TokenRate

Llama 3.2 90B Vision Pricing

Balanced

Meta · 128K tokens context

Llama 3.2 90B Vision from Meta costs $0.900 per 1 million input tokens and $0.900 per 1 million output tokens as of June 2026. The model supports a 128,000-token context window (approximately 96,000 words) with a 4K-token maximum output. A typical 1,000-token request costs $0.0009 in input charges; a 10,000-token request costs $0.0090.

Llama 3.2 90B Vision pricing and capability summary
Input price$0.900 / 1M tokens
Output price$0.900 / 1M tokens
Output / input ratio1.0×
Context window128,000 tokens (~96,000 words)
Maximum output4,096 tokens
Cost per 1K tokens (input)$0.0009
TierBalanced
Last verified

Llama 3.2 90B Vision is Meta's large open-weight multimodal model — strong on image understanding and visual reasoning while remaining self-hostable. Best open multimodal option before Llama 4.

Reference pricing · updated 2026-06-10

Input Price

$0.900

per 1 million tokens

Output Price

$0.900

per 1 million tokens

Context Window

128K tokens

max 4K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.0012$0.00036
10-page document (2,500 words)3,333$0.003$0.0009
1,000 lines of code5,000$0.0045$0.00135
100K token document100,000$0.09$0.027

Output cost estimated at 30% of input token count. Use the calculator for exact figures.

Strengths

  • Best open-weight multimodal before Llama 4
  • Self-hostable
  • Competitive visual reasoning

Limitations

  • Hosting requires significant GPU resources
  • Symmetric pricing model

Best Use Cases

Production vision pipelines
On-prem multimodal apps
Visual document analysis

Calculate Llama 3.2 90B Vision Costs

Use the TokenRate calculator to convert any budget, token count, or text into exact Llama 3.2 90B Vision costs — and compare across all models.

Open Calculator →

Llama 3.2 90B Vision — FAQ

Related Models

Related Guides