LLM Reference

Claude Mythos Preview

Released
2026-05-01
Last refreshed
2026-07-26
Status
Researched 94d ago
ProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use

Claude Mythos Preview is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 1m context window
  • Buyers comparing 2 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Released
2026-05-01
Context
1m
Architecture
Decoder Only
Knowledge cutoff
2025-12
Specialization
security
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Pretrained
Created by

Developing safe and ethical AI systems.

San Francisco, California, United States
Founded 2021
Website
Pricing
Output / 1M
$125.00
Input / 1M
$25.00

Cheapest of 2 routes · Anthropic

About

Anthropic's cybersecurity-focused frontier model, offered as an invitation-only research preview under Project Glasswing. Succeeded by Claude Mythos 5 (API ID: claude-mythos-5) as of June 9, 2026. Anthropic has indicated that Claude Mythos Preview will be retired after Claude Mythos 5 becomes available; no formal retirement date was published as of 2026-06-09. For current access and the migration path, see the Anthropic migration guide.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ D

1 relevant benchmark in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ D

2 relevant benchmarks in the decision map.

Provider price ladder

Compare all 2

Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Anthropic$25.00$125.00
Serverless
Microsoft Foundry--
ServerlessPartial

Available via routers & gateways(15)

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsCode Execution

Benchmark peer barsfor Coding

Benchmark scores(3)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
SWE-bench Verified93.9SWE-bench VerifiedObserved 2026-05-01Source
τ-bench89.2τ-benchObserved 2026-05-05Source
Google-Proof Q&A94.6diamondObserved 2026-05-05Source

Migration checks

No linked migration route is available for this model yet.

Compare Claude Mythos Preview with other models

Show all 19 popular comparisonssorted by 7-day search impressions