Devstral Medium vs GLM-4.5V vs Ling-1T
GLM-4.5V comes out ahead, 49 to 39 and 37 on our weighted score, though Devstral Medium is 11% cheaper per token.
Mistral AIDevstral Medium
39/100- ECI—
- Price$0.40 / $2.00
- Context128K
- Our pick
Z.ai (Zhipu)GLM-4.5V
49/100- ECI—
- Price$0.60 / $1.80
- Context64K
inclusionAILing-1T
37/100- ECI—
- Price$0.57 / $2.29
- Context128K
GLM-4.5V is our pick
GLM-4.5V is the better all-round choice, scoring 49/100 against Devstral Medium (39) and Ling-1T (37). It leads on inputs & features. Devstral Medium wins on price. 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 priceDevstral MediumDevstral Medium $0.80 · GLM-4.5V $0.90 · Ling-1T $1.00 per 1M tokens (3:1 blend)
- Longest contextDevstral Medium and Ling-1TDevstral Medium 128,000 · Ling-1T 128,000 · GLM-4.5V 64,000 tokens
- Widest inputsGLM-4.5VDevstral Medium: Text · GLM-4.5V: Text, Images, Video · Ling-1T: Text
- Self-hostingGLM-4.5V and Ling-1TPublishes downloadable weights
| Measure | Weight | Devstral Medium | GLM-4.5V | Ling-1T |
|---|---|---|---|---|
| Price | 50% | 54 | 52 | 50 |
| Inputs & features | 30% | 25 | 70 | 25 |
| Context window | 20% | 24 | 12 | 24 |
| Overall | 100% | 39/100 | 49/100 | 37/100 |
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 | Devstral MediumMistral AI | GLM-4.5VZ.ai (Zhipu) | Ling-1TinclusionAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.40 (best) | $0.60 | $0.57 |
| Output | $2.00 | $1.80 (best) | $2.29 |
| Cached input | — | — | — |
| Blended (3:1) | $0.80 (best) | $0.90 | $1.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Official Z.AI API | Official Bailing API |
| Limits | |||
| Context window | 128,000 tokens (best) | 64,000 tokens | 128,000 tokens (best) |
| Max output | 128,000 tokens (best) | 16,384 tokens | 32,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | No | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | devstral-medium-2507 | glm-4.5v | Ling-1T |
| API providers | 2 | 11 (best) | 1 |
| Released | Jul 10, 2025 | Aug 11, 2025 | Oct 2025 |
| Knowledge cutoff | May 2025 | Apr 2025 | Jun 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Devstral Medium$8.00
- GLM-4.5V$9.60
- Ling-1T$10.28
Which should you choose?
Which is better: Devstral Medium, GLM-4.5V or Ling-1T?
GLM-4.5V is the better all-round choice, scoring 49/100 against Devstral Medium (39) and Ling-1T (37). It leads on inputs & features. Devstral Medium wins on price. 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, Devstral Medium, GLM-4.5V or Ling-1T?
Devstral Medium is cheaper at $0.40 input / $2.00 output per million tokens (official Mistral API price). GLM-4.5V costs $0.60 input / $1.80 output per million tokens (official Z.AI API price); Ling-1T costs $0.57 input / $2.29 output per million tokens (official Bailing API price). At a typical mix of three input tokens to one output token, that is $0.80 per million tokens for Devstral Medium versus $0.90 for GLM-4.5V (1.1× as much) and $1.00 for Ling-1T (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Devstral Medium has not been scored yet, GLM-4.5V has not been scored yet and Ling-1T has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Devstral Medium, GLM-4.5V and Ling-1T 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?
Devstral Medium and Ling-1T have the largest context windows (128,000 and 128,000 tokens), against 64,000 for GLM-4.5V. Maximum output per response: Devstral Medium up to 128,000, GLM-4.5V up to 16,384, Ling-1T up to 32,000 tokens.
Which can read images, PDFs, audio or video?
Devstral Medium accepts text; GLM-4.5V accepts text, images and video; Ling-1T accepts text. GLM-4.5V handles the widest range of inputs.
Are any of these open source?
GLM-4.5V and Ling-1T publishes its weights and can be self-hosted; Devstral Medium is proprietary.
Which is newer?
Ling-1T is the newest, released Oct 2025. GLM-4.5V came out Aug 11, 2025; Devstral Medium came out Jul 10, 2025. Knowledge cutoff: Devstral Medium May 2025, GLM-4.5V Apr 2025, Ling-1T Jun 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.
