Claude Haiku 4.5 20251001
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. $1 per million input tokens, $5 per million output tokens. 200,000 token context window, maximum output of 64,000 tokens. Higher uptime with 4 providers. Includes independent benchmarks from Artificial Analysis.
- Input / output price
- $1.00 / $5.00 per 1M
- Context
- 200K tokens
- Released
- Oct 15, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
3 routes from 2 providers, cheapest first, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Anthropic anthropic/claude-haiku-4.5-20251001 | $1.00/M | $5.00/M |
Bedrock bedrock/global.anthropic.claude-haiku-4-5-20251001-v1:0 | $1.00/M | $5.00/M |
Bedrock bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0 | $1.10/M | $5.50/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
- $1.03 per 1M
- Average output
- $5.17 per 1M
- Average cache read
- $0.10 per 1M
- Average cache write
- $1.29 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
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 better14tokens/sacross providers
Time to first token
Lower is better0.4sacross providers
Response latency
Lower is better0.7sacross providers
Benchmarks
The Respan Index plus 17 published scores from 7 sources, each linked to where it was published.
19.3/ 100
Respan Index#132 of 176
- 132Claude Haiku 4.519.3
- 131Qwen3-Max19.6
- 132Claude 3.7 Sonnet19.3
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SWE-bench VerifiedAnthropic | 73.3% | Anthropic | Oct 15, 2025 |
| WeirdMLHåvard Tveit Ihle | 45.4% | Håvard Tveit Ihle | Oct 5, 2026 |
| Terminal-Bench 4.0Anthropic | 0% | Anthropic | Oct 7, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| BALROGBALROG | 31.2% | BALROG | Feb 24, 2026 |
| OSWorld 2.1 (offline subset)Anthropic | 15.7% | Anthropic | Oct 7, 2026 |
| Vending-Bench 2Andon Labs | 458.89 · #59 of 68 | Andon Labs | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 71.2% | Epoch AI | Oct 5, 2026 |
| Humanity's Last Exam (with tools)Anthropic | 18.7% | Anthropic | Oct 7, 2026 |
| Humanity's Last Exam (no tools)Anthropic | 10.2% | Anthropic | Oct 7, 2026 |
| Chess PuzzlesEpoch AI | 8% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MATH Level 5Epoch AI | 96.4% | Epoch AI | Oct 5, 2026 |
| OTIS Mock AIME 2024-2025Epoch AI | 66.7% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SimpleQA VerifiedEpoch AI | 13.2% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Chartography (no tools)Anthropic | 6.4% | Anthropic | Oct 7, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1414 Elo · #112 of 191 | LMArena | Oct 8, 2026 |
| LMArena WebDevLMArena | 1330 Elo · #108 of 124 | LMArena | Oct 8, 2026 |
How Claude compares: Claude vs Gemini, Claude vs Grok, Claude vs GPT
Compare Claude Haiku 4.5 20251001: Claude Haiku 4.5 vs Claude Haiku 5.5, Claude Haiku 4.5 vs Gemini 3.8 Flash, Claude Haiku 4.5 vs Gemini 3.5 Flash, Claude Haiku 4.5 vs Gemini 3.6 Flash, Claude Haiku 4.5 vs Claude Fable 5.2, Claude Haiku 4.5 vs Claude Opus 5.5
Apps
Use Claude Haiku 4.5 20251001 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 Haiku 4.5 20251001 FAQ
Short answers, built from the data on this page.
Claude Haiku 4.5 20251001 is a model from Anthropic, released on Oct 15, 2025. Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. $1 per million input tokens, $5 per million output tokens. 200,000 token context window, maximum output of 64,000 tokens. Higher uptime with 4 providers. Includes independent benchmarks from Artificial Analysis.
On the Respan gateway, Claude Haiku 4.5 20251001 costs from $1.00 per 1M input tokens and $5.00 per 1M output tokens on Anthropic and Bedrock, after gateway discounts. Averaged across its 3 routes from 2 providers, it costs $1.03 per 1M input tokens and $5.17 per 1M output tokens.
Claude Haiku 4.5 20251001 is available through 3 routes from 2 providers: Anthropic and Bedrock.
Claude Haiku 4.5 20251001 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-haiku-4.5-20251001". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Claude Haiku 4.5 20251001 scores 19.3 out of 100 on the Respan Index v1.1, ranking #132 of 176 models. By category: Coding 5.1, Agents 15.7, Reasoning 21.5, Knowledge & language 13.2, and Human preference 49.1. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Claude Haiku 4.5 20251001 has 17 published benchmark scores, including SWE-bench Verified 73.3%, BALROG 31.2%, and GPQA Diamond 71.2%. 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.