LLM ReferenceLLM Reference

Claude Haiku 4.5 vs Claude Mythos Preview

Claude Haiku 4.5 (2025) and Claude Mythos Preview (2026) are frontier reasoning models from Anthropic. Claude Haiku 4.5 ships a 200k-token context window, while Claude Mythos Preview ships a 1M-token context window. On SWE-bench Verified, Claude Mythos Preview leads by 20.6 pts. On pricing, Claude Haiku 4.5 costs $0.8/1M input tokens versus $25/1M for the alternative. This comparison covers specs, pricing, capabilities, benchmarks, provider availability, and production fit.

Claude Haiku 4.5 is ~3025% cheaper at $0.8/1M; pay for Claude Mythos Preview only for coding workflow support.

Decision scorecard

Local evidence first
SignalClaude Haiku 4.5Claude Mythos Preview
Decision fitCoding, RAG, and AgentsCoding, RAG, and Agents
Context window200k1M
Cheapest output$4/1M tokens$125/1M tokens
Provider routes7 tracked2 tracked
Shared benchmarks1 rowsSWE-bench Verified leader

Decision tradeoffs

Choose Claude Haiku 4.5 when...
  • Claude Haiku 4.5 has the lower cheapest tracked output price at $4/1M tokens.
  • Claude Haiku 4.5 has broader tracked provider coverage for fallback and procurement flexibility.
  • Local decision data tags Claude Haiku 4.5 for Coding, RAG, and Agents.
Choose Claude Mythos Preview when...
  • Claude Mythos Preview leads the largest shared benchmark signal on SWE-bench Verified by 20.6 points.
  • Claude Mythos Preview has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • Claude Mythos Preview uniquely exposes Reasoning in local model data.
  • Local decision data tags Claude Mythos Preview for Coding, RAG, and Agents.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output prices on this page.

Lower estimate Claude Haiku 4.5

Claude Haiku 4.5

$1,640

Cheapest tracked route: AWS Bedrock

Claude Mythos Preview

$51,250

Cheapest tracked route: Anthropic

Estimated monthly gap: $49,610. Batch, cache, and negotiated pricing are excluded from this local estimate.

Switch friction

Claude Haiku 4.5 -> Claude Mythos Preview
  • Provider overlap exists on Anthropic and Microsoft Foundry; start route-level A/B tests there.
  • Claude Mythos Preview is $121/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Claude Mythos Preview adds Reasoning in local capability data.
Claude Mythos Preview -> Claude Haiku 4.5
  • Provider overlap exists on Microsoft Foundry and Anthropic; start route-level A/B tests there.
  • Claude Haiku 4.5 is $121/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for Reasoning before moving production traffic.

Specs

Specification
Released2025-10-012026-04-07
Context window200k1M
Parameters
Architecturedecoder onlydecoder only
LicenseProprietaryProprietary
Knowledge cutoff2025-022025-12

Pricing and availability

Pricing attributeClaude Haiku 4.5Claude Mythos Preview
Input price$0.8/1M tokens$25/1M tokens
Output price$4/1M tokens$125/1M tokens
Providers

Capabilities

CapabilityClaude Haiku 4.5Claude Mythos Preview
VisionYesYes
MultimodalYesYes
ReasoningNoYes
Function callingYesYes
Tool useYesYes
Structured outputsYesYes
Code executionYesYes

Benchmarks

BenchmarkClaude Haiku 4.5Claude Mythos Preview
SWE-bench Verified73.393.9

Deep dive

On shared benchmark coverage, SWE-bench Verified has Claude Haiku 4.5 at 73.3 and Claude Mythos Preview at 93.9, with Claude Mythos Preview ahead by 20.6 points. The largest visible gap is 20.6 points on SWE-bench Verified, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.

The capability footprint differs most on reasoning mode: Claude Mythos Preview. Both models share vision, multimodal input, function calling, and tool use, 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, Claude Haiku 4.5 lists $0.8/1M input and $4/1M output tokens, while Claude Mythos Preview lists $25/1M input and $125/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Claude Haiku 4.5 lower by about $53.24 per million blended tokens. Availability is 7 providers versus 2, so concentration risk also matters.

Choose Claude Haiku 4.5 when coding workflow support, lower input-token cost, and broader provider choice are central to the workload. Choose Claude Mythos Preview when coding workflow support and larger context windows are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.

FAQ

Which has a larger context window, Claude Haiku 4.5 or Claude Mythos Preview?

Claude Mythos Preview supports 1M tokens, while Claude Haiku 4.5 supports 200k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.

Which is cheaper, Claude Haiku 4.5 or Claude Mythos Preview?

Claude Haiku 4.5 is cheaper on tracked token pricing. Claude Haiku 4.5 costs $0.8/1M input and $4/1M output tokens. Claude Mythos Preview costs $25/1M input and $125/1M output tokens. Provider discounts or batch pricing can still change the final bill.

Is Claude Haiku 4.5 or Claude Mythos Preview open source?

Claude Haiku 4.5 is listed under Proprietary. Claude Mythos Preview is listed under Proprietary. 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, Claude Haiku 4.5 or Claude Mythos Preview?

Both Claude Haiku 4.5 and Claude Mythos Preview expose vision. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.

Which is better for multimodal input, Claude Haiku 4.5 or Claude Mythos Preview?

Both Claude Haiku 4.5 and Claude Mythos Preview expose multimodal input. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.

Where can I run Claude Haiku 4.5 and Claude Mythos Preview?

Claude Haiku 4.5 is available on Microsoft Foundry, Anthropic, Snowflake Cortex, AWS Bedrock, and GCP Vertex AI. Claude Mythos Preview is available on Anthropic and Microsoft Foundry. Provider coverage can affect latency, region availability, compliance posture, and fallback options.

Continue comparing

Last reviewed: 2026-05-16. Data sourced from public model cards and provider documentation.