Skip to content

IBM Watsonx Models

IBM Watsonx provides 28 AI models accessible via API.

Visit IBM Watsonx →

28

Models Available

$0.060

Cheapest Input / 1M

131K

Largest Context

What is IBM Watsonx?

IBM Watsonx is an AI model provider offering 28 large language models for developers. Their cheapest model starts at $0.060 per 1M input tokens, and their largest context window reaches 131K. IBM Watsonx provides 28 AI models accessible via API.

IBM Watsonx Strengths

All IBM Watsonx Models

Model Input $/1M Output $/1M Context Max Output Released
Ibm/Granite 4 H Small $0.060 $0.25 20K 20,480
Ibm/Granite Guardian 3 2 2b $0.10 $0.10 8K 8,192
Ibm/Granite Vision 3 2 2b $0.10 $0.10 8K 8,192
Meta Llama/Llama 3 2 1b Instruct $0.10 $0.10 128K 128,000
Mistralai/Mistral Small 2503 $0.10 $0.30 32K 32,000
Mistralai/Mistral Small 3 1 24b Instruct 2503 $0.10 $0.30 32K 32,000
Meta Llama/Llama 3 2 3b Instruct $0.15 $0.15 128K 128,000
Openai/Gpt Oss 120b $0.15 $0.60 8K 8,192
Ibm/Granite 3 8b Instruct $0.20 $0.20 8K 1,024
Ibm/Granite 3 3 8b Instruct $0.20 $0.20 8K 8,192
Ibm/Granite Guardian 3 3 8b $0.20 $0.20 8K 8,192
Meta Llama/Llama 3 2 11b Vision Instruct $0.35 $0.35 128K 128,000
Meta Llama/Llama 4 Maverick 17b $0.35 $1.40 128K 128,000
Meta Llama/Llama Guard 3 11b Vision $0.35 $0.35 128K 128,000
Mistralai/Pixtral 12b 2409 $0.35 $0.35 128K 128,000
Ibm/Granite Ttm 1024 96 R2 $0.38 $0.38 1K 512
Ibm/Granite Ttm 1536 96 R2 $0.38 $0.38 1K 512
Ibm/Granite Ttm 512 96 R2 $0.38 $0.38 1K 512
Google/Flan T5 Xl 3b $0.60 $0.60 8K 8,192
Ibm/Granite 13b Chat $0.60 $0.60 8K 8,192
Ibm/Granite 13b Instruct $0.60 $0.60 8K 8,192
Meta Llama/Llama 3 3 70b Instruct $0.71 $0.71 128K 128,000
Sdaia/Allam 1 13b Instruct $1.80 $1.80 8K 8,192
Meta Llama/Llama 3 2 90b Vision Instruct $2.00 $2.00 128K 128,000
Mistralai/Mistral Large $3.00 $10.00 131K 16,384
Mistralai/Mistral Medium 2505 $3.00 $10.00 128K 128,000
Bigscience/Mt0 Xxl 13b $500.00 $2000.00 8K 8,192
Core42/Jais 13b Chat $500.00 $2000.00 8K 8,192

Model Details

Ibm/Granite 4 H Small

Ibm/Granite 4 H Small is available via IBM Watsonx with a 20K context window and up to 20,480 output tokens. Pricing: $0.0600/1M input tokens, $0.2500/1M output tokens.

Input: $0.060/1M Output: $0.25/1M Context: 20K
text function calling

Ibm/Granite Guardian 3 2 2b

Ibm/Granite Guardian 3 2 2b is available via IBM Watsonx with a 8K context window and up to 8,192 output tokens. Pricing: $0.1000/1M input tokens, $0.1000/1M output tokens.

Input: $0.10/1M Output: $0.10/1M Context: 8K
text

Ibm/Granite Vision 3 2 2b

Ibm/Granite Vision 3 2 2b is available via IBM Watsonx with a 8K context window and up to 8,192 output tokens. Pricing: $0.1000/1M input tokens, $0.1000/1M output tokens.

Input: $0.10/1M Output: $0.10/1M Context: 8K
text vision

Meta Llama/Llama 3 2 1b Instruct

Meta Llama/Llama 3 2 1b Instruct is available via IBM Watsonx with a 128K context window and up to 128,000 output tokens. Pricing: $0.1000/1M input tokens, $0.1000/1M output tokens.

