Mistral Large 4 vs Inkling vs Inkling Small
Too close to call on our weighted score (Inkling Small 68, Mistral Large 4 67, Inkling 63). The right pick depends on what you value most.
Mistral AIMistral Large 4
67/100- ECI150.6
- Price$0.70 / $2.10
- Context1.05M
Thinking MachinesInkling
63/100- ECI148.5
- Price$1.00 / $4.05
- Context1.05M
- Thinking Machines
Inkling Small
68/100- ECI150.5
- Price$0.58 / $1.44
- Context1.05M
Too close to call
It is close. Our weighted score puts them within 1 points (Inkling Small 68/100, Mistral Large 4 67/100, Inkling 63/100), so choose by what matters most for your work: Mistral Large 4 for raw capability and Inkling Small on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityMistral Large 4Capabilities Index (ECI): Mistral Large 4 150.6 · Inkling Small 150.5 · Inkling 148.5
- Lowest priceInkling SmallInkling Small $0.795 · Mistral Large 4 $1.05 · Inkling $1.76 per 1M tokens (3:1 blend)
- Longest contextAbout the sameMistral Large 4 1,048,576 · Inkling 1,048,576 · Inkling Small 1,048,576 tokens
- Widest inputsInkling and Inkling SmallMistral Large 4: Text, Images · Inkling: Text, Images, Audio · Inkling Small: Text, Images, Audio
- Self-hostingInkling and Inkling SmallPublishes downloadable weights (Apache-2.0)
| Measure | Weight | Mistral Large 4 | Inkling | Inkling Small |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 77 | 75 | 77 |
| Price | 25% | 47 | 37 | 52 |
| Inputs & features | 15% | 70 | 70 | 70 |
| Context window | 10% | 61 | 61 | 61 |
| Overall | 100% | 67/100 | 63/100 | 68/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Mistral Large 4Mistral AI | InklingThinking Machines | Inkling SmallThinking Machines |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 150.6 (best) | 148.5 | 150.5 |
| ECI rank | #57 of 165 (best) | #67 of 165 | #58 of 165 |
| GPQA DiamondGraduate-level science questions | 88.1% | 88.3% | 88.5% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 58.6% (best) | 33.3% | 46.3% |
| OTIS Mock AIME 2024–2025Competition mathematics | 98.3% (best) | 88.9% | 90.0% |
| SimpleQA VerifiedShort factual questions | 20.0% | 40.3% (best) | 19.1% |
| Price per million tokens | |||
| Input | $0.70 | $1.00 | $0.58 (best) |
| Output | $2.10 | $4.05 | $1.44 (best) |
| Cached input | $0.07 (best) | $0.17 | $0.116 |
| Blended (3:1) | $1.05 | $1.76 | $0.795 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Official Thinking Machines API | Official Thinking Machines API |
| Limits | |||
| Context window | 1,048,576 tokens | 1,048,576 tokens | 1,048,576 tokens |
| Max output | 262,144 tokens | 1,048,576 tokens (best) | 1,048,576 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | Yes | Yes |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high | Yeslow · medium · high · xhigh · max | Yeslow · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | OpenApache-2.0 | OpenApache-2.0 |
| API model ID | mistral-large-4 | thinkingmachines/Inkling:peft:262144:sampling-nvfp4 | thinkingmachines/Inkling-Small |
| API providers | 15 | 20 (best) | 12 |
| Released | Oct 6, 2026 | Jul 15, 2026 | Jul 30, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Mistral Large 4$11.20
- Inkling$18.10
- Inkling Small$8.68
Which should you choose?
Which is better: Mistral Large 4, Inkling or Inkling Small?
It is close. Our weighted score puts them within 1 points (Inkling Small 68/100, Mistral Large 4 67/100, Inkling 63/100), so choose by what matters most for your work: Mistral Large 4 for raw capability and Inkling Small on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Mistral Large 4, Inkling or Inkling Small?
Inkling Small is cheaper at $0.58 input / $1.44 output per million tokens (official Thinking Machines API price). Mistral Large 4 costs $0.70 input / $2.10 output per million tokens (official Mistral API price); Inkling costs $1.00 input / $4.05 output per million tokens (official Thinking Machines API price). At a typical mix of three input tokens to one output token, that is $0.795 per million tokens for Inkling Small versus $1.05 for Mistral Large 4 (1.3× as much) and $1.76 for Inkling (2.2× as much).
Which scores higher on benchmarks?
Mistral Large 4 scores higher on the Capabilities Index (ECI): Mistral Large 4 150.6 (#57 of 165), Inkling Small 150.5 (#58 of 165) and Inkling 148.5 (#67 of 165). The confidence ranges of the top two overlap (147.4–153.5 vs 147.7–152.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — Inkling Small 88.5%, Inkling 88.3%, Mistral Large 4 88.1%; FrontierMath Tiers 1–3 — Mistral Large 4 58.6%, Inkling Small 46.3%, Inkling 33.3%; OTIS Mock AIME 2024–2025 — Mistral Large 4 98.3%, Inkling Small 90.0%, Inkling 88.9%; SimpleQA Verified — Inkling 40.3%, Mistral Large 4 20.0%, Inkling Small 19.1%.
Which is better for coding?
There are no published SWE-bench Verified results for Mistral Large 4, Inkling and Inkling Small yet, so there is no like-for-like coding score. On overall capability, Mistral Large 4 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Mistral Large 4, Inkling and Inkling Small share the same 1,048,576-token context window. Maximum output per response: Mistral Large 4 up to 262,144, Inkling up to 1,048,576, Inkling Small up to 1,048,576 tokens.
Which can read images, PDFs, audio or video?
Mistral Large 4 accepts text and images; Inkling accepts text, images and audio; Inkling Small accepts text, images and audio. Inkling handles the widest range of inputs.
Are any of these open source?
Inkling and Inkling Small publishes its weights (Apache-2.0) and can be self-hosted; Mistral Large 4 is proprietary.
Which is newer?
Mistral Large 4 is the newest, released Oct 6, 2026. Inkling Small came out Jul 30, 2026; Inkling came out Jul 15, 2026.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
