Skip to main content

Claude Sonnet 4.5 20250929

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking. Sonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.

Input / output price
$3.00 / $15.00 per 1M
Context
200K tokens
Released
Sep 29, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "anthropic/claude-sonnet-4.5-20250929".

Read docs

Providers

3 routes from 2 providers, cheapest first, priced per 1M tokens after gateway discounts.

ProviderInputOutput
AnthropicRetiringanthropic/claude-sonnet-4.5-20250929
$3.00/M$15.00/M
Bedrockbedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0
$3.00/M$15.00/M
Bedrockbedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0
$3.30/M$16.50/M

Is a provider down? Claude status, AWS Bedrock status

Pricing

Averaged across 3 routes from 2 providers, in USD per 1M tokens after gateway discounts.

Average input
$3.10 per 1M
Average output
$15.50 per 1M
Average cache read
$0.31 per 1M
Average cache write
$3.88 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$3.30/MBedrockLowest$3.00/MAnthropic and Bedrock

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

45tokens/sacross providers

Faster than 61% of the other 599 models on the gateway

Time to first token

Lower is better

1.2sacross providers

Faster than 63% of the other 152 models on the gateway

Response latency

Lower is better

6.1sacross providers

Faster than 27% of the other 780 models on the gateway

Benchmarks

The Respan Index plus 37 published scores from 11 sources, each linked to where it was published.

31.3/ 100

Respan Index#86 of 176

176 ranked models. The shaded band is this model's 95% interval, 28.2 to 35.0. Inkling and MiniMax M3 fall inside it, so the gap is within the margin of error.
Claude Sonnet 4.5 20250929 by category: Coding 13.1, Agents 41.7, Reasoning 27.5, Knowledge & language 31.2, Human preference 50.9
  1. 86Claude Sonnet 4.531.3
  2. 85Inkling31.9
  3. 87MiniMax M331.2

Published scores

BenchmarkScore
SWE-bench VerifiedAnthropic77.2%
SWE-bench VerifiedEpoch AI71.3%
Terminal-Bench 2.0Anthropic51%
WeirdMLHåvard Tveit Ihle47.7%
GSO Opt@1GSO12.7%

Compare Claude Sonnet 4.5 20250929: Claude Sonnet 4.5 vs Claude Sonnet 4, Claude Sonnet 4.5 vs Claude Sonnet 4.6, Claude Sonnet 4.5 vs GLM-5, Claude Sonnet 4.5 vs Claude Fable 5.2, Claude Sonnet 4.5 vs Claude Opus 5.5, Claude Sonnet 4.5 vs Claude Sonnet 5.5

Apps

Use Claude Sonnet 4.5 20250929 in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Claude Sonnet 4.5 20250929 FAQ

Short answers, built from the data on this page.

Claude Sonnet 4.5 20250929 is a model from Anthropic, released on Sep 29, 2025. Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking. Sonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.

On the Respan gateway, Claude Sonnet 4.5 20250929 costs from $3.00 per 1M input tokens and $15.00 per 1M output tokens on Anthropic and Bedrock, after gateway discounts. Averaged across its 3 routes from 2 providers, it costs $3.10 per 1M input tokens and $15.50 per 1M output tokens.

Claude Sonnet 4.5 20250929 is available through 3 routes from 2 providers: Anthropic and Bedrock.

Claude Sonnet 4.5 20250929 accepts up to 200K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "anthropic/claude-sonnet-4.5-20250929". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Claude Sonnet 4.5 20250929 scores 31.3 out of 100 on the Respan Index v1.1, ranking #86 of 176 models. By category: Coding 13.1, Agents 41.7, Reasoning 27.5, Knowledge & language 31.2, and Human preference 50.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Claude Sonnet 4.5 20250929 has 37 published benchmark scores, including SWE-bench Verified 77.2%, Tau2-bench Telecom 98%, and GPQA Diamond 83.4%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.