LLM Reference

Claude 3.7 Sonnet vs Claude 3.5 Haiku

Claude 3.7 Sonnet (2024) and Claude 3.5 Haiku (2024) are frontier-tier reasoning models from Anthropic. Claude 3.7 Sonnet ships a 200k-token context window, while Claude 3.5 Haiku ships a 200k-token context window. On pricing, Claude 3.5 Haiku costs $0.80/1M input tokens versus $3/1M 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 3.5 Haiku is ~275% cheaper at $0.80/1M; pay for Claude 3.7 Sonnet only for coding workflow support.

Decision scorecard

Local evidence first
SignalClaude 3.7 SonnetClaude 3.5 Haiku
Best forreasoning-heavy apps, multimodal apps, and tool-calling agentsreasoning-heavy apps, multimodal apps, and provider-routed production
Decision fitCoding, RAG, and AgentsCoding, RAG, and Agents
Context window200k200k
Cheapest output$15/1M tokens$4/1M tokens
Provider routes6 tracked6 tracked
Shared benchmarks0 shared0 shared

Decision tradeoffs

Choose Claude 3.7 Sonnet when...
  • Claude 3.7 Sonnet uniquely exposes Multimodal and JSON / Tool use in local model data.
  • Local decision data tags Claude 3.7 Sonnet for Coding, RAG, and Agents.
Choose Claude 3.5 Haiku when...
  • Claude 3.5 Haiku has the lower cheapest tracked output price at $4/1M tokens.
  • Local decision data tags Claude 3.5 Haiku 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 3.5 Haiku

Claude 3.7 Sonnet

$6,150

Cheapest tracked route/tier: GCP Vertex AI

Claude 3.5 Haiku

$1,640

Cheapest tracked route/tier: Anthropic

Estimated monthly gap: $4,510. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Claude 3.7 Sonnet -> Claude 3.5 Haiku
  • Provider overlap exists on Anthropic, OpenRouter, and AWS Bedrock; start route-level A/B tests there.
  • Claude 3.5 Haiku is $11/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for Multimodal and JSON / Tool use before moving production traffic.
Claude 3.5 Haiku -> Claude 3.7 Sonnet
  • Provider overlap exists on GCP Vertex AI, Replicate API, and OpenRouter; start route-level A/B tests there.
  • Claude 3.7 Sonnet is $11/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Claude 3.7 Sonnet adds Multimodal and JSON / Tool use in local capability data.

Specs

Specification
Released2024-03-042024-10-22
Context window200k200k
Parameters——
ArchitectureDecoder OnlyDecoder Only
LicenseProprietaryProprietary
OpennessProprietaryProprietary
WeightsNot releasedNot released
CodeUnknownUnknown
Commercial useCommercial use: conditionalCommercial use: conditional
Knowledge cutoff2024-11-

Pricing and availability

Pricing attributeClaude 3.7 SonnetClaude 3.5 Haiku
Input price$3/1M tokens$0.80/1M tokens
Output price$15/1M tokens$4/1M tokens
Providers
Snowflake CortexGCP Vertex AIReplicate APIOpenRouterAWS BedrockAnthropic
AnthropicOpenRouterAWS BedrockGCP Vertex AIReplicate APIVercel AI Gateway

Capabilities

CapabilityClaude 3.7 SonnetClaude 3.5 Haiku
VisionYesYes
MultimodalYesNo
ReasoningYesYes
JSON / Tool useYesNo
Structured outputsYesYes
Code executionYesYes
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark scores are currently available for this pair.

Continue comparing

Model pages
Labs and families
Related comparisons

Popular comparisons for Claude 3.7 Sonnet

Popular comparisons for Claude 3.5 Haiku

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