GPT-6.1 Sol
Proprietary Commercial ★ Pareto-Optimal FrontierDeveloped by OpenAI · Adaptive Reasoning Multimodal Transformer · Modalities: Text, Vision, Audio · Released 2026-10-15
What are the token costs and operational benchmarks for GPT-6.1 Sol?
Verified Capability Benchmarks
Composite Intelligence: 91.2/100Architectural & Production Profile
Delivers near-GPT-6 Astra frontier accuracy at one-fifth the token cost with a 95% cache read discount for high-efficiency agentic coding, computer use, and enterprise workflow automation.
Delivers near-GPT-6 Astra frontier accuracy at one-fifth the token cost with a 95% cache read discount for high-efficiency agentic coding, computer use, and enterprise workflow automation.
- Architecture
- Adaptive Reasoning Multimodal Transformer
- Modalities
- Text, Vision, Audio
- Max Output Tokens
- 128,000 tokens
- Blended Rate (3:1)
- $4.000 / 1M
Verified Cloud Inference Endpoints Hosting GPT-6.1 Sol
Compare latency, streaming speed, and token pricing across cloud API providers.
| Inference Provider | Role | Input / 1M | Output / 1M | Avg TTFT | Throughput |
|---|---|---|---|---|---|
| OpenAI Platform API → | Primary Host | $2.00 | $10.00 | 520ms | 135 tok/s |
Interactive Monthly Token Economics & ROI Forecaster
Model production workloads across prompt, completion, and cached context tokens, or switch models on the fly.
Estimated Monthly Spend
$2.00/1M in · $10.00/1M out
Prompt Cache: $0.100/1M read · $2.00/1M write
$2.00/1M in · $10.00/1M out
Prompt Cache: $0.100/1M read · $0.50/1M write
Head-to-Head Comparisons Involving GPT-6.1 Sol (36)
GPT-6.1 Sol vs Gemini 4 Argon
Gemini 4 Argon and GPT-6.1 Sol share identical input pricing at $2.00 per 1M tokens ($10.00 vs. $10.00 output). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (330ms faster than Gemini 4 Argon) with 135 vs. 115 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 84.5% for Gemini 4 Argon and 92.4% vs. 93.8% on GPQA Diamond.
GPT-6.1 Sol vs Claude 4.5 Sonnet
GPT-6.1 Sol is 33.3% cheaper for input tokens ($2.00 vs. $3.00 per 1M tokens) and $10.00 vs. $15.00 for output tokens (1.5x cost advantage). In terms of operational performance, Claude 4.5 Sonnet delivers lower response latency at 380ms TTFT (140ms faster than GPT-6.1 Sol) with 84 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 75.8% for Claude 4.5 Sonnet and 92.4% vs. 84.2% on GPQA Diamond.
GPT-6.1 Sol vs Claude Opus 5.5
GPT-6.1 Sol is 50.0% cheaper for input tokens ($2.00 vs. $4.00 per 1M tokens) and $10.00 vs. $20.00 for output tokens (2.0x cost advantage). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (160ms faster than Claude Opus 5.5) with 135 vs. 95 tok/s throughput. Claude Opus 5.5 leads coding evaluations at 89.9% SWE-bench Verified vs. 86.4% for GPT-6.1 Sol and 93.2% vs. 92.4% on GPQA Diamond.
GPT-6.1 Sol vs Gemini 3.8 Flash
Gemini 3.8 Flash is 87.5% cheaper for input tokens ($0.25 vs. $2.00 per 1M tokens) and $1.50 vs. $10.00 for output tokens (8.0x cost advantage). In terms of operational performance, Gemini 3.8 Flash delivers lower response latency at 105ms TTFT (415ms faster than GPT-6.1 Sol) with 210 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 68.5% for Gemini 3.8 Flash and 92.4% vs. 79.2% on GPQA Diamond.
GPT-6.1 Sol vs GPT-5
GPT-6.1 Sol is 20.0% cheaper for input tokens ($2.00 vs. $2.50 per 1M tokens) and $10.00 vs. $10.00 for output tokens (1.2x cost advantage). In terms of operational performance, GPT-5 delivers lower response latency at 340ms TTFT (180ms faster than GPT-6.1 Sol) with 105 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 74.9% for GPT-5 and 92.4% vs. 85.4% on GPQA Diamond.
