gpt-oss-120b vs Inkling
OpenAI · US | Thinking Machines Lab · US · Updated June 2026
Quick verdict
Pick gpt-oss-120b for self-hostable on a single 80gb h100 gpu via mxfp4 or configurable reasoning depth (low/medium/high). Pick Inkling for the first model release from mira murati's thinking machines lab (ex-openai cto) - one of the most closely-watched new labs in ai or a 975b-parameter moe (41b active) with native text, image, and audio reasoning in one model.
gpt-oss-120b (OpenAI) and Inkling (Thinking Machines Lab) are two of the models people most often weigh against each other in 2026. gpt-oss-120b is openAI's open-weight 117B-parameter MoE reasoning model (5.1B active) that runs on a single 80GB GPU and approaches o4-mini on reasoning, coding, and tool use. Inkling is mira Murati's Thinking Machines Lab debuts with Inkling - a 975B open-weight MoE with native multimodal reasoning and a dialable thinking-effort control. Their biggest split is context window, and the breakdown below shows exactly how that plays out for your workload.
Key differences at a glance
- ▸Context window: Inkling holds 7.6× more — 1M (~1,500 pages) vs 131K (~197 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
- ▸Recency: Inkling is the newer model by about 11 months (released July 15, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
| Spec | gpt-oss-120b | Inkling |
|---|---|---|
| Provider | OpenAI (US) | Thinking Machines Lab (US) |
| Released | August 5, 2025 | July 15, 2026 |
| Context window | 131K (~197 pages) | 1M (~1,500 pages) |
| Price (in/out) | Open weight (self-host / free) | Open weight (self-host / free) |
| Open weight? | Yes — self-hostable | Yes — self-hostable |
| Modalities | text, code | text, image, audio, code |
| SWE-Bench Verified | 62.4% | Not published |
| MRCR v2 @ 1M | Not published | Not published |
Who wins what
Self-hostable on a single 80GB H100 GPU via MXFP4
gpt-oss-120b
gpt-oss-120b lists self-hostable on a single 80GB H100 GPU via MXFP4 among its strengths; Inkling does not.
Configurable reasoning depth (low/medium/high)
gpt-oss-120b
gpt-oss-120b lists configurable reasoning depth (low/medium/high) among its strengths; Inkling does not.
Agentic tool use, function calling, and code execution
gpt-oss-120b
gpt-oss-120b lists agentic tool use, function calling, and code execution among its strengths; Inkling does not.
The first model release from Mira Murati's Thinking Machines Lab (ex-OpenAI CTO) - one of the most closely-watched new labs in AI
Inkling
gpt-oss-120b is comparatively weak here — 131K context and 5.1B active params trail the largest frontier closed models
A 975B-parameter MoE (41B active) with native text, image, and audio reasoning in one model
Inkling
gpt-oss-120b is comparatively weak here — text-only, no image, audio, or video input
A dialable 'thinking effort' knob (0.2-0.99) that lets you trade speed for depth of reasoning per-request
Inkling
Mira Murati's Thinking Machines Lab debuts with Inkling - a 975B open-weight MoE with native multimodal reasoning and a dialable thinking-effort control — and it carries the larger 1M context.
Largest single-prompt input
Inkling
Its 1M window is about 7.6× larger than gpt-oss-120b's 131K, fitting roughly 1,500 pages in one prompt.
Which should you pick?
Someone analysing very long documents or codebases
→ Inkling
Larger 1M window fits more in one prompt.
Anyone whose priority is self-hostable on a single 80gb h100 gpu via mxfp4
→ gpt-oss-120b
It is specifically built for that.
Anyone whose priority is the first model release from mira murati's thinking machines lab (ex-openai cto) - one of the most closely-watched new labs in ai
→ Inkling
That is its strongest area.
gpt-oss-120b: where it fits
OpenAI's open-weight 117B-parameter MoE reasoning model (5.1B active) that runs on a single 80GB GPU and approaches o4-mini on reasoning, coding, and tool use. Released August 5, 2025 by OpenAI, it is built for self-hostable on a single 80GB H100 GPU via MXFP4, configurable reasoning depth (low/medium/high), agentic tool use, function calling, and code execution, and full chain-of-thought visibility for debugging.
Its trade-offs are real: text-only, no image, audio, or video input, and 131K context and 5.1B active params trail the largest frontier closed models. As an open-weight model, its running cost is your own hardware rather than a per-token fee.
Inkling: where it fits
Mira Murati's Thinking Machines Lab debuts with Inkling - a 975B open-weight MoE with native multimodal reasoning and a dialable thinking-effort control. Released July 15, 2026 by Thinking Machines Lab, it is built for the first model release from Mira Murati's Thinking Machines Lab (ex-OpenAI CTO) - one of the most closely-watched new labs in AI, a 975B-parameter MoE (41B active) with native text, image, and audio reasoning in one model, a dialable 'thinking effort' knob (0.2-0.99) that lets you trade speed for depth of reasoning per-request, and fully open weights (Apache 2.0) at frontier scale - unusual for a model this large and this new.
Its trade-offs: a brand-new lab's first release - no multi-generation track record yet, no official hosted API price - available via third-party hosts only at launch, and independent third-party benchmark verification is still limited given how recently it shipped. As an open-weight model, its running cost is your own hardware rather than a per-token fee.
The bottom line for this matchup
gpt-oss-120b and Inkling overlap enough that the right pick depends on your specific job. Inkling holds the larger context; and each leads in its own area — gpt-oss-120b for self-hostable on a single 80gb h100 gpu via mxfp4, Inkling for the first model release from mira murati's thinking machines lab (ex-openai cto) - one of the most closely-watched new labs in ai. Rather than crowning one, run the same hard task through both once and let the results decide.
Want both gpt-oss-120b and Inkling without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.
See pricingFrequently asked questions
Is gpt-oss-120b or Inkling better for coding?
Public SWE-Bench figures are not available for Inkling, so the honest test is your own repository — run an identical real bug through both. By design, gpt-oss-120b leans toward self-hostable on a single 80gb h100 gpu via mxfp4 while Inkling leans toward the first model release from mira murati's thinking machines lab (ex-openai cto) - one of the most closely-watched new labs in ai, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, gpt-oss-120b or Inkling?
They are priced almost identically, so cost will not decide between them.
Which has the bigger context window?
Inkling — 1M vs 131K, about 7.6× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both gpt-oss-120b and Inkling together?
Yes — a multi-model platform like LumiChats gives you gpt-oss-120b, Inkling and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, gpt-oss-120b or Inkling?
Inkling — released July 15, 2026, about 11 months after gpt-oss-120b.
Related comparisons
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.