LLM Reference

Claude Fable 5 vs Claude Sonnet 4.6

Claude Fable 5 (2026) and Claude Sonnet 4.6 (2026) are frontier-tier reasoning models from Anthropic. Claude Fable 5 ships a 1m-token context window, while Claude Sonnet 4.6 ships a 1m-token context window. On SWE-bench Verified, Claude Fable 5 leads by 16.4 pts. On pricing, Claude Sonnet 4.6 costs $3/1M input tokens versus $10/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

Claude Sonnet 4.6 is ~233% cheaper at $3/1M; pay for Claude Fable 5 only for vision-heavy evaluation.

Decision scorecard

Local evidence first
SignalClaude Fable 5Claude Sonnet 4.6
Best forreasoning-heavy apps, multimodal apps, and tool-calling agentsreasoning-heavy apps, multimodal apps, and tool-calling agents
Decision fitCoding, RAG, and AgentsCoding, RAG, and Agents
Context window1m1m
Cheapest output$50/1M tokens$15/1M tokens
Provider routes8 tracked6 tracked
Shared benchmarksSWE-bench Verified leader7 shared

Decision tradeoffs

Choose Claude Fable 5 when...
  • Claude Fable 5 holds a shared-benchmark lead on SWE-bench Verified, ahead by 16.4 points.
  • Claude Fable 5 has broader tracked provider coverage for fallback and route flexibility.
  • Local decision data tags Claude Fable 5 for Coding, RAG, and Agents.
Choose Claude Sonnet 4.6 when...
  • Claude Sonnet 4.6 has the lower cheapest tracked output price at $15/1M tokens.
  • Claude Sonnet 4.6 uniquely exposes Code execution, Computer use, and Parallel agents in local model data.
  • Local decision data tags Claude Sonnet 4.6 for Coding, RAG, and Agents.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Lower estimate Claude Sonnet 4.6

Claude Fable 5

$20,500

Cheapest tracked route/tier: Anthropic

Claude Sonnet 4.6

$6,150

Cheapest tracked route/tier: OpenRouter

Estimated monthly gap: $14,350. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Claude Fable 5 -> Claude Sonnet 4.6
  • Provider overlap exists on OpenRouter, Anthropic, and AWS Bedrock; start route-level A/B tests there.
  • Claude Sonnet 4.6 is $35/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Claude Sonnet 4.6 adds Code execution, Computer use, and Parallel agents in local capability data.
Claude Sonnet 4.6 -> Claude Fable 5
  • Provider overlap exists on Anthropic, AWS Bedrock, and GCP Vertex AI; start route-level A/B tests there.
  • Claude Fable 5 is $35/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Check replacement coverage for Code execution, Computer use, and Parallel agents before moving production traffic.

Specs

Specification
Released2026-06-092026-02-17
Context window1m1m
Parameters——
ArchitectureDecoder OnlyDecoder Only
LicenseProprietaryProprietary
OpennessProprietaryProprietary
WeightsNot releasedNot released
CodeUnknownUnknown
Commercial useCommercial use: conditionalCommercial use: conditional
Knowledge cutoff-2025-08

Pricing and availability

Pricing attributeClaude Fable 5Claude Sonnet 4.6
Input price$10/1M tokens$3/1M tokens
Output price$50/1M tokens$15/1M tokens
Providers
AnthropicAWS BedrockGCP Vertex AIMicrosoft FoundryOpenRouterVercel AI Gateway
OpenRouterAnthropicAWS BedrockGCP Vertex AIMicrosoft FoundryVercel AI Gateway

Capabilities

CapabilityClaude Fable 5Claude Sonnet 4.6
VisionYesYes
MultimodalYesYes
ReasoningYesYes
JSON / Tool useYesYes
Structured outputsYesYes
Code executionNoYes
IDE integrationNoNo
Computer useNoYes
Parallel agentsNoYes

Benchmarks

BenchmarkClaude Fable 5Claude Sonnet 4.6
SWE-bench Verified96.079.6
CursorBench72.949.0
CursorBench70.549.0
CursorBench68.449.0
CursorBench66.549.0
CursorBench65.249.0
CursorBench62.149.0

Continue comparing

Model pages
Labs and families
Related comparisons

Popular comparisons for Claude Sonnet 4.6

Last reviewed: 2026-07-26. Data sourced from public model cards and provider documentation.