GPT-6.1 Sol vs GPT-6 Astra
GPT-6.1 Sol is 80.0% cheaper for input tokens ($2.00 vs. $10.00 per 1M tokens) and $10.00 vs. $50.00 for output tokens (5.0x cost advantage). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (220ms faster than GPT-6 Astra) with 135 vs. 74 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 75.7% for GPT-6 Astra and 92.4% vs. 96.0% on GPQA Diamond.
GPT-6.1 Sol vs DeepSeek V4 Pro
DeepSeek V4 Pro is 34.0% cheaper for input tokens ($1.32 vs. $2.00 per 1M tokens) and $3.96 vs. $10.00 for output tokens (1.5x cost advantage). In terms of operational performance, Both models demonstrate comparable response latency around 520ms TTFT (78 vs. 135 tok/s). GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 80.6% for DeepSeek V4 Pro and 92.4% vs. 90.1% on GPQA Diamond.
GPT-6.1 Sol vs DeepSeek R1
DeepSeek R1 is 72.5% cheaper for input tokens ($0.55 vs. $2.00 per 1M tokens) and $2.19 vs. $10.00 for output tokens (3.6x cost advantage). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (930ms faster than DeepSeek R1) with 135 vs. 58 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 49.2% for DeepSeek R1 and 92.4% vs. 71.5% on GPQA Diamond.
GPT-6.1 Sol vs DeepSeek V4 Flash Vision (Exp)
DeepSeek V4 Flash Vision (Exp) is 89.0% cheaper for input tokens ($0.22 vs. $2.00 per 1M tokens) and $0.65 vs. $10.00 for output tokens (9.1x cost advantage). In terms of operational performance, DeepSeek V4 Flash Vision (Exp) delivers lower response latency at 310ms TTFT (210ms faster than GPT-6.1 Sol) with 165 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 77.4% for DeepSeek V4 Flash Vision (Exp) and 92.4% vs. 91.3% on GPQA Diamond.
GPT-6.1 Sol vs OpenAI o3
GPT-6.1 Sol and OpenAI o3 share identical input pricing at $2.00 per 1M tokens ($10.00 vs. $8.00 output). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (630ms faster than OpenAI o3) with 135 vs. 82 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 71.7% for OpenAI o3 and 92.4% vs. 87.7% on GPQA Diamond.
GPT-6.1 Sol vs Claude 4 Opus
GPT-6.1 Sol is 86.7% cheaper for input tokens ($2.00 vs. $15.00 per 1M tokens) and $10.00 vs. $75.00 for output tokens (7.5x cost advantage). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (400ms faster than Claude 4 Opus) with 135 vs. 46 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 77.2% for Claude 4 Opus and 92.4% vs. 87.1% on GPQA Diamond.
GPT-6.1 Sol vs Claude 3.7 Sonnet
GPT-6.1 Sol is 33.3% cheaper for input tokens ($2.00 vs. $3.00 per 1M tokens) and $10.00 vs. $15.00 for output tokens (1.5x cost advantage). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (20ms faster than Claude 3.7 Sonnet) with 135 vs. 72 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 70.3% for Claude 3.7 Sonnet and 92.4% vs. 78.5% on GPQA Diamond.
GPT-6.1 Sol vs Gemini 3.1 Pro
Gemini 3.1 Pro is 37.5% cheaper for input tokens ($1.25 vs. $2.00 per 1M tokens) and $10.00 vs. $10.00 for output tokens (1.6x cost advantage). In terms of operational performance, Gemini 3.1 Pro delivers lower response latency at 420ms TTFT (100ms faster than GPT-6.1 Sol) with 98 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 71.8% for Gemini 3.1 Pro and 92.4% vs. 82.4% on GPQA Diamond.
