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
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
3 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Prime Intellect prime_intellect/thinkingmachines/inkling-2-small | $0.15/M | $0.50/M |
DeepInfra deepinfra/inkling-small | $0.45/M | $1.20/M |
OpenRouter openrouter/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.
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 better46tokens/sacross providers
Time to first token
Lower is better0.5sacross providers
Response latency
Lower is better5.9sacross providers
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
- 95Inkling-Small29.4
- 94Qwen3.5 397B-A17B29.5
- 96Kimi K2.529.3
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SWE-bench Verifiedthinkingmachines.ai | 80.2% | thinkingmachines.ai | Jul 30, 2026 |
| Terminal-Bench 2.1 (best harness)thinkingmachines.ai | 64.7% | thinkingmachines.ai | Jul 30, 2026 |
| SWE-bench Pro (public)thinkingmachines.ai | 55.9% | thinkingmachines.ai | Jul 30, 2026 |
| Terminal-Bench 4.0Vals AI | 0% | Vals AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MCP Atlas (all)thinkingmachines.ai | 79.2% | thinkingmachines.ai | Jul 30, 2026 |
| BrowseComp (with context management)thinkingmachines.ai | 77.4% | thinkingmachines.ai | Jul 30, 2026 |
| Toolathlon Verifiedthinkingmachines.ai | 54.4% | thinkingmachines.ai | Jul 30, 2026 |
| Toolathlon-VerifiedHKUST | 54.4% | HKUST | Jul 30, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 88.5% | Epoch AI | Oct 5, 2026 |
| ARC-AGI-1thinkingmachines.ai | 84% | thinkingmachines.ai | Jul 30, 2026 |
| ARC-AGI-2thinkingmachines.ai | 40.1% | thinkingmachines.ai | Jul 30, 2026 |
| Chess PuzzlesEpoch AI | 18% | Epoch AI | Oct 5, 2026 |
| Mystery Game PuzzlesEpoch AI | 6% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2026thinkingmachines.ai | 95.5% | thinkingmachines.ai | Jul 30, 2026 |
| HMMT Feb 2026thinkingmachines.ai | 90.2% | thinkingmachines.ai | Jul 30, 2026 |
| OTIS Mock AIME 2024-2025Epoch AI | 90% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 46.3% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 17.1% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| IFBenchthinkingmachines.ai | 82.2% | thinkingmachines.ai | Jul 30, 2026 |
| SimpleQA Verifiedthinkingmachines.ai | 20.6% | thinkingmachines.ai | Jul 30, 2026 |
| SimpleQA VerifiedEpoch AI | 19.1% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| CharXiv RQ (with python)thinkingmachines.ai | 81.3% | thinkingmachines.ai | Jul 30, 2026 |
| CharXiv RQthinkingmachines.ai | 77.4% | thinkingmachines.ai | Jul 30, 2026 |
| MMAUthinkingmachines.ai | 77% | thinkingmachines.ai | Jul 30, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena WebDevLMArena | 1408 Elo · #86 of 124 | LMArena | Nov 19, 2026 |
| LMArena EloLMArena | 1406 Elo · #120 of 191 | LMArena | Nov 19, 2026 |
| LMArena VisionLMArena | 1208 Elo · #69 of 91 | LMArena | Nov 19, 2026 |
| LMArena AgentLMArena | -0.1853 · #67 of 68 | LMArena | Nov 18, 2026 |
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.