All models
Text & reasoningPreview
CelerisCeleris-1 Magnus
Celeris' agent-focused diffusion language model for fast reasoning, tool loops, structured actions, and OpenAI-compatible integration.
Plain-English overview
What Celeris-1 Magnus actually is
Celeris-1 Magnus is the more capable, task-oriented sibling of the original Celeris-1. It is intended for agents that need to reason, call tools, execute several steps, and return structured results, while keeping the same familiar API shape.
Its OpenAI-compatible endpoint makes initial testing straightforward. Magnus reasoning is configurable, and image content parts and JSON schemas are supported, but cost and latency still depend on output limits, tool loops, reasoning effort, and region.
Good fit for
- Low-latency tool-using agents
- Structured extraction and action workflows
- Teams migrating an OpenAI-compatible client
Category comparison
The facts that matter for text models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Context window
- 131,072 tokens combinedMaximum combined prompt and working context documented by the provider.
- Maximum output
- Any positive limit within the combined contextProvider-published response limit, where available.
- Knowledge cutoff
- Not publishedLatest 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.
- Input price
- $0.20 / 1M listed family rate; verify MagnusCurrent standard list price per million input tokens unless noted.
- Output price
- $0.70 / 1M listed family rate; verify MagnusCurrent standard list price per million output tokens unless noted.
- Inputs
- Text; image content parts supported by the APIMedia types accepted by the listed model endpoint.
- Tools & agents
- Tools, JSON schema, reasoning low/medium/xhighSelected native tools and agent-building capabilities, not an exhaustive list.
Pricing & comparisons
Estimate your cost
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.
Advanced options
Celeris-1 Magnus
Celeris
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
How this estimate works
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.
API and provider access
Where to get Celeris-1 Magnus
Availability
Regions and access stage
Live for Celeris API customers through an OpenAI-compatible endpoint.
Celeris says it runs in AWS and GCP and offers enterprise VPC deployment; exact public regions and account availability should be confirmed directly.
Check live availabilityData and training
The route matters.
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.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Celeris-1 Magnus FAQ
What is Celeris-1 Magnus?
Celeris' agent-focused diffusion language model for fast reasoning, tool loops, structured actions, and OpenAI-compatible integration. Celeris-1 Magnus is the more capable, task-oriented sibling of the original Celeris-1. It is intended for agents that need to reason, call tools, execute several steps, and return structured results, while keeping the same familiar API shape.
When was Celeris-1 Magnus released?
Celeris-1 Magnus was released on August 31, 2026 according to the cited provider materials.
Where can I access Celeris-1 Magnus?
Live for Celeris API customers through an OpenAI-compatible endpoint. The access routes listed in this guide are Celeris and Celeris API.
How much does Celeris-1 Magnus cost?
$0.20 input · $0.70 output / 1M tokens listed for Celeris-1. Celeris's public pricing page lists the family rate for Celeris-1 but does not label a separate Magnus price. Confirm Magnus billing in the console before production.
Where is Celeris-1 Magnus available?
Live for Celeris API customers through an OpenAI-compatible endpoint. Celeris says it runs in AWS and GCP and offers enterprise VPC deployment; exact public regions and account availability should be confirmed directly.
Is my Celeris-1 Magnus API data used for training?
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. The policy belongs to the provider route and account terms, so verify it again before production use.
Price comparison
USD per million tokens for the shown API routes at standard context length. Cache and long-context rates may differ. Models without matching reviewed prices are omitted; lower cost does not mean better quality.
- Mistral Small 4$0.15
Mistral AI
- Gemini 3.8 Flash$0.75
Google
- GPT-5.6 Sol$4.00
OpenAI
- GPT-6 Astra$10.00
OpenAI
- Claude Fable 5.1$10.00
Anthropic
- Mistral Small 4$0.60
Mistral AI
- Gemini 3.8 Flash$3.75
Google
- GPT-5.6 Sol$20.00
OpenAI
- GPT-6 Astra$50.00
OpenAI
- Claude Fable 5.1$50.00
Anthropic
Related comparisons
Head-to-head comparisons
Celeris-1 Magnus vs GPT-6 Astra
OpenAI's most capable model for difficult end-to-end work, combining frontier reasoning with a million-token context window and a broad set of agent tools.
