Apertus 70B vs Jamba Large vs o4-mini-deep-research
o4-mini-deep-research comes out ahead, 37 to 32 and 29 on our weighted score, though Apertus 70B is 2.6× cheaper per token.
Swiss AI
Apertus 70B
32/100- ECI—
- Price$0.82 / $2.42
- Context66K
AI21 LabsJamba Large
29/100- ECI—
- Price$2.00 / $8.00
- Context256K
- Our pick
OpenAIo4-mini-deep-research
37/100- ECI—
- Price$1.80 / $7.20
- Context200K
o4-mini-deep-research is our pick
o4-mini-deep-research is the better all-round choice, scoring 37/100 against Apertus 70B (32) and Jamba Large (29). It leads on inputs & features. Apertus 70B wins on price. Jamba Large wins on 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 priceApertus 70BApertus 70B $1.22 · o4-mini-deep-research $3.15 · Jamba Large $3.50 per 1M tokens (3:1 blend)
- Longest contextJamba LargeJamba Large 256,000 · o4-mini-deep-research 200,000 · Apertus 70B 65,536 tokens
- Widest inputso4-mini-deep-researchApertus 70B: Text · Jamba Large: Text · o4-mini-deep-research: Text, Images
- Self-hostingApertus 70B and Jamba LargePublishes downloadable weights (Apache-2.0)
| Measure | Weight | Apertus 70B | Jamba Large | o4-mini-deep-research |
|---|---|---|---|---|
| Price | 50% | 44 | 23 | 25 |
| Inputs & features | 30% | 25 | 35 | 60 |
| Context window | 20% | 12 | 36 | 32 |
| Overall | 100% | 32/100 | 29/100 | 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 | Apertus 70BSwiss AI | Jamba LargeAI21 Labs | o4-mini-deep-researchOpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.82 (best) | $2.00 | $1.80 |
| Output | $2.42 (best) | $8.00 | $7.20 |
| Cached input | — | — | — |
| Blended (3:1) | $1.22 (best) | $3.50 | $3.15 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 3 providers | Official AI21 Labs API | Median of 1 providers |
| Limits | |||
| Context window | 65,536 tokens | 256,000 tokens (best) | 200,000 tokens |
| Max output | 8,192 tokens | 4,096 tokens | 100,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenApache-2.0 | Open | Proprietary |
| API model ID | — | jamba-large | — |
| API providers | 3 (best) | 1 | 1 |
| Released | Sep 2, 2025 | Jul 3, 2025 | Jun 26, 2025 |
| Knowledge cutoff | Sep 2025 | Aug 22, 2024 | May 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Apertus 70B$13.04
- Jamba Large$36.00
- o4-mini-deep-research$32.40
Which should you choose?
Which is better: Apertus 70B, Jamba Large or o4-mini-deep-research?
o4-mini-deep-research is the better all-round choice, scoring 37/100 against Apertus 70B (32) and Jamba Large (29). It leads on inputs & features. Apertus 70B wins on price. Jamba Large wins on 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, Apertus 70B, Jamba Large or o4-mini-deep-research?
Apertus 70B is cheaper at $0.82 input / $2.42 output per million tokens (median across 3 API providers). o4-mini-deep-research costs $1.80 input / $7.20 output per million tokens (median across 1 API provider); Jamba Large costs $2.00 input / $8.00 output per million tokens (official AI21 Labs API price). At a typical mix of three input tokens to one output token, that is $1.22 per million tokens for Apertus 70B versus $3.15 for o4-mini-deep-research (2.6× as much) and $3.50 for Jamba Large (2.9× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Apertus 70B has not been scored yet, Jamba Large has not been scored yet and o4-mini-deep-research has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Apertus 70B, Jamba Large and o4-mini-deep-research 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?
Jamba Large has the largest context window at 256,000 tokens, against 200,000 for o4-mini-deep-research and 65,536 for Apertus 70B. Maximum output per response: Apertus 70B up to 8,192, Jamba Large up to 4,096, o4-mini-deep-research up to 100,000 tokens.
Which can read images, PDFs, audio or video?
Apertus 70B accepts text; Jamba Large accepts text; o4-mini-deep-research accepts text and images. o4-mini-deep-research handles the widest range of inputs.
Are any of these open source?
Apertus 70B and Jamba Large publishes its weights (Apache-2.0) and can be self-hosted; o4-mini-deep-research is proprietary.
Which is newer?
Apertus 70B is the newest, released Sep 2, 2025. Jamba Large came out Jul 3, 2025; o4-mini-deep-research came out Jun 26, 2025. Knowledge cutoff: Apertus 70B Sep 2025, Jamba Large Aug 22, 2024, o4-mini-deep-research May 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 Nov 2, 2026.
