Anthropic: Claude Sonnet 5

anthropic/claude-sonnet-5

Claude Sonnet 5 (Anthropic) ranks #41 of 261 on the TryAii Score at $2/$10 per million input/output tokens, though Ling 3.1 Flash matches it for $0.225 per million output tokens. It's strongest on knowledge (#29 on GPQA). It's reasonably quick at roughly 50-74 tokens/sec.

Prompt $/1M

$2.000

Completion $/1M

$10.000

Context

1,000,000 tok

Best provider

87 tok/s · Google

Specs

Model id: anthropic/claude-sonnet-5
Display name: Anthropic: Claude Sonnet 5
Modality: text+image+file->text
Tokenizer: Claude
Instruct type: —
Context length: 1,000,000
Max completion: 128,000
Prompt $/1M: $2.000
Completion $/1M: $10.000
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
Google	87	2,408 ms	2,777 ms
Claude Platform on AWS	74	1,249 ms	2,144 ms
Anthropic	73	1,208 ms	1,996 ms
Azure	51	1,377 ms	1,660 ms
Amazon Bedrock	51	3,883 ms	4,288 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).
Amazon Bedrock	1,024 tokens	General Claude-on-Bedrock tier (5-min TTL, reset on hit).
Anthropic	1,024 tokens	Sonnet tier (all versions).