LLM Pricing
← All models

granite-4-h-small

watsonx · chat model

granite-4-h-small is listed here as a chat model from watsonx. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.

Input
$0.0600 / 1M tokens
Output
$0.2500 / 1M tokens
Cached input
N/A
Context
20.5K
Compare similar models Open a side-by-side table using this route and the closest match from the current catalog. Estimate workload cost Use token counts, request volume, and cache assumptions to check a realistic monthly bill. Explore benchmarks Review benchmark rows by family and benchmark label without cross-benchmark ranking. Check data sources See how pricing data is generated and what still needs provider verification.

Quick read

Best for

Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.

Things to verify

Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.

Pricing

Item Price
Input
$0.0600 / 1M tokens
Output
$0.2500 / 1M tokens
Embedding
$0.0600 / 1M tokens

Token limits

Context window
20.5K
Max input tokens
20.5K
Max output tokens
20.5K
Max tokens
20.5K

Capabilities

Capability Supported
Vision —
Function calling ✅
Parallel function calling ✅
Tool choice —
Prompt caching —
Reasoning —
Response schema —
System messages —
Audio input —
Audio output —
Web search —
PDF input —
Video input —

Sources

Source links
Pricing data LiteLLM model cost map
Synced at 2026-05-28

Similar models

This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.

Comparing from
Model Cost Input shape Features Context Why it is close
granite-4-h-small
watsonx
In $0.0600 / 1M tokens
Out $0.2500 / 1M tokens
Output: unknown
Function callingParallel function calling
20.5K
Current model
Reference row

Overall blends cost, modality overlap, capabilities, and context.

Model Cost Input shape Features Context Why it is close
mistral-small-2503
watsonx
In $0.1000 / 1M tokens
Out $0.3000 / 1M tokens
Output: unknown
Function callingParallel function calling
32.0K
Same provider
Overall 49%
mistral-small-3-1-24b-instruct-2503
watsonx
In $0.1000 / 1M tokens
Out $0.3000 / 1M tokens
Output: unknown
Function callingParallel function calling
32.0K
Same provider
Overall 49%
granite-3-3-8b-instruct
watsonx
In $0.2000 / 1M tokens
Out $0.2000 / 1M tokens
Output: unknown
Function callingParallel function calling
8.2K
Same provider
Overall 43%
Qwen3-14B
nebius
In $0.0800 / 1M tokens
Out $0.2400 / 1M tokens
Output: unknown
Function calling
32.8K
Partial I/O overlap
Overall 39%
Qwen3-4B
nebius
In $0.0800 / 1M tokens
Out $0.2400 / 1M tokens
Output: unknown
Function calling
32.8K
Partial I/O overlap
Overall 39%
llama-3-2-3b-instruct
watsonx
In $0.1500 / 1M tokens
Out $0.1500 / 1M tokens
Output: unknown
Function callingParallel function calling
128.0K
Same provider
Overall 38%
llama-3-2-1b-instruct
watsonx
In $0.1000 / 1M tokens
Out $0.1000 / 1M tokens
Output: unknown
Function callingParallel function calling
128.0K
Same provider
Overall 37%
gpt-4o-2024-08-06
github_copilot
In N/A
Out N/A
imagetext
Output: text
Function callingParallel function calling
16.4K
Partial I/O overlap
Overall 37%
llama-3-3-70b-instruct
watsonx
In $0.7100 / 1M tokens
Out $0.7100 / 1M tokens
Output: unknown
Function callingParallel function calling
128.0K
Same provider
Overall 32%
apac.amazon.nova-lite-v1:0
bedrock_converse
In $0.0630 / 1M tokens
Out $0.2520 / 1M tokens
imagepdf
Output: text
Function calling
10.0K
Partial I/O overlap
Overall 31%
gpt-4-o-preview
github_copilot
In N/A
Out N/A
Output: unknown
Function callingParallel function calling
4.1K
Partial I/O overlap
Overall 28%
gpt-4o-mini
github_copilot
In N/A
Out N/A
imagetext
Output: text
Function callingParallel function calling
4.1K
Partial I/O overlap
Overall 28%
gpt-4o-mini-2024-07-18
github_copilot
In N/A
Out N/A
imagetext
Output: text
Function callingParallel function calling
4.1K
Partial I/O overlap
Overall 28%
llama-3-8b
replicate
In $0.0500 / 1M tokens
Out $0.2500 / 1M tokens
text
Output: text
Low overlap
8.1K
Partial I/O overlap
Overall 24%
llama-3-8b-instruct
replicate
In $0.0500 / 1M tokens
Out $0.2500 / 1M tokens
text
Output: text
Low overlap
8.1K
Partial I/O overlap
Overall 24%
llama-2-7b
replicate
In $0.0500 / 1M tokens
Out $0.2500 / 1M tokens
text
Output: text
Low overlap
4.1K
Partial I/O overlap
Overall 22%
llama-2-7b-chat
replicate
In $0.0500 / 1M tokens
Out $0.2500 / 1M tokens
text
Output: text
Low overlap
4.1K
Partial I/O overlap
Overall 22%
mistral-7b-instruct-v0.2
replicate
In $0.0500 / 1M tokens
Out $0.2500 / 1M tokens
text
Output: text
Low overlap
4.1K
Partial I/O overlap
Overall 22%