Anthropic: Claude Sonnet 4.6

Claude workhorse for coding agents, careful analysis, and production cost control

Source-linked claude-sonnet Closed weights Released 2026-02-17

API record Report

InputT

OutputT

Input price$3/M

Output price$15/M

Context1M

Max output64K

Providers52

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering Claude Sonnet 4.6
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
AnyAPI	`anthropic/claude-sonnet-4-6`	1M	64K	—	—	—	ReasoningTools	Docs ↗
Xpersona	`claude-sonnet-4-6`	200K	128K	$0.9	$5.55	$0.09	ReasoningTools	Docs ↗
Requesty	`anthropic/claude-sonnet-4-6`	1M	128K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Vercel AI Gateway	`anthropic/claude-sonnet-4.6`	1M	128K	$3	$15	$0.3	ReasoningTools	Docs ↗
Auriko	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
DigitalOcean	`anthropic-claude-4.6-sonnet`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
Venice AI	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
CrossModel	`anthropic/claude-sonnet-4-6`	1M	128K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Snowflake Cortex	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Merge Gateway	`anthropic/claude-sonnet-4-6`	1M	128K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
OrcaRouter	`anthropic/claude-sonnet-4.6`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
NEAR AI Cloud	`anthropic/claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
Pioneer	`claude-sonnet-4-6`	1M	128K	$3	$15	$0.3	ReasoningTools	Docs ↗
DevPass (LLM Gateway)	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
Abacus	`claude-sonnet-4-6`	1M	64K	$3	$15	—	ReasoningTools	Docs ↗
Cloudflare AI Gateway	`anthropic/claude-sonnet-4-6`	1M	128K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
DaoXE	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
Vertex (Anthropic)	`claude-sonnet-4-6@default`	1M	128K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Azure	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Anthropic	`claude-sonnet-4-6`	1M	128K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
FreeModel	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
OpenCode	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
Perplexity Agent	`anthropic/claude-sonnet-4-6`	200K	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
GMI Cloud	`anthropic/claude-sonnet-4.6`	409.6K	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
FrogBot	`claude-sonnet-4-6`	200K	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
OpenRouter	`anthropic/claude-sonnet-4.6`	1M	128K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Databricks	`databricks-claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
FastRouter	`anthropic/claude-sonnet-4.6`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
routing.run	`claude-sonnet-4-6`	1M	64K	$3	$15	—	ReasoningTools	Docs ↗
AIHubMix	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Vertex	`claude-sonnet-4-6@default`	1M	128K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
NanoGPT	`anthropic/claude-sonnet-4.6`	1M	128K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Neon	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
GitHub Copilot	`claude-sonnet-4.6`	200K	32K	$3	$15	$0.3	ReasoningTools	Docs ↗
Modelis	`claude-sonnet-4-6`	1M	64K	$3	$15	—	ReasoningTools	Docs ↗
Impossibl	`anthropic/claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
Kilo Gateway	`anthropic/claude-sonnet-4.6`	1M	128K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Requesty	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Ofox	`anthropic/claude-sonnet-4.6`	1M	128K	$3	$15	$0.3	ReasoningTools	Docs ↗
Azure Cognitive Services	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Eden AI	`anthropic/claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Cloudflare AI Gateway	`anthropic/claude-sonnet-4.6`	1M	128K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Opper	`anthropic/claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
LLM Gateway	`anthropic/claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Tempr Gateway	`anthropic/claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningToolsJSON	Docs ↗
Prime Inference	`anthropic/claude-sonnet-4.6`	1M	128K	$3	$15	—	ReasoningToolsJSON	Docs ↗
CommandCode	`claude-sonnet-4-6`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
ZenMux	`anthropic/claude-sonnet-4.6`	1M	64K	$3	$15	$0.3	ReasoningTools	Docs ↗
Cortecs	`claude-4-6-sonnet`	1M	128K	$3.196	$15.94	$0.32	ReasoningToolsJSON	Docs ↗
Amazon Bedrock	`anthropic.claude-sonnet-4-6`	1M	128K	$3.3	$16.5	$0.33	ReasoningToolsJSON	Docs ↗
Opper	`claude-sonnet-4-6`	1M	64K	$3.3	$16.5	$0.33	ReasoningToolsJSON	Docs ↗
Kenari	`claude-sonnet-4-6`	1M	64K	$3.6	$17.714	$0.36	ReasoningTools	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.9/M

