impulse

Llama 3.2 90B Vision Instruct

Open weights
API id llama-v3p2-90b-vision-instruct
Input / 1M
$0.90
at Fireworks AI
Output / 1M
$0.90
at Fireworks AI
Context window
131K
tokens
Max output
16K
tokens per reply
Hosts
5
5 listings
Released
-
date not published

Pricing

List prices at Fireworks AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.90$0.90

What it costs a month

At Fireworks AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$338
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$464
  • Coding agent1,000 requests a day, 40K in / 2K out$1,134
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$2,376
Use your own numbers

Where to run it

5 hosts serve Llama 3.2 90B Vision Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Fireworks AIInference
llama-v3p2-90b-vision-instruct
$0.90 / $0.90
llama-3-2-90b-vision-instruct
$2.00 / $2.00
+122% vs headline
meta.llama-3.2-90b-vision-instruct
$2.00 / $2.00
+122% vs headline
llama-3.2-90b-vision-instruct-maas
-
NVIDIA NIMInference
llama-3.2-90b-vision-instruct
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImages
Produces
Text
Open weights
License: Llama Community License
Runtimes: Ollama, TGI, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Fireworks AI.

Smaller Meta models

Other frontier labs

  • Gemini 3.5 Flash Lite
    Google · on Google AI Studio
    $0.30 / $2.50
    Has every key capability
    6% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    49% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    78% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    78% less

Open-weight picks

  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    24% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    29% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    42% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    46% less

Call it

Using Fireworks AI's API.

Python
from litellm import completion

response = completion(
    model="fireworks_ai/llama-v3p2-90b-vision-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Llama 3.2 90B Vision Instruct cost?

On Fireworks AI, Llama 3.2 90B Vision Instruct costs $0.90 per million input tokens and $0.90 per million output tokens.

Which APIs offer Llama 3.2 90B Vision Instruct?

Llama 3.2 90B Vision Instruct runs on 5 APIs: Fireworks AI, IBM watsonx.ai, Oracle OCI, Vertex AI and NVIDIA NIM.

What is Llama 3.2 90B Vision Instruct's context window?

131K tokens, with up to 16K tokens in one reply.

Is Llama 3.2 90B Vision Instruct being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Llama 3.2 90B Vision Instruct?

Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (86% less), Gemini 3.5 Flash Lite on Google AI Studio (6% less), GPT-5.4 Nano on OpenAI (49% less) and Kimi K2.7 Code on CLF AI Gateway (24% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Llama 3.2 90B Vision Instruct's API model id?

Use llama-v3p2-90b-vision-instruct with Fireworks AI. Other hosts use their own ids: llama-3-2-90b-vision-instruct on IBM watsonx.ai, meta.llama-3.2-90b-vision-instruct on Oracle OCI, llama-3.2-90b-vision-instruct-maas on Vertex AI, llama-3.2-90b-vision-instruct on NVIDIA NIM.

Sources

Raw catalog entry for llama-v3p2-90b-vision-instruct on Fireworks AI
{
  "input_cost_per_token": 9e-7,
  "litellm_provider": "fireworks_ai",
  "max_input_tokens": 131072,
  "max_output_tokens": 16384,
  "mode": "chat",
  "output_cost_per_token": 9e-7,
  "source": "https://fireworks.ai/pricing",
  "supports_response_schema": true,
  "supports_tool_choice": false,
  "supports_vision": true
}