Input: $0.10/1M Output: $0.10/1M Context: 128K
text function calling

Mistralai/Mistral Small 2503

Mistralai/Mistral Small 2503 is available via IBM Watsonx with a 32K context window and up to 32,000 output tokens. Pricing: $0.1000/1M input tokens, $0.3000/1M output tokens.

Input: $0.10/1M Output: $0.30/1M Context: 32K
text function calling

Mistralai/Mistral Small 3 1 24b Instruct 2503

Mistralai/Mistral Small 3 1 24b Instruct 2503 is available via IBM Watsonx with a 32K context window and up to 32,000 output tokens. Pricing: $0.1000/1M input tokens, $0.3000/1M output tokens.

Input: $0.10/1M Output: $0.30/1M Context: 32K
text function calling

Meta Llama/Llama 3 2 3b Instruct

Meta Llama/Llama 3 2 3b Instruct is available via IBM Watsonx with a 128K context window and up to 128,000 output tokens. Pricing: $0.1500/1M input tokens, $0.1500/1M output tokens.

Input: $0.15/1M Output: $0.15/1M Context: 128K
text function calling

Openai/Gpt Oss 120b

Openai/Gpt Oss 120b is available via IBM Watsonx with a 8K context window and up to 8,192 output tokens. Pricing: $0.1500/1M input tokens, $0.6000/1M output tokens.

Input: $0.15/1M Output: $0.60/1M Context: 8K
text

Ibm/Granite 3 8b Instruct

Ibm/Granite 3 8b Instruct is available via IBM Watsonx with a 8K context window and up to 1,024 output tokens. Pricing: $0.2000/1M input tokens, $0.2000/1M output tokens.

Input: $0.20/1M Output: $0.20/1M Context: 8K
text function calling json mode

Ibm/Granite 3 3 8b Instruct

Ibm/Granite 3 3 8b Instruct is available via IBM Watsonx with a 8K context window and up to 8,192 output tokens. Pricing: $0.2000/1M input tokens, $0.2000/1M output tokens.

Input: $0.20/1M Output: $0.20/1M Context: 8K
text function calling

Ibm/Granite Guardian 3 3 8b

Ibm/Granite Guardian 3 3 8b is available via IBM Watsonx with a 8K context window and up to 8,192 output tokens. Pricing: $0.2000/1M input tokens, $0.2000/1M output tokens.

Input: $0.20/1M Output: $0.20/1M Context: 8K
text

Meta Llama/Llama 3 2 11b Vision Instruct

Meta Llama/Llama 3 2 11b Vision Instruct is available via IBM Watsonx with a 128K context window and up to 128,000 output tokens. Pricing: $0.3500/1M input tokens, $0.3500/1M output tokens.

Input: $0.35/1M Output: $0.35/1M Context: 128K
text vision function calling

Meta Llama/Llama 4 Maverick 17b

Meta Llama/Llama 4 Maverick 17b is available via IBM Watsonx with a 128K context window and up to 128,000 output tokens. Pricing: $0.3500/1M input tokens, $1.40/1M output tokens.

Input: $0.35/1M Output: $1.40/1M Context: 128K
text function calling

Meta Llama/Llama Guard 3 11b Vision

Meta Llama/Llama Guard 3 11b Vision is available via IBM Watsonx with a 128K context window and up to 128,000 output tokens. Pricing: $0.3500/1M input tokens, $0.3500/1M output tokens.

Input: $0.35/1M Output: $0.35/1M Context: 128K
text vision

Mistralai/Pixtral 12b 2409

Mistralai/Pixtral 12b 2409 is available via IBM Watsonx with a 128K context window and up to 128,000 output tokens. Pricing: $0.3500/1M input tokens, $0.3500/1M output tokens.

Input: $0.35/1M Output: $0.35/1M Context: 128K
text vision

Ibm/Granite Ttm 1024 96 R2

Ibm/Granite Ttm 1024 96 R2 is available via IBM Watsonx with a 1K context window and up to 512 output tokens. Pricing: $0.3800/1M input tokens, $0.3800/1M output tokens.

