Fugu Ultra vs Mistral Magistral Small 2509
Fugu Ultra (2026) and Mistral Magistral Small 2509 (2025) are frontier reasoning models from Sakana AI and MistralAI. Fugu Ultra ships a 1m-token context window, while Mistral Magistral Small 2509 ships a not-yet-sourced context window. On pricing, Fugu Ultra ranges from $5 to $10/1M input tokens by tier; Mistral Magistral Small 2509 costs $0.50/1M input tokens. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.
Fugu Ultra is safer overall; choose Mistral Magistral Small 2509 when provider fit matters.
Decision scorecard
Local evidence first| Signal | Fugu Ultra | Mistral Magistral Small 2509 |
|---|---|---|
| Best for | reasoning-heavy apps, multimodal apps, and tool-calling agents | provider-routed production |
| Decision fit | Coding, RAG, and Agents | General |
| Context window | 1m | — |
| Cheapest output | $30/1M tokens | $1.50/1M tokens |
| Provider routes | 2 tracked | 2 tracked |
| Shared benchmarks | 0 shared | 0 shared |
Decision tradeoffs
- Fugu Ultra has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Fugu Ultra uniquely exposes Vision, Multimodal, and Reasoning in local model data.
- Local decision data tags Fugu Ultra for Coding, RAG, and Agents.
- Mistral Magistral Small 2509 has the lower cheapest tracked output price at $1.50/1M tokens.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
Fugu Ultra
$11,500
Cheapest tracked route/tier: Sakana AI <=272K tokens
Mistral Magistral Small 2509
$775
Cheapest tracked route/tier: AWS Bedrock
Estimated monthly gap: $10,725. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on Vercel AI Gateway; start route-level A/B tests there.
- Mistral Magistral Small 2509 is $28.50/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
- Check replacement coverage for Vision, Multimodal, and Reasoning before moving production traffic.
- Provider overlap exists on Vercel AI Gateway; start route-level A/B tests there.
- Fugu Ultra is $28.50/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
- Fugu Ultra adds Vision, Multimodal, and Reasoning in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2026-06-22 | 2025-09-01 |
| Context window | 1m | — |
| Parameters | — | 24B |
| Architecture | Composition of Experts | - |
| License | Proprietary | Apache 2.0OSI-approved |
| Openness | Proprietary | Open source |
| Commercial use | Commercial use: conditional | Commercial use: permitted |
| Knowledge cutoff | - | - |
Pricing and availability
| Pricing attribute | Fugu Ultra | Mistral Magistral Small 2509 |
|---|---|---|
| Input price |
| $0.50/1M tokens |
| Output price |
| $1.50/1M tokens |
| Providers |
Capabilities
| Capability | Fugu Ultra | Mistral Magistral Small 2509 |
|---|---|---|
| Vision | Yes | No |
| Multimodal | Yes | No |
| Reasoning | Yes | No |
| Function calling | Yes | No |
| Tool use | Yes | No |
| Structured outputs | Yes | No |
| Code execution | No | No |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
No shared benchmark scores are currently available for this pair.
Deep dive
The capability footprint differs most on vision: Fugu Ultra, multimodal input: Fugu Ultra, reasoning mode: Fugu Ultra, function calling: Fugu Ultra, tool use: Fugu Ultra, and structured outputs: Fugu Ultra. Both models share the core language-model surface, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.
For cost, Fugu Ultra lists tiered pricing: <=272K tokens is $5/1M input and $30/1M output; >272K tokens is $10/1M input and $45/1M output, while Mistral Magistral Small 2509 lists $0.50/1M input and $1.50/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Mistral Magistral Small 2509 lower by about $11.70 per million blended tokens. For tiered rows, this cheapest-track view can understate interactive or fast-lane spend, so compare the tier you will actually use. Availability is 2 providers versus 2, so concentration risk also matters.
Choose Fugu Ultra when reasoning depth are central to the workload. Choose Mistral Magistral Small 2509 when provider fit and lower input-token cost are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.
FAQ
Which is cheaper, Fugu Ultra or Mistral Magistral Small 2509?
Fugu Ultra lists tiered pricing: <=272K tokens is $5/1M input and $30/1M output; >272K tokens is $10/1M input and $45/1M output. Mistral Magistral Small 2509 lists $0.50/1M input and $1.50/1M output tokens on the cheapest tracked provider. Compare the tier you will actually use; cheap async pricing can overstate savings for interactive workflows. Provider discounts or batch pricing can still change the final bill.
Is Fugu Ultra or Mistral Magistral Small 2509 open source?
Fugu Ultra is listed under Proprietary. Mistral Magistral Small 2509 is listed under Apache 2.0. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for vision, Fugu Ultra or Mistral Magistral Small 2509?
Fugu Ultra has the clearer documented vision signal in this comparison. If vision is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.
Which is better for multimodal input, Fugu Ultra or Mistral Magistral Small 2509?
Fugu Ultra has the clearer documented multimodal input signal in this comparison. If multimodal input is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Which is better for reasoning mode, Fugu Ultra or Mistral Magistral Small 2509?
Fugu Ultra has the clearer documented reasoning mode signal in this comparison. If reasoning mode is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Where can I run Fugu Ultra and Mistral Magistral Small 2509?
Fugu Ultra is available on Sakana AI and Vercel AI Gateway. Mistral Magistral Small 2509 is available on AWS Bedrock and Vercel AI Gateway. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-06-22. Data sourced from public model cards and provider documentation.