GPT-6.1 Sol vs Grok 4
GPT-6.1 Sol is 20.0% cheaper for input tokens ($2.00 vs. $2.50 per 1M tokens) and $10.00 vs. $12.50 for output tokens (1.2x cost advantage). In terms of operational performance, Grok 4 delivers lower response latency at 480ms TTFT (40ms faster than GPT-6.1 Sol) with 95 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 73.2% for Grok 4 and 92.4% vs. 86.2% on GPQA Diamond.
GPT-6.1 Sol vs Llama 4 Maverick
Llama 4 Maverick is 90.0% cheaper for input tokens ($0.20 vs. $2.00 per 1M tokens) and $0.60 vs. $10.00 for output tokens (10.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (385ms faster than GPT-6.1 Sol) with 175 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 92.4% vs. 73.8% on GPQA Diamond.
GPT-6.1 Sol vs Qwen 3.8 Flash Next
Qwen 3.8 Flash Next is 92.0% cheaper for input tokens ($0.16 vs. $2.00 per 1M tokens) and $0.47 vs. $10.00 for output tokens (12.5x cost advantage). In terms of operational performance, Qwen 3.8 Flash Next delivers lower response latency at 280ms TTFT (240ms faster than GPT-6.1 Sol) with 185 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 81.0% for Qwen 3.8 Flash Next and 92.4% vs. 91.7% on GPQA Diamond.
GPT-6.1 Sol vs Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite is 96.2% cheaper for input tokens ($0.07 vs. $2.00 per 1M tokens) and $0.30 vs. $10.00 for output tokens (26.7x cost advantage). In terms of operational performance, Gemini 3.5 Flash-Lite delivers lower response latency at 78ms TTFT (442ms faster than GPT-6.1 Sol) with 265 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 55.4% for Gemini 3.5 Flash-Lite and 92.4% vs. 68.4% on GPQA Diamond.
GPT-6.1 Sol vs OpenAI o4-mini
OpenAI o4-mini is 45.0% cheaper for input tokens ($1.10 vs. $2.00 per 1M tokens) and $4.40 vs. $10.00 for output tokens (1.8x cost advantage). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (160ms faster than OpenAI o4-mini) with 135 vs. 125 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 68.1% for OpenAI o4-mini and 92.4% vs. 81.4% on GPQA Diamond.
GPT-6.1 Sol vs DeepSeek V3
DeepSeek V3 is 93.0% cheaper for input tokens ($0.14 vs. $2.00 per 1M tokens) and $0.28 vs. $10.00 for output tokens (14.3x cost advantage). In terms of operational performance, DeepSeek V3 delivers lower response latency at 410ms TTFT (110ms faster than GPT-6.1 Sol) with 78 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 42.0% for DeepSeek V3 and 92.4% vs. 59.1% on GPQA Diamond.
GPT-6.1 Sol vs Gemma 4 31B IT
Gemma 4 31B IT is 94.0% cheaper for input tokens ($0.12 vs. $2.00 per 1M tokens) and $0.36 vs. $10.00 for output tokens (16.7x cost advantage). In terms of operational performance, Gemma 4 31B IT delivers lower response latency at 115ms TTFT (405ms faster than GPT-6.1 Sol) with 155 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 59.2% for Gemma 4 31B IT and 92.4% vs. 71.2% on GPQA Diamond.
GPT-6.1 Sol vs OpenAI o3-mini
OpenAI o3-mini is 45.0% cheaper for input tokens ($1.10 vs. $2.00 per 1M tokens) and $4.40 vs. $10.00 for output tokens (1.8x cost advantage). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (430ms faster than OpenAI o3-mini) with 135 vs. 98 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 49.3% for OpenAI o3-mini and 92.4% vs. 79.7% on GPQA Diamond.
GPT-6.1 Sol vs Claude 3.5 Haiku
Claude 3.5 Haiku is 60.0% cheaper for input tokens ($0.80 vs. $2.00 per 1M tokens) and $4.00 vs. $10.00 for output tokens (2.5x cost advantage). In terms of operational performance, Claude 3.5 Haiku delivers lower response latency at 190ms TTFT (330ms faster than GPT-6.1 Sol) with 130 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 92.4% vs. 41.6% on GPQA Diamond.
