Pick Apple Foundation Models 3 for runs entirely on-device on iphone - no api call, no per-token cost, works offline or the 20b sparse 'core advanced' variant lifted on-device output quality from 23% to 46% user preference in apple's own testing versus the prior generation. 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. Choose Inkling if you need self-hosting or data privacy; Apple Foundation Models 3 if you want a managed API.
Apple Foundation Models 3 (Apple) and Inkling (Thinking Machines Lab) are two of the models people most often weigh against each other in 2026. Apple Foundation Models 3 is apple's on-device model family - genuinely small context and no API access, but private, offline, and free to run on every iPhone. 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. They diverge most on context window and open vs. closed weights — each quantified below from the models' real specs.
Key differences
Cost model: Inkling ships open weights you can self-host (hardware cost only, no per-token fee), while Apple Foundation Models 3 is API-metered at Not published. Your choice depends on whether you want zero marginal cost at the price of running infrastructure.
Context window: Inkling holds 244× more — 1M (~1,500 pages) vs 4K (~6 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 44 days (released July 15, 2026), usually meaning fresher training data and capabilities.
Specifications
Spec
Apple Foundation Models 3
Inkling
Provider
Apple (US)
Thinking Machines Lab (US)
Released
June 2026
July 15, 2026
Context window
4K (~6 pages)
1M (~1,500 pages)
Price (in/out)
Not published
Open weight (self-host / free)
Open weight?
No — API only
Yes — self-hostable
Modalities
text, image
text, image, audio, code
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Runs entirely on-device on iPhone - no API call, no per-token cost, works offline: Apple Foundation Models 3 — Apple Foundation Models 3 lists runs entirely on-device on iPhone - no API call, no per-token cost, works offline among its strengths; Inkling does not.
The 20B sparse 'Core Advanced' variant lifted on-device output quality from 23% to 46% user preference in Apple's own testing versus the prior generation: Apple Foundation Models 3 — Inkling is comparatively weak here — a brand-new lab's first release - no multi-generation track record yet
Deep integration with iOS apps via the Foundation Models framework, now open to third-party LLM providers too: Apple Foundation Models 3 — Inkling is comparatively weak here — no official hosted API price - available via third-party hosts only at launch
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 — Open weights make this possible at all — Apple Foundation Models 3 is API-only, so it cannot leave the vendor's servers.
A 975B-parameter MoE (41B active) with native text, image, and audio reasoning in one model: Inkling — Apple Foundation Models 3 is comparatively weak here — a genuinely small context window (about 4,096 tokens, shared between input and output) - far below cloud frontier models
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 244× larger than Apple Foundation Models 3's 4K, 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.
A team with data-privacy or self-hosting needs: Inkling — Open weights let you run it on your own hardware; Apple Foundation Models 3 is API-only.
Anyone whose priority is runs entirely on-device on iphone - no api call, no per-token cost, works offline: Apple Foundation Models 3 — 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.
Apple Foundation Models 3: where it fits
Apple's on-device model family - genuinely small context and no API access, but private, offline, and free to run on every iPhone. Released June 2026 by Apple, it is built for runs entirely on-device on iPhone - no API call, no per-token cost, works offline, the 20B sparse 'Core Advanced' variant lifted on-device output quality from 23% to 46% user preference in Apple's own testing versus the prior generation, deep integration with iOS apps via the Foundation Models framework, now open to third-party LLM providers too, and zero marginal cost and strong privacy - nothing leaves the device.
Its trade-offs are real: a genuinely small context window (about 4,096 tokens, shared between input and output) - far below cloud frontier models, not comparable in raw capability to frontier cloud models - built for efficiency and privacy, not benchmark leadership, and no public API pricing since it isn't sold per-token - only usable within Apple's own platforms.
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
The defining split here is open vs. closed. Inkling gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Apple Foundation Models 3 gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Frequently asked questions
Is Apple Foundation Models 3 or Inkling better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Apple Foundation Models 3 leans toward runs entirely on-device on iphone - no api call, no per-token cost, works offline 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, Apple Foundation Models 3 or Inkling?
Inkling is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Apple Foundation Models 3 is API-metered at Not published. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
Which has the bigger context window?
Inkling — 1M vs 4K, about 244× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both Apple Foundation Models 3 and Inkling together?
Yes — a multi-model platform like LumiChats gives you Apple Foundation Models 3, 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, Apple Foundation Models 3 or Inkling?
Inkling — released July 15, 2026, about 44 days after Apple Foundation Models 3.