Input: $0.38/1M Output: $0.38/1M Context: 1K
text

Ibm/Granite Ttm 1536 96 R2

Ibm/Granite Ttm 1536 96 R2 is available via IBM Watsonx with a 1K context window and up to 512 output tokens. Pricing: $0.3800/1M input tokens, $0.3800/1M output tokens.

Input: $0.38/1M Output: $0.38/1M Context: 1K
text

Ibm/Granite Ttm 512 96 R2

Ibm/Granite Ttm 512 96 R2 is available via IBM Watsonx with a 1K context window and up to 512 output tokens. Pricing: $0.3800/1M input tokens, $0.3800/1M output tokens.

Input: $0.38/1M Output: $0.38/1M Context: 1K
text

Google/Flan T5 Xl 3b

Google/Flan T5 Xl 3b is available via IBM Watsonx with a 8K context window and up to 8,192 output tokens. Pricing: $0.6000/1M input tokens, $0.6000/1M output tokens.

Input: $0.60/1M Output: $0.60/1M Context: 8K
text

Ibm/Granite 13b Chat

Ibm/Granite 13b Chat is available via IBM Watsonx with a 8K context window and up to 8,192 output tokens. Pricing: $0.6000/1M input tokens, $0.6000/1M output tokens.

Input: $0.60/1M Output: $0.60/1M Context: 8K
text

Ibm/Granite 13b Instruct

Ibm/Granite 13b Instruct is available via IBM Watsonx with a 8K context window and up to 8,192 output tokens. Pricing: $0.6000/1M input tokens, $0.6000/1M output tokens.

Input: $0.60/1M Output: $0.60/1M Context: 8K
text

Meta Llama/Llama 3 3 70b Instruct

Meta Llama/Llama 3 3 70b Instruct is available via IBM Watsonx with a 128K context window and up to 128,000 output tokens. Pricing: $0.7100/1M input tokens, $0.7100/1M output tokens.

Input: $0.71/1M Output: $0.71/1M Context: 128K
text function calling

Sdaia/Allam 1 13b Instruct

Sdaia/Allam 1 13b Instruct is available via IBM Watsonx with a 8K context window and up to 8,192 output tokens. Pricing: $1.80/1M input tokens, $1.80/1M output tokens.

Input: $1.80/1M Output: $1.80/1M Context: 8K
text

Meta Llama/Llama 3 2 90b Vision Instruct

Meta Llama/Llama 3 2 90b Vision Instruct is available via IBM Watsonx with a 128K context window and up to 128,000 output tokens. Pricing: $2.00/1M input tokens, $2.00/1M output tokens.

Input: $2.00/1M Output: $2.00/1M Context: 128K
text vision function calling

Mistralai/Mistral Large

Mistralai/Mistral Large is available via IBM Watsonx with a 131K context window and up to 16,384 output tokens. Pricing: $3.00/1M input tokens, $10.00/1M output tokens.

Input: $3.00/1M Output: $10.00/1M Context: 131K
text function calling json mode

Mistralai/Mistral Medium 2505

Mistralai/Mistral Medium 2505 is available via IBM Watsonx with a 128K context window and up to 128,000 output tokens. Pricing: $3.00/1M input tokens, $10.00/1M output tokens.

Input: $3.00/1M Output: $10.00/1M Context: 128K
text function calling

Bigscience/Mt0 Xxl 13b

Bigscience/Mt0 Xxl 13b is available via IBM Watsonx with a 8K context window and up to 8,192 output tokens. Pricing: $500.00/1M input tokens, $2000.00/1M output tokens.

Input: $500.00/1M Output: $2000.00/1M Context: 8K
text

Core42/Jais 13b Chat

Core42/Jais 13b Chat is available via IBM Watsonx with a 8K context window and up to 8,192 output tokens. Pricing: $500.00/1M input tokens, $2000.00/1M output tokens.

Input: $500.00/1M Output: $2000.00/1M Context: 8K
text

Compare IBM Watsonx model pricing

Use our pricing calculator to find the cheapest IBM Watsonx model for your workload.

Pricing Calculator Compare Models All Models Directory

Related Reading

OpenAI vs Anthropic vs Google: Which AI API Should You Choose? → Cheapest LLM API in 2026: Complete Pricing Comparison → OpenAI API Pricing Guide 2026 →