
    $0.06 / $0.12
    Has every key capability
    12% less
  • Mistral Nemo
    Mistral AI · on Novita AI
    $0.04 / $0.17
    Has every key capability
    15% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedGranite 3.3 8B InstructLatest$0.20 / $0.20
  2. UndatedGranite 3.2 8B Instruct$0.03 / $0.25
  3. UndatedGranite 3.1 8B InstructThis page$0.03 / $0.25
  4. UndatedGranite 3 8B Instruct$0.20 / $0.20
  5. UndatedGranite 3.0 8B Instruct$0.05 / $0.25

Call it

Using Replicate's API.

Python
from litellm import completion

response = completion(
    model="replicate/granite-3.1-8b-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Granite 3.1 8B Instruct cost?

On Replicate, Granite 3.1 8B Instruct costs $0.03 per million input tokens and $0.25 per million output tokens.

Which APIs offer Granite 3.1 8B Instruct?

Granite 3.1 8B Instruct runs on 1 API: Replicate.

Is Granite 3.1 8B Instruct being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Granite 3.1 8B Instruct?

Yes. Granite 3.3 8B Instruct is the newest model in this line.

What are cheaper alternatives to Granite 3.1 8B Instruct?

Models that cost less and keep most of what it can do: Granite 4.2 8B on W&B Inference (3% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Granite 3.1 8B Instruct's API model id?

Use granite-3.1-8b-instruct with Replicate.

Sources

Raw catalog entry for granite-3.1-8b-instruct on Replicate
{
  "input_cost_per_token": 3e-8,
  "litellm_provider": "replicate",
  "mode": "chat",
  "output_cost_per_token": 2.5e-7,
  "source": "https://replicate.com/ibm-granite/granite-3.1-8b-instruct",
  "supports_system_messages": true
}