{
  "schema_version": "2026-05-28.v1",
  "canonical_site": "aicodingpricing.com",
  "canonical_route": "/llm-leaderboard",
  "purpose": "Source-led AI coding model leaderboard seed for frontend implementation. It supports workflow comparison and calculator prefill without creating a fake universal LLM ranking.",
  "updated_at": "2026-05-28",
  "source_policy": {
    "pricing_priority": "official_provider_pricing_first; aggregator pricing must be labeled route-specific",
    "benchmark_policy": "benchmark values stay source-specific; no composite overall score",
    "speed_policy": "only use public TTFT/tokens_per_second/latency sources; otherwise null with not_disclosed",
    "task_cost_policy": "computed by calculator from token assumptions; not stored as factual billing data in seed",
    "required_source_fields": [
      "source_name",
      "source_url",
      "source_type",
      "last_checked",
      "confidence",
      "update_policy"
    ]
  },
  "unknown_policy": {
    "numeric_unknown": null,
    "display_unknown": "not_disclosed",
    "benchmark_unknown": "not_publicly_benchmarked",
    "rule": "Do not infer missing price, context, speed, or benchmark values from nearby model names. If exact model/source alignment is not verified, mark the field as null/not_disclosed and explain in source_note."
  },
  "workflow_tags": [
    "coding_agent",
    "frontend_generation",
    "repo_refactor",
    "bug_fixing",
    "code_review",
    "test_generation",
    "chinese_coding_workflow",
    "low_cost_agent",
    "long_context"
  ],
  "models": [
    {
      "model": "claude-opus-4-5",
      "display_name": "Claude Opus 4.5",
      "provider": "Anthropic",
      "availability": "api",
      "benchmark_refs": [
        {
          "benchmark_name": "SWE-bench Verified",
          "metric_label": "% Resolved",
          "metric_value": "76.80%",
          "source_name": "SWE-bench Leaderboards",
          "source_url": "https://www.swebench.com/",
          "last_checked": "2026-05-28",
          "confidence": "medium",
          "caveat": "Captured source names the row as Claude 4.5 Opus — high reasoning; verify exact API model alias before display."
        }
      ],
      "price_input": {
        "value_usd_per_1m_tokens": 5,
        "status": "available",
        "source_name": "Anthropic Claude API pricing",
        "source_url": "https://docs.anthropic.com/en/docs/about-claude/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "price_output": {
        "value_usd_per_1m_tokens": 25,
        "status": "available",
        "source_name": "Anthropic Claude API pricing",
        "source_url": "https://docs.anthropic.com/en/docs/about-claude/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "cache_price": {
        "read_usd_per_1m_tokens": 0.5,
        "write_5m_usd_per_1m_tokens": 6.25,
        "write_1h_usd_per_1m_tokens": 10,
        "status": "available",
        "source_name": "Anthropic Claude API pricing",
        "source_url": "https://docs.anthropic.com/en/docs/about-claude/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "context": {
        "tokens": null,
        "status": "not_disclosed",
        "source_note": "Context window was not captured in the verified pricing source extract; verify from Anthropic model docs before display."
      },
      "speed_source": null,
      "best_for": ["coding_agent", "repo_refactor", "code_review"],
      "caveat": "Strong SWE-bench evidence in captured source, but expensive output pricing; do not present as universal best model.",
      "source_urls": [
        "https://www.swebench.com/",
        "https://docs.anthropic.com/en/docs/about-claude/pricing"
      ],
      "updated_at": "2026-05-28",
      "data_status": "partial",
      "source_confidence": "medium"
    },
    {
      "model": "claude-sonnet-4-5",
      "display_name": "Claude Sonnet 4.5",
      "provider": "Anthropic",
      "availability": "api",
      "benchmark_refs": [
        {
          "benchmark_name": "SWE-bench Verified",
          "metric_label": "% Resolved",
          "metric_value": "71.40%",
          "source_name": "SWE-bench Leaderboards",
          "source_url": "https://www.swebench.com/",
          "last_checked": "2026-05-28",
          "confidence": "medium",
          "caveat": "Captured source names the row as Claude 4.5 Sonnet — high reasoning; verify exact API model alias before display."
