impulse

Titan Text Lite

API id amazon.titan-text-lite-v1
Input / 1M
$0.15
at Amazon Bedrock
Output / 1M
$0.20
at Amazon Bedrock
Context window
42K
tokens
Max output
4K
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$0.15$0.20

What it costs a month

At Amazon Bedrock list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$60.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$79.20
  • Coding agent1,000 requests a day, 40K in / 2K out$192
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$408
Use your own numbers

Where to run it

1 host serve Titan Text Lite. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
amazon.titan-text-lite-v1
$0.15 / $0.20
Show 2 more listings: regions, snapshots and variants
Amazon Bedrock
us-gov-east-1
amazon.titan-text-lite-v1
$0.30 / $0.40
+100% vs headline
us-gov-west-1
amazon.titan-text-lite-v1
$0.30 / $0.40
+100% vs headline

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
Text
Produces
Text

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 Amazon models

  • Nova Lite
    Amazon · on Amazon Nova
    $0.06 / $0.24
    Has every key capability
    35% less
  • Nova Micro
    Amazon · on Amazon Nova
    $0.035 / $0.14
    Has every key capability
    62% less

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    2% less
  • Ministral 8B 2512
    Mistral AI · on Mistral AI
    $0.15 / $0.15
    Has every key capability
    8% less
  • MiMo V2.5
    Xiaomi · on GMI Cloud
    $0.119 / $0.238
    Has every key capability
    8% less
  • DeepSeek V4.1 Flash
    DeepSeek · on Sail
    $0.09 / $0.30
    Has every key capability
    12% less

Call it

Using Amazon Bedrock's API.

Python
from litellm import completion

response = completion(
    model="bedrock/amazon.titan-text-lite-v1",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Titan Text Lite cost?

On Amazon Bedrock, Titan Text Lite costs $0.15 per million input tokens and $0.20 per million output tokens.

Which APIs offer Titan Text Lite?

Titan Text Lite runs on 1 API: Amazon Bedrock.

What is Titan Text Lite's context window?

42K tokens, with up to 4K tokens in one reply.

Is Titan Text Lite being retired?

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

What are cheaper alternatives to Titan Text Lite?

Models that cost less and keep most of what it can do: Nova Lite on Amazon Nova (35% less) and Gemma 4 31B IT on W&B Inference (2% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Titan Text Lite's API model id?

Use amazon.titan-text-lite-v1 with Amazon Bedrock.

Sources

Raw catalog entry for amazon.titan-text-lite-v1 on Amazon Bedrock
{
  "input_cost_per_token": 1.5e-7,
  "litellm_provider": "bedrock",
  "max_input_tokens": 42000,
  "max_output_tokens": 4000,
  "mode": "chat",
  "output_cost_per_token": 2e-7
}