Inkling 2 Small
Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total.
inkling-2-smallReleased 9 Nov 2026 (9 days ago)Pricing
List prices at Cloudflare Workers AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.30 | $1.00 | |
| Cached input 67% off input | $0.10 | 67% off input |
What it costs a month
At Cloudflare Workers AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$147
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$132
- Coding agent1,000 requests a day, 40K in / 2K out, cached$252
- Overnight batch20,000 requests a day, 4K in / 0.4K out$960
Where to run it
3 hosts serve Inkling 2 Small. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
inkling-2-small | $0.30 / $1.00 | inkling-2-small | |
Nebius AI StudioInference Inkling-2-Small | $0.30 / $1.00 | Inkling-2-Small | |
Together AIInference Inkling-2-Small | $0.30 / $1.00 | Inkling-2-Small |
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: Apache-2.0Runs in about 1425.7 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 Cloudflare Workers AI.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 3% less
- 58% less
- 58% less
- 45% less
Open-weight picks
- 5% less
- 8% less
- 17% less
- 22% less
Call it
Using Cloudflare Workers AI's API.
from litellm import completion
response = completion(
model="cloudflare/inkling-2-small",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Inkling 2 Small cost?
On Cloudflare Workers AI, Inkling 2 Small costs $0.30 per million input tokens and $1.00 per million output tokens. Cached input costs $0.10 per million tokens.
Which APIs offer Inkling 2 Small?
Inkling 2 Small runs on 3 APIs: Cloudflare Workers AI, Nebius AI Studio and Together AI.
What is Inkling 2 Small's context window?
1M tokens, with up to 1M tokens in one reply.
Is Inkling 2 Small being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Inkling 2 Small?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (3% less), Claude Haiku 5.5 on Anthropic (58% less) and GLM 4 6v on Novita AI (5% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Inkling 2 Small released?
Independent released it on 9 Nov 2026.
What is Inkling 2 Small's API model id?
Use inkling-2-small with Cloudflare Workers AI. Other hosts use their own ids: Inkling-2-Small on Nebius AI Studio, Inkling-2-Small on Together AI.
Sources
Raw catalog entry for inkling-2-small on Cloudflare Workers AI
{
"cache_read_input_token_cost": 1e-7,
"input_cost_per_token": 3e-7,
"litellm_provider": "cloudflare",
"max_input_tokens": 1048576,
"mode": "chat",
"output_cost_per_token": 0.000001,
"source": "https://developers.cloudflare.com/workers-ai/models/inkling-2-small/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_vision": true
}