Skip to main content

Inkling Small

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

Model card on Hugging Face
Input / output price
$0.15 / $0.50 per 1M
Context
1M tokens
Released
Jul 30, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "inkling-small".

Read docs

Providers

3 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Prime Intellectprime_intellect/thinkingmachines/inkling-2-small
$0.15/M$0.50/M
DeepInfradeepinfra/inkling-small
$0.45/M$1.20/M
OpenRouteropenrouter/inkling-small
$0.45/M$1.20/M

Is a provider down? OpenRouter status

Pricing

Averaged across 3 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.35 per 1M
Average output
$0.97 per 1M
Average cache read
$0.08 per 1M
Average cache write
$0.15 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.45/MDeepInfra and OpenRouterLowest$0.15/MPrime Intellect

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

46tokens/sacross providers

Faster than 64% of the other 596 models on the gateway

Time to first token

Lower is better

0.5sacross providers

Faster than 92% of the other 153 models on the gateway

Response latency

Lower is better

5.9sacross providers

Faster than 28% of the other 776 models on the gateway

Benchmarks

The Respan Index plus 29 published scores from 5 sources, each linked to where it was published.

29.4/ 100

Respan Index#95 of 176

176 ranked models. The shaded band is this model's 95% interval, 25.8 to 33.6. Qwen3.5 397B-A17B and Kimi K2.5 fall inside it, so the gap is within the margin of error.
Inkling Small by category: Coding 5.7, Agents 41.5, Reasoning 32.2, Knowledge & language 19.1, Human preference 50.9
  1. 95Inkling-Small29.4
  2. 94Qwen3.5 397B-A17B29.5
  3. 96Kimi K2.529.3

Published scores

BenchmarkScore
SWE-bench Verifiedthinkingmachines.ai80.2%
Terminal-Bench 2.1 (best harness)thinkingmachines.ai64.7%
SWE-bench Pro (public)thinkingmachines.ai55.9%
Terminal-Bench 4.0Vals AI0%

Compare Inkling Small: Inkling-Small vs Inkling 2 Small, Inkling-Small vs Inkling

Apps

Use Inkling Small in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Inkling Small FAQ

Short answers, built from the data on this page.

Inkling Small is a model from Thinking Machines, released on Jul 30, 2026. Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.

On the Respan gateway, Inkling Small costs from $0.15 per 1M input tokens and $0.50 per 1M output tokens on Prime Intellect, after gateway discounts. Averaged across its 3 providers, it costs $0.35 per 1M input tokens and $0.97 per 1M output tokens.

Inkling Small is available through 3 providers: Prime Intellect, DeepInfra, and OpenRouter.

Inkling Small accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "inkling-small". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Inkling Small scores 29.4 out of 100 on the Respan Index v1.1, ranking #95 of 176 models. By category: Coding 5.7, Agents 41.5, Reasoning 32.2, Knowledge & language 19.1, and Human preference 50.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Inkling Small has 29 published benchmark scores, including SWE-bench Verified 80.2%, MCP Atlas (all) 79.2%, and GPQA Diamond 88.5%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.