AutoGLM Phone 9B Multilingual vs Schematron V2 Turbo vs Trinity Mini
Trinity Mini comes out ahead, 65 to 60 and 55 on our weighted score, though Schematron V2 Turbo is 16% cheaper per token.
Z.ai (Zhipu)AutoGLM Phone 9B Multilingual
60/100- ECI—
- Price$0.035 / $0.138
- Context66K
Inference.net
Schematron V2 Turbo
55/100- ECI—
- Price$0.03 / $0.15
- Context128K
- Our pick
Arcee AITrinity Mini
65/100- ECI—
- Price$0.045 / $0.15
- Context131K
Trinity Mini is our pick
Trinity Mini is the better all-round choice, scoring 65/100 against AutoGLM Phone 9B Multilingual (60) and Schematron V2 Turbo (55). It leads on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceSchematron V2 TurboSchematron V2 Turbo $0.06 · AutoGLM Phone 9B Multilingual $0.061 · Trinity Mini $0.071 per 1M tokens (3:1 blend)
- Longest contextTrinity MiniTrinity Mini 131,072 · Schematron V2 Turbo 128,000 · AutoGLM Phone 9B Multilingual 65,536 tokens
- Widest inputsAutoGLM Phone 9B MultilingualAutoGLM Phone 9B Multilingual: Text, Images · Schematron V2 Turbo: Text · Trinity Mini: Text
- Self-hostingAutoGLM Phone 9B Multilingual and Trinity MiniPublishes downloadable weights (MIT and OpenMDW-1.1)
| Measure | Weight | AutoGLM Phone 9B Multilingual | Schematron V2 Turbo | Trinity Mini |
|---|---|---|---|---|
| Price | 50% | 100 | 100 | 100 |
| Inputs & features | 30% | 25 | 0 | 35 |
| Context window | 20% | 12 | 24 | 25 |
| Overall | 100% | 60/100 | 55/100 | 65/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | AutoGLM Phone 9B MultilingualZ.ai (Zhipu) | Schematron V2 TurboInference.net | Trinity MiniArcee AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.035 | $0.03 (best) | $0.045 |
| Output | $0.138 (best) | $0.15 | $0.15 |
| Cached input | — | — | — |
| Blended (3:1) | $0.061 | $0.06 (best) | $0.071 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 2 providers | Median of 5 providers | Median of 1 providers |
| Limits | |||
| Context window | 65,536 tokens | 128,000 tokens | 131,072 tokens (best) |
| Max output | 65,536 tokens | 8,192 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | Yes |
| Tool calling | No | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenMIT | Proprietary | OpenOpenMDW-1.1 |
| API model ID | — | — | — |
| API providers | 2 | 5 (best) | 1 |
| Released | Dec 10, 2025 | Apr 16, 2026 | Dec 1, 2025 |
| 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.
- AutoGLM Phone 9B Multilingual$0.626
- Schematron V2 Turbo$0.60
- Trinity Mini$0.75
Which should you choose?
Which is better: AutoGLM Phone 9B Multilingual, Schematron V2 Turbo or Trinity Mini?
Trinity Mini is the better all-round choice, scoring 65/100 against AutoGLM Phone 9B Multilingual (60) and Schematron V2 Turbo (55). It leads on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, AutoGLM Phone 9B Multilingual, Schematron V2 Turbo or Trinity Mini?
Schematron V2 Turbo is cheaper at $0.03 input / $0.15 output per million tokens (median across 5 API providers). AutoGLM Phone 9B Multilingual costs $0.035 input / $0.138 output per million tokens (median across 2 API providers); Trinity Mini costs $0.045 input / $0.15 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.06 per million tokens for Schematron V2 Turbo versus $0.061 for AutoGLM Phone 9B Multilingual (1× as much) and $0.071 for Trinity Mini (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. AutoGLM Phone 9B Multilingual has not been scored yet, Schematron V2 Turbo has not been scored yet and Trinity Mini has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for AutoGLM Phone 9B Multilingual, Schematron V2 Turbo and Trinity Mini yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that AutoGLM Phone 9B Multilingual and Schematron V2 Turbo does not support tool calling, which most coding agents need.
Which has the bigger context window?
Trinity Mini has the largest context window at 131,072 tokens, against 128,000 for Schematron V2 Turbo and 65,536 for AutoGLM Phone 9B Multilingual. Maximum output per response: AutoGLM Phone 9B Multilingual up to 65,536, Schematron V2 Turbo up to 8,192, Trinity Mini up to 131,072 tokens.
Which can read images, PDFs, audio or video?
AutoGLM Phone 9B Multilingual accepts text and images; Schematron V2 Turbo accepts text; Trinity Mini accepts text. AutoGLM Phone 9B Multilingual handles the widest range of inputs.
Are any of these open source?
AutoGLM Phone 9B Multilingual and Trinity Mini publishes its weights (MIT and OpenMDW-1.1) and can be self-hosted; Schematron V2 Turbo is proprietary.
Which is newer?
Schematron V2 Turbo is the newest, released Apr 16, 2026. AutoGLM Phone 9B Multilingual came out Dec 10, 2025; Trinity Mini came out Dec 1, 2025.
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.
Related comparisons
- AutoGLM Phone 9B Multilingual vs Qwen3 VL Flash (Alibaba Cloud)Alibaba (Qwen)
- AutoGLM Phone 9B Multilingual vs LFM2 24B A2BLiquid AI
- Schematron V2 Turbo vs Gemma 4 E2B ITGoogle
- Schematron V2 Turbo vs LFM2 24B A2BLiquid AI
- Schematron V2 Turbo vs Hy-MT2-1.8BTencent
- Schematron V2 Turbo vs Qwen3.5 4BAlibaba (Qwen)
