impulse

Allam 1 13B Instruct

API id allam-1-13b-instruct
Input / 1M
$1.80
at IBM watsonx.ai
Output / 1M
$1.80
at IBM watsonx.ai
Context window
8K
tokens
Max output
8K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at IBM watsonx.ai, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$1.80$1.80

What it costs a month

At IBM watsonx.ai list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$675
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$929
  • Coding agent1,000 requests a day, 40K in / 2K out$2,268
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$4,752
Use your own numbers

Where to run it

1 host serve Allam 1 13B Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
allam-1-13b-instruct
$1.80 / $1.80

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 IBM watsonx.ai.

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
    6% less
  • Grok 4.20 Multi Agent
    xAI · on xAI
    $1.25 / $2.50
    Has every key capability
    13% less
  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    17% 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
    4% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    52% less
  • Nemotron 3 Ultra 550B A55B
    NVIDIA · on Perplexity
    $0.25 / $2.50
    Has every key capability
    55% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    56% less

Call it

Using IBM watsonx.ai's API.

Python
from litellm import completion

response = completion(
    model="watsonx/allam-1-13b-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Allam 1 13B Instruct cost?

On IBM watsonx.ai, Allam 1 13B Instruct costs $1.80 per million input tokens and $1.80 per million output tokens.

Which APIs offer Allam 1 13B Instruct?

Allam 1 13B Instruct runs on 1 API: IBM watsonx.ai.

What is Allam 1 13B Instruct's context window?

8K tokens, with up to 8K tokens in one reply.

Is Allam 1 13B Instruct being retired?

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

What are cheaper alternatives to Allam 1 13B Instruct?

Models that cost less and keep most of what it can do: GPT-5.4 Mini on OpenAI (6% less), Grok 4.20 Multi Agent on xAI (13% less) and Inkling on DeepInfra (4% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Allam 1 13B Instruct's API model id?

Use allam-1-13b-instruct with IBM watsonx.ai.

Sources

Raw catalog entry for allam-1-13b-instruct on IBM watsonx.ai
{
  "max_input_tokens": 8192,
  "max_output_tokens": 8192,
  "input_cost_per_token": 0.0000018,
  "output_cost_per_token": 0.0000018,
  "litellm_provider": "watsonx",
  "mode": "chat",
  "supports_function_calling": false,
  "supports_parallel_function_calling": false,
  "supports_vision": false
}