GPT-6.1 Sol vs Claude 3.5 Sonnet
GPT-6.1 Sol is 33.3% cheaper for input tokens ($2.00 vs. $3.00 per 1M tokens) and $10.00 vs. $15.00 for output tokens (1.5x cost advantage). In terms of operational performance, Claude 3.5 Sonnet delivers lower response latency at 310ms TTFT (210ms faster than GPT-6.1 Sol) with 80 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 49.0% for Claude 3.5 Sonnet and 92.4% vs. 59.4% on GPQA Diamond.
GPT-6.1 Sol vs Gemini 2.0 Flash
Gemini 2.0 Flash is 95.0% cheaper for input tokens ($0.10 vs. $2.00 per 1M tokens) and $0.40 vs. $10.00 for output tokens (20.0x cost advantage). In terms of operational performance, Gemini 2.0 Flash delivers lower response latency at 280ms TTFT (240ms faster than GPT-6.1 Sol) with 185 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 51.8% for Gemini 2.0 Flash and 92.4% vs. 63.6% on GPQA Diamond.
GPT-6.1 Sol vs Gemini 2.5 Flash
Gemini 2.5 Flash is 85.0% cheaper for input tokens ($0.30 vs. $2.00 per 1M tokens) and $2.50 vs. $10.00 for output tokens (6.7x cost advantage). In terms of operational performance, Gemini 2.5 Flash delivers lower response latency at 110ms TTFT (410ms faster than GPT-6.1 Sol) with 180 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 58.0% for Gemini 2.5 Flash and 92.4% vs. 70.5% on GPQA Diamond.
GPT-6.1 Sol vs Gemini 2.5 Pro
Gemini 2.5 Pro is 37.5% cheaper for input tokens ($1.25 vs. $2.00 per 1M tokens) and $10.00 vs. $10.00 for output tokens (1.6x cost advantage). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (180ms faster than Gemini 2.5 Pro) with 135 vs. 80 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 63.8% for Gemini 2.5 Pro and 92.4% vs. 74.0% on GPQA Diamond.
GPT-6.1 Sol vs GLM-5.3-Flash
GLM-5.3-Flash is 94.0% cheaper for input tokens ($0.12 vs. $2.00 per 1M tokens) and $0.40 vs. $10.00 for output tokens (16.7x cost advantage). In terms of operational performance, GLM-5.3-Flash delivers lower response latency at 90ms TTFT (430ms faster than GPT-6.1 Sol) with 175 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 52.8% for GLM-5.3-Flash and 92.4% vs. 63.5% on GPQA Diamond.
GPT-6.1 Sol vs GLM-5.3
GLM-5.3 is 82.5% cheaper for input tokens ($0.35 vs. $2.00 per 1M tokens) and $1.00 vs. $10.00 for output tokens (5.7x cost advantage). In terms of operational performance, GLM-5.3 delivers lower response latency at 160ms TTFT (360ms faster than GPT-6.1 Sol) with 120 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 56.0% for GLM-5.3 and 92.4% vs. 67.0% on GPQA Diamond.
GPT-6.1 Sol vs GPT-4o Mini
GPT-4o Mini is 92.5% cheaper for input tokens ($0.15 vs. $2.00 per 1M tokens) and $0.60 vs. $10.00 for output tokens (13.3x cost advantage). In terms of operational performance, GPT-4o Mini delivers lower response latency at 220ms TTFT (300ms faster than GPT-6.1 Sol) with 140 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 41.0% for GPT-4o Mini and 92.4% vs. 40.2% on GPQA Diamond.
GPT-6.1 Sol vs GPT-4o
GPT-6.1 Sol is 20.0% cheaper for input tokens ($2.00 vs. $2.50 per 1M tokens) and $10.00 vs. $10.00 for output tokens (1.2x cost advantage). In terms of operational performance, GPT-4o delivers lower response latency at 280ms TTFT (240ms faster than GPT-6.1 Sol) with 100 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 48.0% for GPT-4o and 92.4% vs. 53.6% on GPQA Diamond.