Open full comparisonCeleris-1 Magnus vs GPT-5.6 Sol
OpenAI's flagship general model for difficult coding, analysis, and professional work, with a very large context window and a broad native tool set.
Open full comparisonCeleris-1 Magnus vs Claude Fable 5.1
Anthropic's frontier model for ambitious, long-running agentic and coding work, with strong vision and enterprise marketplace availability.
Open full comparisonCeleris-1 Magnus vs Gemini 3.8 Flash
Google's stable, high-efficiency multimodal model for agents, software work, and large mixed-media inputs at an introductory Flash-tier price.
Open full comparisonCeleris-1 Magnus vs Grok 4.6
SpaceXAI's frontier text-and-image model for coding, agentic tasks, and knowledge work, with direct web, X, and code tools.
Open full comparisonCeleris-1 Magnus vs Grok 4.20 Multi-Agent Beta
A specialist Grok model that sends several AI agents to investigate a difficult question in parallel, then combines their work into one researched answer.
Open full comparisonCeleris-1 Magnus vs Inkling
Thinking Machines Lab's large open-weights model for customizable reasoning, coding, tools, vision, and audio workflows.
Open full comparisonCeleris-1 Magnus vs Mistral Medium 3.5
Mistral's open-weight frontier model for demanding multimodal, coding, reasoning, and agent workflows, with a 256K context window.
Open full comparisonCeleris-1 Magnus vs Mistral Small 4
Mistral's lower-cost open model that combines normal instruction following, reasoning, coding, vision, and agent tools in one endpoint.
Open full comparisonCeleris-1 Magnus vs Qwen3.8 Max
Alibaba's frontier Qwen model for long-context reasoning, coding, tools, and understanding text, images, and video.
Open full comparisonCeleris-1 Magnus vs MiniMax M3
MiniMax's million-token multimodal model for coding, agents, computer use, and long projects at a low direct API price.
Open full comparisonCeleris-1 Magnus vs GLM-5.3
Z.ai's open-weight long-context reasoning model for coding, tools, and agentic work across self-hosted and managed routes.
Open full comparisonCeleris-1 Magnus vs Kimi K3
Moonshot AI's frontier multimodal model for million-token coding, reasoning, knowledge work, and tool-driven agents.
Open full comparisonCeleris-1 Magnus vs Falcon-H1R-7B
TII's compact open reasoning model for text tasks, long contexts, and self-hosted function-calling workflows.
Open full comparisonCeleris-1 Magnus vs Falcon-H1-34B-Instruct
TII's 34B open instruction model for multilingual text, coding, and controlled self-hosted applications.
Open full comparisonCeleris-1 Magnus vs Muse Spark 1.3
Meta's latest multimodal reasoning model for long-running agents, coding, tools, and complex user collaboration.
Open full comparisonCeleris-1 Magnus vs NVIDIA Nemotron 3 Ultra
NVIDIA's largest Nemotron 3 reasoning model for complex agents, coding, planning, tools, RAG, and million-token analysis.
Open full comparisonCeleris-1 Magnus vs NVIDIA Nemotron 3.5 Lightning
NVIDIA's compact 30B mixture-of-experts model for efficient specialist agents and high-volume text workflows.
Open full comparisonCeleris-1 Magnus vs Qwen3.8-Flash
Alibaba's efficient million-context multimodal model for fast agents, coding, document work, vision, video understanding, and tool use.
Open full comparisonCeleris-1 Magnus vs DeepSeek-V4-Pro
DeepSeek's flagship million-context text model for difficult reasoning, coding, long-running agents, tools, and very large outputs.
Open full comparisonCeleris-1 Magnus vs DeepSeek-V4-Flash
DeepSeek's lower-cost V4 model for high-volume reasoning, coding, agents, and million-token text workloads.
Open full comparison
