Llama 3.1 Nemotron Ultra 253B vs Codestral vs GLM-4.5-Flash
Too close to call on our weighted score (GLM-4.5-Flash 65, Llama 3.1 Nemotron Ultra 253B 65, Codestral 48). The right pick depends on what you value most.
NVIDIALlama 3.1 Nemotron Ultra 253B
65/100- ECI—
- PriceFree / Free
- Context128K
Mistral AICodestral
48/100- ECI—
- Price$0.30 / $0.90
- Context256K
Z.ai (Zhipu)GLM-4.5-Flash
65/100- ECI—
- PriceFree / Free
- Context131K
Too close to call
It is close. Our weighted score puts them within a point (GLM-4.5-Flash 65/100, Llama 3.1 Nemotron Ultra 253B 65/100, Codestral 48/100), so choose by what matters most for your work: Llama 3.1 Nemotron Ultra 253B on price and Codestral 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 priceLlama 3.1 Nemotron Ultra 253B and GLM-4.5-FlashLlama 3.1 Nemotron Ultra 253B Free · GLM-4.5-Flash Free · Codestral $0.45 per 1M tokens (3:1 blend)
- Longest contextCodestralCodestral 256,000 · GLM-4.5-Flash 131,072 · Llama 3.1 Nemotron Ultra 253B 128,000 tokens
- Widest inputsSame inputsLlama 3.1 Nemotron Ultra 253B: Text · Codestral: Text · GLM-4.5-Flash: Text
- Self-hostingLlama 3.1 Nemotron Ultra 253B and CodestralPublishes downloadable weights
| Measure | Weight | Llama 3.1 Nemotron Ultra 253B | Codestral | GLM-4.5-Flash |
|---|---|---|---|---|
| Price | 50% | 100 | 66 | 100 |
| Inputs & features | 30% | 35 | 25 | 35 |
| Context window | 20% | 24 | 36 | 24 |
| Overall | 100% | 65/100 | 48/100 | 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 | Llama 3.1 Nemotron Ultra 253BNVIDIA | CodestralMistral AI | GLM-4.5-FlashZ.ai (Zhipu) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | Free (best) | $0.30 | Free (best) |
| Output | Free (best) | $0.90 | Free (best) |
| Cached input | — | $0.03 | — |
| Blended (3:1) | Free (best) | $0.45 | Free (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Nvidia API | Official Mistral API | Official Z.AI API |
| Limits | |||
| Context window | 128,000 tokens | 256,000 tokens (best) | 131,072 tokens |
| Max output | 8,192 tokens | 4,096 tokens | 98,304 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | nvidia/llama-3.1-nemotron-ultra-253b-v1 | codestral-latest | glm-4.5-flash |
| API providers | 1 | 3 | 4 (best) |
| Released | Apr 7, 2025 | May 29, 2024 | Jul 28, 2025 |
| Knowledge cutoff | — | Oct 2024 | Apr 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Llama 3.1 Nemotron Ultra 253BFree
- Codestral$4.80
- GLM-4.5-FlashFree
Which should you choose?
Which is better: Llama 3.1 Nemotron Ultra 253B, Codestral or GLM-4.5-Flash?
It is close. Our weighted score puts them within a point (GLM-4.5-Flash 65/100, Llama 3.1 Nemotron Ultra 253B 65/100, Codestral 48/100), so choose by what matters most for your work: Llama 3.1 Nemotron Ultra 253B on price and Codestral 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, Llama 3.1 Nemotron Ultra 253B, Codestral or GLM-4.5-Flash?
Llama 3.1 Nemotron Ultra 253B is cheaper at Free input / Free output per million tokens (official Nvidia API price). GLM-4.5-Flash costs Free input / Free output per million tokens (official Z.AI API price); Codestral costs $0.30 input / $0.90 output per million tokens (official Mistral API price). Llama 3.1 Nemotron Ultra 253B is listed as free.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Llama 3.1 Nemotron Ultra 253B has not been scored yet, Codestral has not been scored yet and GLM-4.5-Flash has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Llama 3.1 Nemotron Ultra 253B, Codestral and GLM-4.5-Flash 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?
Codestral has the largest context window at 256,000 tokens, against 131,072 for GLM-4.5-Flash and 128,000 for Llama 3.1 Nemotron Ultra 253B. Maximum output per response: Llama 3.1 Nemotron Ultra 253B up to 8,192, Codestral up to 4,096, GLM-4.5-Flash up to 98,304 tokens.
Which can read images, PDFs, audio or video?
Llama 3.1 Nemotron Ultra 253B accepts text; Codestral accepts text; GLM-4.5-Flash accepts text. They handle the same number of input types.
Are any of these open source?
Llama 3.1 Nemotron Ultra 253B and Codestral publishes its weights and can be self-hosted; GLM-4.5-Flash is proprietary.
Which is newer?
GLM-4.5-Flash is the newest, released Jul 28, 2025. Llama 3.1 Nemotron Ultra 253B came out Apr 7, 2025; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024, GLM-4.5-Flash Apr 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 Oct 4, 2026.
