Anthropic: Claude Sonnet 4

anthropic/claude-sonnet-4

Claude Sonnet 4 is Anthropic's budget option at $3/$15 per million input/output tokens, with a 1M-token context. It sits mid-board on capability, at #110 of 235 on the TryAii Score — its best showing is #3 on SWE-bench-verified. It's reasonably quick at roughly 46-50 tokens/sec.

Prompt $/1M

$3.000

Completion $/1M

$15.000

Context

1,000,000 tok

Best provider

54 tok/s · Amazon Bedrock

Specs

Model id: anthropic/claude-sonnet-4
Display name: Anthropic: Claude Sonnet 4
Modality: text+image+file->text
Tokenizer: Claude
Instruct type: —
Context length: 1,000,000
Max completion: 64,000
Prompt $/1M: $3.000
Completion $/1M: $15.000
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedyes

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Amazon Bedrockfastest	54	933 ms	1,238 ms
Google	46	534 ms	555 ms
Anthropicfastest	45	1,125 ms	1,302 ms

Prompt caching by provider

Provider	Min tokens to cache	Notes
Google Vertex	1,024 tokens	Claude-on-Vertex, Opus 4.0/4.1/4.8 + Sonnet tiers (Anthropic per-model tiers).
Anthropic	1,024 tokens	Sonnet tier (all versions).
Amazon Bedrock	1,024 tokens	General Claude-on-Bedrock tier (5-min TTL, reset on hit).