        }
      ],
      "price_input": {
        "value_usd_per_1m_tokens": 3,
        "status": "available",
        "source_name": "Anthropic Claude API pricing",
        "source_url": "https://docs.anthropic.com/en/docs/about-claude/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "price_output": {
        "value_usd_per_1m_tokens": 15,
        "status": "available",
        "source_name": "Anthropic Claude API pricing",
        "source_url": "https://docs.anthropic.com/en/docs/about-claude/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "cache_price": {
        "read_usd_per_1m_tokens": 0.3,
        "write_5m_usd_per_1m_tokens": 3.75,
        "write_1h_usd_per_1m_tokens": 6,
        "status": "available",
        "source_name": "Anthropic Claude API pricing",
        "source_url": "https://docs.anthropic.com/en/docs/about-claude/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "context": {
        "tokens": null,
        "status": "not_disclosed",
        "source_note": "Context window was not captured in the verified pricing source extract; verify from Anthropic model docs before display."
      },
      "speed_source": null,
      "best_for": ["coding_agent", "frontend_generation", "repo_refactor", "test_generation"],
      "caveat": "Good candidate for default coding workflow shortlist, but scenario label must cite benchmark and price fields rather than claim overall superiority.",
      "source_urls": [
        "https://www.swebench.com/",
        "https://docs.anthropic.com/en/docs/about-claude/pricing"
      ],
      "updated_at": "2026-05-28",
      "data_status": "partial",
      "source_confidence": "medium"
    },
    {
      "model": "claude-haiku-4-5",
      "display_name": "Claude Haiku 4.5",
      "provider": "Anthropic",
      "availability": "api",
      "benchmark_refs": [
        {
          "benchmark_name": "SWE-bench Verified",
          "metric_label": "% Resolved",
          "metric_value": "66.60%",
          "source_name": "SWE-bench Leaderboards",
          "source_url": "https://www.swebench.com/",
          "last_checked": "2026-05-28",
          "confidence": "medium",
          "caveat": "Captured source names the row as Claude 4.5 Haiku — high reasoning; verify exact API model alias before display."
        }
      ],
      "price_input": {
        "value_usd_per_1m_tokens": 1,
        "status": "available",
        "source_name": "Anthropic Claude API pricing",
        "source_url": "https://docs.anthropic.com/en/docs/about-claude/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "price_output": {
        "value_usd_per_1m_tokens": 5,
        "status": "available",
        "source_name": "Anthropic Claude API pricing",
        "source_url": "https://docs.anthropic.com/en/docs/about-claude/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "cache_price": {
        "read_usd_per_1m_tokens": 0.1,
        "write_5m_usd_per_1m_tokens": 1.25,
        "write_1h_usd_per_1m_tokens": 2,
        "status": "available",
        "source_name": "Anthropic Claude API pricing",
        "source_url": "https://docs.anthropic.com/en/docs/about-claude/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "context": {
        "tokens": null,
        "status": "not_disclosed",
        "source_note": "Context window was not captured in the verified pricing source extract; verify from Anthropic model docs before display."
      },
      "speed_source": null,
      "best_for": ["low_cost_agent", "test_generation", "bug_fixing"],
      "caveat": "Lower token price does not guarantee lower task cost if retry rate rises; calculator must expose retry assumptions.",
      "source_urls": [
        "https://www.swebench.com/",
        "https://docs.anthropic.com/en/docs/about-claude/pricing"
      ],
      "updated_at": "2026-05-28",
      "data_status": "partial",
      "source_confidence": "medium"
    },
    {
      "model": "gpt-5-mini",
      "display_name": "GPT-5 Mini",
      "provider": "OpenAI",
      "availability": "api",
      "benchmark_refs": [
        {
          "benchmark_name": "SWE-bench Verified",
          "metric_label": "% Resolved",
          "metric_value": "56.20%",
          "source_name": "SWE-bench Leaderboards",
          "source_url": "https://www.swebench.com/",
          "last_checked": "2026-05-28",
          "confidence": "medium",
          "caveat": "Captured source names GPT-5 Mini; exact official pricing row for this model was not verified in captured OpenAI pricing extract."
