impulse

Granite 20B Code Instruct 8K

Open weights
API id granite-20b-code-instruct-8k
Input / 1M
$0.10
at Replicate
Output / 1M
$0.50
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$0.10$0.50

What it costs a month

At Replicate list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$67.50
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$66.00
  • Coding agent1,000 requests a day, 40K in / 2K out$150
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$360
Use your own numbers

Where to run it

1 host serve Granite 20B Code Instruct 8K. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
ReplicateInference
granite-20b-code-instruct-8k
$0.10 / $0.50

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

  • Qwen3.8 Flash
    Alibaba Qwen · on AIHubMix
    $0.113 / $0.38
    Has every key capability
    10% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    11% less
  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    20% less
  • Ministral 8B 2512
    Mistral AI · on Mistral AI
    $0.15 / $0.15
    Has every key capability
    25% less

Call it

Using Replicate's API.

Python
from litellm import completion

response = completion(
    model="replicate/granite-20b-code-instruct-8k",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Granite 20B Code Instruct 8K cost?

On Replicate, Granite 20B Code Instruct 8K costs $0.10 per million input tokens and $0.50 per million output tokens.

Which APIs offer Granite 20B Code Instruct 8K?

Granite 20B Code Instruct 8K runs on 1 API: Replicate.

Is Granite 20B Code Instruct 8K being retired?

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

What are cheaper alternatives to Granite 20B Code Instruct 8K?

Models that cost less and keep most of what it can do: Qwen3.8 Flash on AIHubMix (10% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Granite 20B Code Instruct 8K's API model id?

Use granite-20b-code-instruct-8k with Replicate.

Sources

Raw catalog entry for granite-20b-code-instruct-8k on Replicate
{
  "input_cost_per_token": 1e-7,
  "litellm_provider": "replicate",
  "mode": "chat",
  "output_cost_per_token": 5e-7,
  "source": "https://replicate.com/ibm-granite/granite-20b-code-instruct-8k",
  "supports_system_messages": true
}