impulse

Pegasus 1.5

API id twelvelabs.pegasus-1-5-v1:0
Input / 1M
$0.00
at Amazon Bedrock
Output / 1M
$7.50
at Amazon Bedrock
Context window
261K
tokens
Max output
98K
tokens per reply
Hosts
1
3 listings
Released
-
date not published

Pricing

List prices at Amazon Bedrock, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.00$7.50

What it costs a month

At Amazon Bedrock list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$563
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$270
  • Coding agent1,000 requests a day, 40K in / 2K out$450
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,800
Use your own numbers

Where to run it

1 host serve Pegasus 1.5. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
twelvelabs.pegasus-1-5-v1:0
$0.00 / $7.50
Show 2 more listings: regions, snapshots and variants
Amazon Bedrock
us
us.twelvelabs.pegasus-1-5-v1:0
$0.00 / $7.50
global
global.twelvelabs.pegasus-1-5-v1:0
$0.00 / $7.50

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
TextVideo
Produces
Text
Features
Video input

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 Amazon Bedrock.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • GPT-5.4 Mini
    OpenAI · on OpenAI
    $0.75 / $4.50
    Has every key capability
    10% less
  • Grok 4.20 Multi Agent
    xAI · on xAI
    $1.25 / $2.50
    Has every key capability
    17% less
  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    20% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    89% less

Open-weight picks

  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    8% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    54% less
  • Nemotron 3 Ultra 550B A55B
    NVIDIA · on Perplexity
    $0.25 / $2.50
    Has every key capability
    57% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    58% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedPegasus 1.5Latest$0.00 / $7.50
  2. UndatedPegasus 1.2$0.00 / $7.50

Call it

Using Amazon Bedrock's API.

Python
from litellm import completion

response = completion(
    model="bedrock/twelvelabs.pegasus-1-5-v1:0",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Pegasus 1.5 cost?

On Amazon Bedrock, Pegasus 1.5 costs $7.50 per million output tokens.

Which APIs offer Pegasus 1.5?

Pegasus 1.5 runs on 1 API: Amazon Bedrock.

What is Pegasus 1.5's context window?

261K tokens, with up to 98K tokens in one reply.

Is Pegasus 1.5 being retired?

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

Is there a newer version of Pegasus 1.5?

No. Pegasus 1.5 is the newest model in its line.

What are cheaper alternatives to Pegasus 1.5?

Models that cost less and keep most of what it can do: GPT-5.4 Mini on OpenAI (10% less), Grok 4.20 Multi Agent on xAI (17% less) and Inkling on DeepInfra (8% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Pegasus 1.5's API model id?

Use twelvelabs.pegasus-1-5-v1:0 with Amazon Bedrock.

Sources

Raw catalog entry for twelvelabs.pegasus-1-5-v1:0 on Amazon Bedrock
{
  "input_cost_per_video_per_second": 0.00049,
  "litellm_provider": "bedrock",
  "max_input_tokens": 261120,
  "max_output_tokens": 98304,
  "mode": "chat",
  "output_cost_per_token": 0.0000075,
  "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html",
  "supports_video_input": true
}