Apple Foundation Models 3 vs Inkling
Apple · US | Thinking Machines Lab · US · Updated June 2026
Quick verdict
Pick Apple Foundation Models 3 for runs entirely on-device on iphone - no api call, no per-token cost, works offline or the 20b sparse 'core advanced' variant lifted on-device output quality from 23% to 46% user preference in apple's own testing versus the prior generation. 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. Choose Inkling if you need self-hosting or data privacy; Apple Foundation Models 3 if you want a managed API.
Apple Foundation Models 3 (Apple) and Inkling (Thinking Machines Lab) are two of the models people most often weigh against each other in 2026. Apple Foundation Models 3 is apple's on-device model family - genuinely small context and no API access, but private, offline, and free to run on every iPhone. 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. They diverge most on context window and open vs. closed weights — each quantified below from the models' real specs.
Key differences at a glance
▸Cost model: Inkling ships open weights you can self-host (hardware cost only, no per-token fee), while Apple Foundation Models 3 is API-metered at Not published. Your choice depends on whether you want zero marginal cost at the price of running infrastructure.
▸Context window: Inkling holds 244× more — 1M (~1,500 pages) vs 4K (~6 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 44 days (released July 15, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
Spec
Apple Foundation Models 3
Inkling
Provider
Apple (US)
Thinking Machines Lab (US)
Released
June 2026
July 15, 2026
Context window
4K (~6 pages)
1M (~1,500 pages)
Price (in/out)
Not published
Open weight (self-host / free)
Open weight?
No — API only
Yes — self-hostable
Modalities
text, image
text, image, audio, code
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Runs entirely on-device on iPhone - no API call, no per-token cost, works offline
Apple Foundation Models 3
Apple Foundation Models 3 lists runs entirely on-device on iPhone - no API call, no per-token cost, works offline among its strengths; Inkling does not.
The 20B sparse 'Core Advanced' variant lifted on-device output quality from 23% to 46% user preference in Apple's own testing versus the prior generation
Apple Foundation Models 3
Inkling is comparatively weak here — a brand-new lab's first release - no multi-generation track record yet
Deep integration with iOS apps via the Foundation Models framework, now open to third-party LLM providers too
Apple Foundation Models 3
Inkling is comparatively weak here — no official hosted API price - available via third-party hosts only at launch
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
Open weights make this possible at all — Apple Foundation Models 3 is API-only, so it cannot leave the vendor's servers.
A 975B-parameter MoE (41B active) with native text, image, and audio reasoning in one model
Inkling
Apple Foundation Models 3 is comparatively weak here — a genuinely small context window (about 4,096 tokens, shared between input and output) - far below cloud frontier models
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 244× larger than Apple Foundation Models 3's 4K, 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.
A team with data-privacy or self-hosting needs
→ Inkling
Open weights let you run it on your own hardware; Apple Foundation Models 3 is API-only.
Anyone whose priority is runs entirely on-device on iphone - no api call, no per-token cost, works offline
→ Apple Foundation Models 3
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.
Apple Foundation Models 3: where it fits
Apple's on-device model family - genuinely small context and no API access, but private, offline, and free to run on every iPhone. Released June 2026 by Apple, it is built for runs entirely on-device on iPhone - no API call, no per-token cost, works offline, the 20B sparse 'Core Advanced' variant lifted on-device output quality from 23% to 46% user preference in Apple's own testing versus the prior generation, deep integration with iOS apps via the Foundation Models framework, now open to third-party LLM providers too, and zero marginal cost and strong privacy - nothing leaves the device.
Its trade-offs are real: a genuinely small context window (about 4,096 tokens, shared between input and output) - far below cloud frontier models, not comparable in raw capability to frontier cloud models - built for efficiency and privacy, not benchmark leadership, and no public API pricing since it isn't sold per-token - only usable within Apple's own platforms.
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
The defining split here is open vs. closed. Inkling gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Apple Foundation Models 3 gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Want both Apple Foundation Models 3 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.
Is Apple Foundation Models 3 or Inkling better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Apple Foundation Models 3 leans toward runs entirely on-device on iphone - no api call, no per-token cost, works offline 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, Apple Foundation Models 3 or Inkling?
Inkling is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Apple Foundation Models 3 is API-metered at Not published. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
Which has the bigger context window?
Inkling — 1M vs 4K, about 244× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both Apple Foundation Models 3 and Inkling together?
Yes — a multi-model platform like LumiChats gives you Apple Foundation Models 3, 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, Apple Foundation Models 3 or Inkling?
Inkling — released July 15, 2026, about 44 days after Apple Foundation Models 3.
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.