Model comparison
Compare Mistral Small 4 and Celeris-1 Magnus using the same provider-sourced text & reasoning rubric. No mystery score and no invented benchmark ranking.
Facts checked September 4, 2026
Set your usage. Your estimate updates as you type.
Example: 6,000 input tokens for 10 pages, plus a 500-token summary. Page lengths vary; adjust the numbers below.
One run sends your input to the model once and receives an answer. Tokens are pieces of text: input is what you send, output is the answer you receive.
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
| Model | Access | Estimated total (USD) |
|---|---|---|
| Mistral Small 4Mistral AI | Mistral AI | $0.0012 |
| Celeris-1 MagnusCeleris | Celeris | No reviewed rate |
Quick take
Mistral's lower-cost open model that combines normal instruction following, reasoning, coding, vision, and agent tools in one endpoint.
Sparse activation lowers inference work but does not make the full 119B checkpoint small. Size hardware around the actual quantization and context you plan to serve.
Celeris' agent-focused diffusion language model for fast reasoning, tool loops, structured actions, and OpenAI-compatible integration.
The public price page labels Celeris-1 rather than Magnus, and the service remains early. Confirm Magnus billing, capacity, support, data retention, and a production SLA directly.
Compare the published facts
Values use each provider's own published units and limits. A blank means the provider did not publish a directly comparable value in the sources reviewed.
| Text & reasoning | Mistral Small 4 | Celeris-1 Magnus |
|---|---|---|
| Context windowMaximum combined prompt and working context documented by the provider. | 256K tokens combined | 131,072 tokens combined |
| Maximum outputProvider-published response limit, where available. | Not separately published | Any positive limit within the combined context |
| Knowledge cutoffLatest reliable knowledge date explicitly published by the model provider. Search and connected tools can retrieve newer information but do not change the model's built-in cutoff. | Not published | Not published |
| Input priceCurrent standard list price per million input tokens unless noted. | $0.15 / 1M | $0.20 / 1M listed family rate; verify Magnus |
| Output priceCurrent standard list price per million output tokens unless noted. | $0.60 / 1M | $0.70 / 1M listed family rate; verify Magnus |
| InputsMedia types accepted by the listed model endpoint. | Text, image | Text; image content parts supported by the API |
| Tools & agentsSelected native tools and agent-building capabilities, not an exhaustive list. | Functions, agents, built-in tools, structured and predicted outputs | Tools, JSON schema, reasoning low/medium/xhigh |
How to choose
Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.
Mistral's commercial terms exclude model training by default except when a customer opts in or uses designated Labs or preview models. Self-hosting keeps inference data under the operator's controls; hosted API retention is generally 30 days unless zero data retention is enabled.
Provider and API links
Celeris says API inputs and outputs are processed to provide the service and monitor abuse and reliability. Its public notice does not give one fixed content-retention period or no-training promise; enterprise VPC options are available.
Provider and API links
Frequently asked questions
Mistral Small 4: Mistral's lower-cost open model that combines normal instruction following, reasoning, coding, vision, and agent tools in one endpoint. Celeris-1 Magnus: Celeris' agent-focused diffusion language model for fast reasoning, tool loops, structured actions, and OpenAI-compatible integration.
Consider Mistral Small 4 when your priority is Cost-sensitive production assistants. Consider Celeris-1 Magnus when your priority is Low-latency tool-using agents. Test both with your own data and provider route before committing.
No. This comparison aligns provider-published facts for the Text & reasoning category. It does not claim a universal winner or combine incompatible third-party benchmark scores.
