GPT-5.4 mini vs Laguna M.1 vs North Small Translate
Laguna M.1 comes out ahead, 68 to 50 and 49 on our weighted score.
OpenAIGPT-5.4 mini
49/100- ECI148.8
- Price$0.75 / $4.50
- Context400K
- Our pick
PoolsideLaguna M.1
68/100- ECI—
- PriceFree / Free
- Context262K
CohereNorth Small Translate
50/100- ECI—
- PriceFree / Free
- Context16K
Laguna M.1 is our pick
Laguna M.1 is the better all-round choice, scoring 68/100 against North Small Translate (50) and GPT-5.4 mini (49). GPT-5.4 mini wins on inputs & features and context window. 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 priceLaguna M.1 and North Small TranslateLaguna M.1 Free · North Small Translate Free · GPT-5.4 mini $1.69 per 1M tokens (3:1 blend)
- Longest contextGPT-5.4 miniGPT-5.4 mini 400,000 · Laguna M.1 262,144 · North Small Translate 16,000 tokens
- Widest inputsGPT-5.4 miniGPT-5.4 mini: Text, Images · Laguna M.1: Text · North Small Translate: Text
- Self-hostingLaguna M.1 and North Small TranslatePublishes downloadable weights (CC-BY-NC-4.0)
| Measure | Weight | GPT-5.4 mini | Laguna M.1 | North Small Translate |
|---|---|---|---|---|
| Price | 50% | 39 | 100 | 100 |
| Inputs & features | 30% | 70 | 35 | 0 |
| Context window | 20% | 44 | 37 | 0 |
| Overall | 100% | 49/100 | 68/100 | 50/100 |
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 | GPT-5.4 miniOpenAI | Laguna M.1Poolside | North Small TranslateCohere |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 148.8 | — | — |
| ECI rank | #56 of 148 | — | — |
| GPQA DiamondGraduate-level science questions | 86.9% | — | — |
| FrontierMath Tiers 1–3Research-level mathematics | 51.2% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 88.9% | — | — |
| SimpleQA VerifiedShort factual questions | 29.4% | — | — |
| Price per million tokens | |||
| Input | $0.75 | Free (best) | Free (best) |
| Output | $4.50 | Free (best) | Free (best) |
| Cached input | $0.075 | — | — |
| Blended (3:1) | $1.69 | Free (best) | Free (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Official Poolside API | Official Cohere API |
| Limits | |||
| Context window | 400,000 tokens (best) | 262,144 tokens | 16,000 tokens |
| Max output | 128,000 tokens (best) | 32,768 tokens | 16,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high · xhigh | Yes | No |
| Tool calling | Yes | Yes | No |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Open | OpenCC-BY-NC-4.0 |
| API model ID | gpt-5.4-mini | poolside/laguna-m.1 | north-small-translate-09-2026 |
| API providers | 29 (best) | 2 | 1 |
| Released | Mar 17, 2026 | Apr 28, 2026 | Sep 9, 2026 |
| Knowledge cutoff | Aug 31, 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GPT-5.4 mini$16.50
- Laguna M.1Free
- North Small TranslateFree
Which should you choose?
Which is better: GPT-5.4 mini, Laguna M.1 or North Small Translate?
Laguna M.1 is the better all-round choice, scoring 68/100 against North Small Translate (50) and GPT-5.4 mini (49). GPT-5.4 mini wins on inputs & features and context window. 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, GPT-5.4 mini, Laguna M.1 or North Small Translate?
Laguna M.1 is cheaper at Free input / Free output per million tokens (official Poolside API price). North Small Translate costs Free input / Free output per million tokens (official Cohere API price); GPT-5.4 mini costs $0.75 input / $4.50 output per million tokens (official OpenAI API price). Laguna M.1 is listed as free.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GPT-5.4 mini has an ECI of 148.8, Laguna M.1 has not been scored yet and North Small Translate has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-5.4 mini, Laguna M.1 and North Small Translate yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that North Small Translate does not support tool calling, which most coding agents need.
Which has the bigger context window?
GPT-5.4 mini has the largest context window at 400,000 tokens, against 262,144 for Laguna M.1 and 16,000 for North Small Translate. Maximum output per response: GPT-5.4 mini up to 128,000, Laguna M.1 up to 32,768, North Small Translate up to 16,000 tokens.
Which can read images, PDFs, audio or video?
GPT-5.4 mini accepts text and images; Laguna M.1 accepts text; North Small Translate accepts text. GPT-5.4 mini handles the widest range of inputs.
Are any of these open source?
Laguna M.1 and North Small Translate publishes its weights (CC-BY-NC-4.0) and can be self-hosted; GPT-5.4 mini is proprietary.
Which is newer?
North Small Translate is the newest, released Sep 9, 2026. Laguna M.1 came out Apr 28, 2026; GPT-5.4 mini came out Mar 17, 2026. Knowledge cutoff: GPT-5.4 mini Aug 31, 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.
