Watsonx LLM API pricing
Every model Watsonx serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.
Models served
26
on this provider
Cheapest input
$0.06
per 1M tokens
Cheapest output
$0.10
per 1M tokens
Max context
131K
tokens
| Model ID | |||||
|---|---|---|---|---|---|
| Granite 4 H Small | IBM | 20K | $0.06 | $0.25 | watsonx/ibm/granite-4-h-small |
| Mistral Small 2503 | Mistral | 128K | $0.10 | $0.30 | watsonx/mistralai/mistral-small-2503 |
| Mistral Small 3.1 24B Instruct 2503 | Mistral | 32K | $0.10 | $0.30 | watsonx/mistralai/mistral-small-3-1-24b-instruct-2503 |
| Llama 3.2 1B Instruct | Meta | 131K | $0.10 | $0.10 | watsonx/meta-llama/llama-3-2-1b-instruct |
| Granite Vision 3.2 2B | IBM | 8K | $0.10 | $0.10 | watsonx/ibm/granite-vision-3-2-2b |
| Granite Guardian 3.2 2B | IBM | 8K | $0.10 | $0.10 | watsonx/ibm/granite-guardian-3-2-2b |
| Llama 3.2 3B Instruct | Meta | 131K | $0.15 | $0.15 | watsonx/meta-llama/llama-3-2-3b-instruct |
| gpt-oss-120b | OpenAI | 131K | $0.15 | $0.60 | watsonx/openai/gpt-oss-120b |
| Granite 3.3 8B Instruct | IBM | 8K | $0.20 | $0.20 | watsonx/ibm/granite-3-3-8b-instruct |
| Granite Guardian 3.3 8B | IBM | 8K | $0.20 | $0.20 | watsonx/ibm/granite-guardian-3-3-8b |
| Granite 3 8B Instruct | IBM | 8K | $0.20 | $0.20 | watsonx/ibm/granite-3-8b-instruct |
| Llama 3.2 11B Vision Instruct | Meta | 131K | $0.35 | $0.35 | watsonx/meta-llama/llama-3-2-11b-vision-instruct |
| Pixtral 12B 2409 | Mistral | 128K | $0.35 | $0.35 | watsonx/mistralai/pixtral-12b-2409 |
| Llama 4 Maverick 17B | Meta | 128K | $0.35 | $1.40 | watsonx/meta-llama/llama-4-maverick-17b |
| Llama Guard 3 11B Vision | Meta | 128K | $0.35 | $0.35 | watsonx/meta-llama/llama-guard-3-11b-vision |
| Granite Ttm 1536 96 R2 | IBM | 512 | $0.38 | $0.38 | watsonx/ibm/granite-ttm-1536-96-r2 |
| Granite Ttm 1024 96 R2 | IBM | 512 | $0.38 | $0.38 | watsonx/ibm/granite-ttm-1024-96-r2 |
| Granite Ttm 512 96 R2 | IBM | 512 | $0.38 | $0.38 | watsonx/ibm/granite-ttm-512-96-r2 |
| Flan T5 Xl 3B | Other | 8K | $0.60 | $0.60 | watsonx/google/flan-t5-xl-3b |
| Granite 13B Instruct | IBM | 8K | $0.60 | $0.60 | watsonx/ibm/granite-13b-instruct-v2 |
| Granite 13B Chat | IBM | 8K | $0.60 | $0.60 | watsonx/ibm/granite-13b-chat-v2 |
| Llama 3.3 70B Instruct | Meta | 131K | $0.71 | $0.71 | watsonx/meta-llama/llama-3-3-70b-instruct |
| Allam 1 13B Instruct | G42 | 8K | $1.80 | $1.80 | watsonx/sdaia/allam-1-13b-instruct |
| Llama 3.2 90B Vision Instruct | Meta | 128K | $2.00 | $2.00 | watsonx/meta-llama/llama-3-2-90b-vision-instruct |
| Mistral Large | Mistral | 131K | $3.00 | $10.00 | watsonx/mistralai/mistral-large |
| Mistral Medium 2505 | Mistral | 131K | $3.00 | $10.00 | watsonx/mistralai/mistral-medium-2505 |
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI