+
+
Llama 3.2 90B Vision
meta-llama/llama-3-2-90b-vision-instruct
Share
Llama 3.2 90B Vision is a multimodal capability available through HOROS. It can be composed into missions requiring advanced vision and perception. HOROS evaluates the capability against workload requirements before deployment.
+
+
Pricing
USD, pay per token$0.80
per 1M input tokens$0.08
per 1M cached input tokens$2.00
per 1M output tokens+
+
Measured performance
Output speed
115
output tok/s, model onlyTime to first token
450
milliseconds to first reasoning tokenCache hit rate
94.2%last 24 hours
+
+
Access
Confirm how your client reaches this model.
Provider
Meta
API compatibility
Mission-compatible Outcome Intents
Anthropic compatibility
Anthropic-compatible Messages, POST /v1/messages
Accepted input
Text, images
Availability
Available
Data retention
Your state and execution memory are never stored or used for external model training.
Capacity
Check the limits your workload must fit.
Context window
128,000 tokens
Maximum request size
10.0 MB per request
Maximum generated output
8,192 tokens
Capabilities
See which request modes the API supports.
Tool calling
Supported
JSON mode
Supported
Streaming
Supported
Precision
FP8
View Full Spec
+
+
Code examples
Set HOROS_GATEWAY_KEY to your workspace API key before using an example.
CLIENT_REQUEST_ID="$(uuidgen)"
curl -X POST "https://api.horos.com/v1/chat/completions" \
-H "Authorization: Bearer $HOROS_GATEWAY_KEY" \
-H "X-Client-Request-Id: $CLIENT_REQUEST_ID" \
-H "Content-Type: application/json" \
-d '{"model":"llama-3-2-90b-vision-instruct","messages":[{"role":"user","content":"Hello"}],"max_tokens":2048}'Trust and provenance
Verify the company and operating credentials behind this capability.
HOROS is a product of System Integration.