impulse

Inkling Small

Open weights

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.

API id Inkling-SmallReleased 30 Jul 2026 (Jul 2026)
Input / 1M
$0.45
at DeepInfra
Output / 1M
$1.20
at DeepInfra
Context window
524K
tokens
Max output
524K
tokens per reply
Hosts
2
2 listings
Released
Jul 2026
30 Jul 2026

Pricing

List prices at DeepInfra, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.45$1.20
Cached input
78% off input
$0.10

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$193
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$175
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$318
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,368
Use your own numbers

Where to run it

2 hosts serve Inkling Small. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
Inkling-Small
$0.45 / $1.20
BasetenInference
inkling-small
$0.50 / $1.20
+6% 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
TextImages
Produces
Text
Features
Prompt caching
Open weights
License: Apache-2.0
Runs in about 638.3 GB of GPU memory

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 DeepInfra.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    27% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    69% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    69% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    59% less

Open-weight picks

  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    18% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    24% less
  • MiMo V2.6 Pro
    Xiaomi · on GMI Cloud
    $0.348 / $0.696
    Has every key capability
    32% less
  • Muse Glimmer 30B
    Meta · on EmpirioLabs AI
    $0.20 / $0.80
    Has every key capability
    45% less

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/Inkling-Small",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Inkling Small cost?

On DeepInfra, Inkling Small costs $0.45 per million input tokens and $1.20 per million output tokens. Cached input costs $0.10 per million tokens.

Which APIs offer Inkling Small?

Inkling Small runs on 2 APIs: DeepInfra and Baseten.

What is Inkling Small's context window?

524K tokens, with up to 524K tokens in one reply.

Is Inkling Small being retired?

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

What are cheaper alternatives to Inkling Small?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (27% less), Claude Haiku 5.5 on Anthropic (69% less) and DeepSeek Flash on DeepSeek (18% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Inkling Small released?

Independent released it on 30 Jul 2026.

What is Inkling Small's API model id?

Use Inkling-Small with DeepInfra. Other hosts use their own ids: inkling-small on Baseten.

Sources

Raw catalog entry for Inkling-Small on DeepInfra
{
  "max_output_tokens": 524288,
  "max_input_tokens": 524288,
  "input_cost_per_token": 4.5e-7,
  "output_cost_per_token": 0.0000012,
  "cache_read_input_token_cost": 1e-7,
  "supports_prompt_caching": true,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_tool_choice": true,
  "supports_response_schema": true,
  "supports_reasoning": true,
  "supports_vision": true,
  "source": "https://deepinfra.com/pricing"
}