Anthropic models on Felo

Compare the Anthropic models currently available through Felo, including model IDs, pricing, context windows, and Quick Start examples.

models

max context

protocols

Flagships first

ModelContextPricing

Claude Opus 4.8

Anthropicclaude-opus-4-8

A premium route for complex planning, multi-step analysis, high-stakes content generation, and advanced software engineering assistance.

Deep analysisComplex codingStrategy workLong-horizon agents

Context

Max output

128K

Input tokens

$5.00 /M

Output tokens

$25.00 /M

Claude Sonnet 5

Anthropicclaude-sonnet-5

A strong default for modern applications that need long context, tool use, structured output, and reliable streaming responses.

Default model routeAssistant appsCodingKnowledge workflows

Context

Max output

128K

Input tokens

$2.00 /M

Output tokens

$10.00 /M

Claude Sonnet 4.6

Anthropicclaude-sonnet-4-6

A general-purpose flagship route for agent workflows, long document understanding, coding assistance, and production-grade reasoning.

Agent tasksCode generationLong documentsResearch workflows

Context

Max output

128K

Input tokens

$3.00 /M

Output tokens

$15.00 /M

Claude Haiku 4.5

Anthropicclaude-haiku-4-5

A compact, responsive model route for support bots, extraction, classification, and search-backed answers where latency matters.

High-throughput chatClassificationExtractionSearch summaries

Context

200K

Max output

64K

Input tokens

$1.00 /M

Output tokens

$5.00 /M