GPT-6.1 Sol vs Grok 3
GPT-6.1 Sol is 33.3% cheaper for input tokens ($2.00 vs. $3.00 per 1M tokens) and $10.00 vs. $15.00 for output tokens (1.5x cost advantage). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (100ms faster than Grok 3) with 135 vs. 88 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 65.8% for Grok 3 and 92.4% vs. 84.6% on GPQA Diamond.
GPT-6.1 Sol vs Grok 3 Mini
Grok 3 Mini is 85.0% cheaper for input tokens ($0.30 vs. $2.00 per 1M tokens) and $1.20 vs. $10.00 for output tokens (6.7x cost advantage). In terms of operational performance, Grok 3 Mini delivers lower response latency at 150ms TTFT (370ms faster than GPT-6.1 Sol) with 160 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 54.0% for Grok 3 Mini and 92.4% vs. 68.0% on GPQA Diamond.
GPT-6.1 Sol vs Llama 3.3 70B Instruct
Llama 3.3 70B Instruct is 94.0% cheaper for input tokens ($0.12 vs. $2.00 per 1M tokens) and $0.30 vs. $10.00 for output tokens (16.7x cost advantage). In terms of operational performance, Llama 3.3 70B Instruct delivers lower response latency at 145ms TTFT (375ms faster than GPT-6.1 Sol) with 165 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 42.5% for Llama 3.3 70B Instruct and 92.4% vs. 55.6% on GPQA Diamond.
GPT-6.1 Sol vs Mistral Large 2 (2411)
GPT-6.1 Sol and Mistral Large 2 (2411) share identical input pricing at $2.00 per 1M tokens ($10.00 vs. $6.00 output). In terms of operational performance, Mistral Large 2 (2411) delivers lower response latency at 380ms TTFT (140ms faster than GPT-6.1 Sol) with 75 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 45.2% for Mistral Large 2 (2411) and 92.4% vs. 54.2% on GPQA Diamond.
GPT-6.1 Sol vs o1
GPT-6.1 Sol is 86.7% cheaper for input tokens ($2.00 vs. $15.00 per 1M tokens) and $10.00 vs. $60.00 for output tokens (7.5x cost advantage). In terms of operational performance, GPT-6.1 Sol delivers lower response latency at 520ms TTFT (2080ms faster than o1) with 135 vs. 48 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 48.9% for o1 and 92.4% vs. 78.0% on GPQA Diamond.
GPT-6.1 Sol vs Qwen 3.8 27B
Qwen 3.8 27B is 90.0% cheaper for input tokens ($0.20 vs. $2.00 per 1M tokens) and $0.60 vs. $10.00 for output tokens (10.0x cost advantage). In terms of operational performance, Qwen 3.8 27B delivers lower response latency at 120ms TTFT (400ms faster than GPT-6.1 Sol) with 140 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 58.4% for Qwen 3.8 27B and 92.4% vs. 68.0% on GPQA Diamond.
Frequently Asked Questions & Query Fan-Out
How much does GPT-6.1 Sol cost per 1M tokens including prompt caching?
GPT-6.1 Sol costs $2.00 per million input tokens and $10.00 per million output tokens. Cached input reads cost $0.100 per 1M tokens, reducing repeated context costs by 95%.
What are GPT-6.1 Sol's coding and reasoning benchmark scores?
GPT-6.1 Sol achieves 86.4% on SWE-bench Verified, 96.8% on HumanEval coding, 92.4% on GPQA Diamond graduate-level science, 91% on MMLU-Pro, and 98.8% on MATH-500, earning an overall Inference Value Ratio (IVR) of 62.9/100.
What is the context window, TTFT latency, and token throughput of GPT-6.1 Sol?
GPT-6.1 Sol supports a 1,075,200 token context window (128,000 max output tokens) and operates at 520ms average Time to First Token (TTFT) with 135 tokens/sec output streaming throughput.
What are the primary production use cases for GPT-6.1 Sol?
Delivers near-GPT-6 Astra frontier accuracy at one-fifth the token cost with a 95% cache read discount for high-efficiency agentic coding, computer use, and enterprise workflow automation.