Inkling Small vs MiniMax-M3 vs Seed 2.1 Turbo
Too close to call on our weighted score (Seed 2.1 Turbo 84, Inkling Small 82, MiniMax-M3 77). The right pick depends on what you value most.
Price in rating: Excluded · Include price
Thinking Machines
Inkling Small
82/100- ECI150.8
- Price$0.58 / $1.44
- Context1.05M
MiniMax
MiniMax-M3
77/100- ECI147.9
- Price$0.30 / $1.20
- Context1.05M
ByteDance Seed
Seed 2.1 Turbo
84/100- ECI—
- Price$0.445 / $2.23
- Context256K
Too close to call
It is close. Our weighted score puts them within 1 points (Seed 2.1 Turbo 84/100, Inkling Small 82/100, MiniMax-M3 77/100), so choose by what matters most for your work: Seed 2.1 Turbo for raw capability and MiniMax-M3 on price. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Seed 2.1 Turbo has no Capabilities Index score yet.
- CapabilitySeed 2.1 TurboShared benchmarks: Seed 2.1 Turbo 92.8% · Inkling Small 89.3% · MiniMax-M3 81.0%
- Lowest priceMiniMax-M3MiniMax-M3 $0.525 · Inkling Small $0.795 · Seed 2.1 Turbo $0.891 per 1M tokens (3:1 blend)
- Longest contextInkling Small and MiniMax-M3Inkling Small 1,048,576 · MiniMax-M3 1,048,576 · Seed 2.1 Turbo 256,000 tokens
- Widest inputsSame inputsInkling Small: Text, Images, Audio · MiniMax-M3: Text, Images, Video · Seed 2.1 Turbo: Text, Images, Video
- Self-hostingInkling Small and MiniMax-M3Publishes downloadable weights (Apache-2.0)
| Measure | Weight | Inkling Small | MiniMax-M3 | Seed 2.1 Turbo |
|---|---|---|---|---|
| CapabilityShared benchmarks | 67% | 89 | 81 | 93 |
| Inputs & features | 20% | 70 | 70 | 80 |
| Context window | 13% | 65 | 65 | 43 |
| Overall | 100% | 82/100 | 77/100 | 84/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 150.8 (best) | 147.9 | — |
| ECI rank | #65 of 158 (best) | #77 of 158 | — |
| GPQA DiamondGraduate-level science questions | 88.5% | 90.9% (best) | 89.6% |
| FrontierMath Tiers 1–3Research-level mathematics | 46.3% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 90.0% | 71.1% | 96.1% (best) |
| SimpleQA VerifiedShort factual questions | 19.1% | — | 29.7% (best) |
| Price per million tokens | |||
| Input | $0.58 | $0.30 (best) | $0.445 |
| Output | $1.44 | $1.20 (best) | $2.23 |
| Cached input | $0.116 | $0.06 (best) | $0.089 |
| Blended (3:1) | $0.795 | $0.525 (best) | $0.891 |
| Long-context rate | Same rate | Over 512K: $0.60 / $2.40 | Same rate |
| Price source | Official Thinking Machines API | Official MiniMax (minimax.io) API | Official Volcengine Ark API |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 1,048,576 tokens (best) | 256,000 tokens |
| Max output | 1,048,576 tokens (best) | 512,000 tokens | 256,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | Yes | No | No |
| Video | No | Yes | Yes |
| Reasoning | Yeslow · medium · high · xhigh · max | Yes | Yesminimal · low · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | OpenApache-2.0 | Open | Proprietary |
| API model ID | thinkingmachines/Inkling-Small:peft:262144 | MiniMax-M3 | doubao-seed-2-1-turbo-260628 |
| API providers | 12 | 52 (best) | 9 |
| Released | Jul 30, 2026 | Jun 1, 2026 | Jun 23, 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.
Inkling Small$8.68
MiniMax-M3$5.40
Seed 2.1 Turbo$8.91
Which should you choose?
Which is better: Inkling Small, MiniMax-M3 or Seed 2.1 Turbo?
It is close. Our weighted score puts them within 1 points (Seed 2.1 Turbo 84/100, Inkling Small 82/100, MiniMax-M3 77/100), so choose by what matters most for your work: Seed 2.1 Turbo for raw capability and MiniMax-M3 on price. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Seed 2.1 Turbo has no Capabilities Index score yet.
Which is cheaper, Inkling Small, MiniMax-M3 or Seed 2.1 Turbo?
MiniMax-M3 is cheaper at $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). Inkling Small costs $0.58 input / $1.44 output per million tokens (official Thinking Machines API price); Seed 2.1 Turbo costs $0.445 input / $2.23 output per million tokens (official Volcengine Ark API price). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for MiniMax-M3 versus $0.795 for Inkling Small (1.5× as much) and $0.891 for Seed 2.1 Turbo (1.7× as much).
Which scores higher on benchmarks?
Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): Seed 2.1 Turbo 92.8%, Inkling Small 89.3% and MiniMax-M3 81.0%. On individual benchmarks: GPQA Diamond — MiniMax-M3 90.9%, Seed 2.1 Turbo 89.6%, Inkling Small 88.5%; OTIS Mock AIME 2024–2025 — Seed 2.1 Turbo 96.1%, Inkling Small 90.0%, MiniMax-M3 71.1%.
Which is better for coding?
There are no published SWE-bench Verified results for Inkling Small, MiniMax-M3 and Seed 2.1 Turbo yet, so there is no like-for-like coding score. On overall capability, Seed 2.1 Turbo 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?
Inkling Small and MiniMax-M3 have the largest context windows (1,048,576 and 1,048,576 tokens), against 256,000 for Seed 2.1 Turbo. Maximum output per response: Inkling Small up to 1,048,576, MiniMax-M3 up to 512,000, Seed 2.1 Turbo up to 256,000 tokens.
Which can read images, PDFs, audio or video?
Inkling Small accepts text, images and audio; MiniMax-M3 accepts text, images and video; Seed 2.1 Turbo accepts text, images and video. They handle the same number of input types.
Are any of these open source?
Inkling Small and MiniMax-M3 publishes its weights (Apache-2.0) and can be self-hosted; Seed 2.1 Turbo is proprietary.
Which is newer?
Inkling Small is the newest, released Jul 30, 2026. Seed 2.1 Turbo came out Jun 23, 2026; MiniMax-M3 came out Jun 1, 2026.
How do you decide the winner?
This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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 18, 2026.