GLM-4.6V vs GPT-5.1 Codex mini vs MiniMax-M2.1
Too close to call on our weighted score (GLM-4.6V 59, GPT-5.1 Codex mini 59, MiniMax-M2.1 48). The right pick depends on what you value most.
Z.ai (Zhipu)GLM-4.6V
59/100- ECI—
- Price$0.30 / $0.90
- Context128K
OpenAIGPT-5.1 Codex mini
59/100- ECI—
- Price$0.25 / $2.00
- Context400K
MiniMaxMiniMax-M2.1
48/100- ECI—
- Price$0.30 / $1.20
- Context205K
Too close to call
It is close. Our weighted score puts them within a point (GLM-4.6V 59/100, GPT-5.1 Codex mini 59/100, MiniMax-M2.1 48/100), so choose by what matters most for your work: GLM-4.6V on price and GPT-5.1 Codex mini for long inputs. 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 priceGLM-4.6VGLM-4.6V $0.45 · MiniMax-M2.1 $0.525 · GPT-5.1 Codex mini $0.688 per 1M tokens (3:1 blend)
- Longest contextGPT-5.1 Codex miniGPT-5.1 Codex mini 400,000 · MiniMax-M2.1 204,800 · GLM-4.6V 128,000 tokens
- Widest inputsGLM-4.6VGLM-4.6V: Text, Images, Video · GPT-5.1 Codex mini: Text, Images · MiniMax-M2.1: Text
- Self-hostingGLM-4.6V and MiniMax-M2.1Publishes downloadable weights
| Measure | Weight | GLM-4.6V | GPT-5.1 Codex mini | MiniMax-M2.1 |
|---|---|---|---|---|
| Price | 50% | 66 | 58 | 63 |
| Inputs & features | 30% | 70 | 70 | 35 |
| Context window | 20% | 24 | 44 | 32 |
| Overall | 100% | 59/100 | 59/100 | 48/100 |
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 | GLM-4.6VZ.ai (Zhipu) | GPT-5.1 Codex miniOpenAI | MiniMax-M2.1MiniMax |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.25 (best) | $0.30 |
| Output | $0.90 (best) | $2.00 | $1.20 |
| Cached input | — | — | $0.03 |
| Blended (3:1) | $0.45 (best) | $0.688 | $0.525 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Z.AI API | Median of 10 providers | Official MiniMax (minimax.io) API |
| Limits | |||
| Context window | 128,000 tokens | 400,000 tokens (best) | 204,800 tokens |
| Max output | 32,768 tokens | 128,000 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | glm-4.6v | — | MiniMax-M2.1 |
| API providers | 10 | 10 | 13 (best) |
| Released | Dec 8, 2025 | Nov 13, 2025 | Dec 23, 2025 |
| Knowledge cutoff | Apr 2025 | Sep 30, 2024 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GLM-4.6V$4.80
- GPT-5.1 Codex mini$6.50
- MiniMax-M2.1$5.40
Which should you choose?
Which is better: GLM-4.6V, GPT-5.1 Codex mini or MiniMax-M2.1?
It is close. Our weighted score puts them within a point (GLM-4.6V 59/100, GPT-5.1 Codex mini 59/100, MiniMax-M2.1 48/100), so choose by what matters most for your work: GLM-4.6V on price and GPT-5.1 Codex mini for long inputs. 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, GLM-4.6V, GPT-5.1 Codex mini or MiniMax-M2.1?
GLM-4.6V is cheaper at $0.30 input / $0.90 output per million tokens (official Z.AI API price). MiniMax-M2.1 costs $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price); GPT-5.1 Codex mini costs $0.25 input / $2.00 output per million tokens (median across 10 API providers). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for GLM-4.6V versus $0.525 for MiniMax-M2.1 (1.2× as much) and $0.688 for GPT-5.1 Codex mini (1.5× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GLM-4.6V has not been scored yet, GPT-5.1 Codex mini has not been scored yet and MiniMax-M2.1 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for GLM-4.6V, GPT-5.1 Codex mini and MiniMax-M2.1 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
GPT-5.1 Codex mini has the largest context window at 400,000 tokens, against 204,800 for MiniMax-M2.1 and 128,000 for GLM-4.6V. Maximum output per response: GLM-4.6V up to 32,768, GPT-5.1 Codex mini up to 128,000, MiniMax-M2.1 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
GLM-4.6V accepts text, images and video; GPT-5.1 Codex mini accepts text and images; MiniMax-M2.1 accepts text. GLM-4.6V handles the widest range of inputs.
Are any of these open source?
GLM-4.6V and MiniMax-M2.1 publishes its weights and can be self-hosted; GPT-5.1 Codex mini is proprietary.
Which is newer?
MiniMax-M2.1 is the newest, released Dec 23, 2025. GLM-4.6V came out Dec 8, 2025; GPT-5.1 Codex mini came out Nov 13, 2025. Knowledge cutoff: GLM-4.6V Apr 2025, GPT-5.1 Codex mini Sep 30, 2024.
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 Oct 4, 2026.