Across 51 priced providers

Median input $3/M

Midpoint of listed rates

Highest input $3.6/M

4.0× the lowest listed rate

Output range $5.55 – $17.714

Per million output tokens

Xpersona $0.9/MLowest

Requesty $3/M

Vercel AI Gateway $3/M

Auriko $3/M

DigitalOcean $3/M

Venice AI $3/M

CrossModel $3/M

Snowflake Cortex $3/M

Merge Gateway $3/M

OrcaRouter $3/M

NEAR AI Cloud $3/M

Pioneer $3/M

DevPass (LLM Gateway) $3/M

Abacus $3/M

Cloudflare AI Gateway $3/M

DaoXE $3/M

Vertex (Anthropic) $3/M

Azure $3/M

Anthropic $3/M

FreeModel $3/M

OpenCode $3/M

Perplexity Agent $3/M

GMI Cloud $3/M

FrogBot $3/M

OpenRouter $3/M

Databricks $3/M

FastRouter $3/M

routing.run $3/M

AIHubMix $3/M

Vertex $3/M

NanoGPT $3/M

Neon $3/M

GitHub Copilot $3/M

Modelis $3/M

Impossibl $3/M

Kilo Gateway $3/M

Requesty $3/M

Ofox $3/M

Azure Cognitive Services $3/M

Eden AI $3/M

Cloudflare AI Gateway $3/M

Opper $3/M

LLM Gateway $3/M

Tempr Gateway $3/M

Prime Inference $3/M

CommandCode $3/M

ZenMux $3/M

Cortecs $3.196/M

Amazon Bedrock $3.3/M

Opper $3.3/M

Kenari $3.6/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 200K to 1M tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes

✓ Tool calling Yes

? Structured output Unknown

✓ Attachments Yes

✓ Vision input Yes

× Open weights No

Creator: Anthropic
Model family: claude-sonnet
Knowledge cutoff: 2025-08-31
License: Not documented
Release date: 2026-02-17
Model ID: anthropic/claude-sonnet-4-6

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

Benchmark profile

Each axis is this model's percentile among the 7 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

Humanity's Last Exam accuracy · 2026-06-30 Source ↗

Humanity's Last Exam #15 of 23

46.8

OSWorld-Verified success rate · 2026-06-30 Source ↗

OSWorld-Verified #8 of 17

78.5

Terminal-Bench — 2.1 pass@1 · Claude Code Source ↗

Terminal-Bench #7 of 7

63.1

Terminal-Bench — 2.1 success rate · Terminus-2 · 2026-06-30 Source ↗

Terminal-Bench #6 of 7

67.0

Artificial Analysis Coding Agent Index average pass@1 · Claude Code Source ↗

Artificial Analysis Coding Agent Index #6 of 6

49.4

SWE-Atlas Codebase QnA pass@1 · Claude Code Source ↗

SWE-Atlas Codebase QnA #4 of 6

70.3

SWE-Bench Pro pass@1 · Claude Code Source ↗

SWE-Bench Pro #5 of 6

14.9

SWE-Atlas Refactoring score · Claude Code Source ↗

SWE-Atlas Refactoring #3 of 3

32.21

SWE-Atlas Codebase QnA score · Claude Code Source ↗

31.2 2 models scored — too few for a distribution

SWE-Atlas Test Writing score · Claude Code Source ↗

31.76 2 models scored — too few for a distribution

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against Humanity's Last Exam, the benchmark with the widest published coverage that this model appears in.

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

No changes recorded

This record has not changed within the retained import history.

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Oct 24, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://modelbench.lol/api/v1/models/anthropic/claude-sonnet-4-6

curl

curl "https://modelbench.lol/api/v1/models/anthropic/claude-sonnet-4-6"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Claude Sonnet 4.6?

Claude workhorse for coding agents, careful analysis, and production cost control. It is published by Anthropic and catalogued here from Models.dev.

How much does Claude Sonnet 4.6 cost?

Listed input pricing starts at $0.9 per million tokens from Xpersona, rising to $3.6 across 51 listed providers.

What is the context length of Claude Sonnet 4.6?

Claude Sonnet 4.6 accepts up to 1M tokens of context and returns up to 64K output tokens.

Does Claude Sonnet 4.6 support tool calling and structured output?

Provider catalogs list support for tool calling, reasoning, and image input.

Which providers serve Claude Sonnet 4.6?

49 providers list this model: AnyAPI, Xpersona, Requesty, Vercel AI Gateway, Auriko, DigitalOcean and 43 more.

Are the weights for Claude Sonnet 4.6 open?

No. This model is served through hosted APIs only.

When was Claude Sonnet 4.6 released?

The catalog records a release date of 2026-02-17, last verified Oct 24, 2026.

More models from Anthropic

View all →

Claude Sonnet 5

Everyday Claude agent model for coding, planning, browsing, and general work

1M ctx $2/M in Claude Fable 5

Claude model for creative writing, analysis, and controlled agent workflows

1M ctx $10/M in Anthropic: Claude Opus 4.8 (Fast)

Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

1M ctx $10/M in Anthropic: Claude Opus 4.8

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

1M ctx $5/M in