Granite 8B Code Instruct 128K
granite-8b-code-instruct-128kPricing
List prices at Replicate, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.05 | $0.25 |
What it costs a month
At Replicate list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$33.75
- RAG over documents2,000 requests a day, 8K in / 0.6K out$33.00
- Coding agent1,000 requests a day, 40K in / 2K out$75.00
- Overnight batch20,000 requests a day, 4K in / 0.4K out$180
Where to run it
1 host serve Granite 8B Code Instruct 128K. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
ReplicateInference granite-8b-code-instruct-128k | $0.05 / $0.25 | granite-8b-code-instruct-128k |
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-2.0Runtimes: 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
- 5% less
- 10% less
- 13% less
- 18% less
Call it
Using Replicate's API.
from litellm import completion
response = completion(
model="replicate/granite-8b-code-instruct-128k",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Granite 8B Code Instruct 128K cost?
On Replicate, Granite 8B Code Instruct 128K costs $0.05 per million input tokens and $0.25 per million output tokens.
Which APIs offer Granite 8B Code Instruct 128K?
Granite 8B Code Instruct 128K runs on 1 API: Replicate.
Is Granite 8B Code Instruct 128K being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Granite 8B Code Instruct 128K?
Models that cost less and keep most of what it can do: GLM 5.3 Flash on CLF AI Gateway (5% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Granite 8B Code Instruct 128K's API model id?
Use granite-8b-code-instruct-128k with Replicate.
Sources
Raw catalog entry for granite-8b-code-instruct-128k on Replicate
{
"input_cost_per_token": 5e-8,
"litellm_provider": "replicate",
"mode": "chat",
"output_cost_per_token": 2.5e-7,
"source": "https://replicate.com/ibm-granite/granite-8b-code-instruct-128k",
"supports_system_messages": true
}