        }
      ],
      "price_input": {
        "value_usd_per_1m_tokens": null,
        "status": "not_disclosed",
        "source_name": "OpenAI API pricing",
        "source_url": "https://openai.com/api/pricing/",
        "last_checked": "2026-05-28",
        "confidence": "low",
        "source_note": "OpenAI pricing extract captured GPT-5.4 mini at $0.75 input / $4.50 output, but not exact GPT-5 Mini. Do not copy that value onto this row without exact alias verification."
      },
      "price_output": {
        "value_usd_per_1m_tokens": null,
        "status": "not_disclosed",
        "source_name": "OpenAI API pricing",
        "source_url": "https://openai.com/api/pricing/",
        "last_checked": "2026-05-28",
        "confidence": "low"
      },
      "cache_price": {
        "read_usd_per_1m_tokens": null,
        "write_5m_usd_per_1m_tokens": null,
        "write_1h_usd_per_1m_tokens": null,
        "status": "not_disclosed"
      },
      "context": {
        "tokens": null,
        "status": "not_disclosed",
        "source_note": "Not verified from exact model docs in this seed."
      },
      "speed_source": null,
      "best_for": ["low_cost_agent", "test_generation"],
      "caveat": "Include only as benchmark-backed partial row until exact OpenAI API price and model alias are verified.",
      "source_urls": [
        "https://www.swebench.com/",
        "https://openai.com/api/pricing/"
      ],
      "updated_at": "2026-05-28",
      "data_status": "partial",
      "source_confidence": "low"
    },
    {
      "model": "gemini-3-flash-high-reasoning",
      "display_name": "Gemini 3 Flash — high reasoning",
      "provider": "Google",
      "availability": "api",
      "benchmark_refs": [
        {
          "benchmark_name": "SWE-bench Verified",
          "metric_label": "% Resolved",
          "metric_value": "75.80%",
          "source_name": "SWE-bench Leaderboards",
          "source_url": "https://www.swebench.com/",
          "last_checked": "2026-05-28",
          "confidence": "medium",
          "caveat": "Captured benchmark row is Gemini 3 Flash — high reasoning; exact Google API pricing row for this exact model alias was not captured."
        }
      ],
      "price_input": {
        "value_usd_per_1m_tokens": null,
        "status": "not_disclosed",
        "source_name": "Gemini Developer API pricing",
        "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
        "last_checked": "2026-05-28",
        "confidence": "low",
        "source_note": "Extract captured Gemini 3.5 Flash and Gemini 3.1 Pro Preview pricing, not exact Gemini 3 Flash."
      },
      "price_output": {
        "value_usd_per_1m_tokens": null,
        "status": "not_disclosed",
        "source_name": "Gemini Developer API pricing",
        "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
        "last_checked": "2026-05-28",
        "confidence": "low"
      },
      "cache_price": {
        "read_usd_per_1m_tokens": null,
        "write_5m_usd_per_1m_tokens": null,
        "write_1h_usd_per_1m_tokens": null,
        "status": "not_disclosed"
      },
      "context": {
        "tokens": null,
        "status": "not_disclosed"
      },
      "speed_source": null,
      "best_for": ["coding_agent", "long_context", "frontend_generation"],
      "caveat": "Strong captured SWE-bench result, but price/context must remain unknown until exact Gemini model docs are mapped.",
      "source_urls": [
        "https://www.swebench.com/",
        "https://ai.google.dev/gemini-api/docs/pricing"
      ],
      "updated_at": "2026-05-28",
      "data_status": "partial",
      "source_confidence": "low"
    },
    {
      "model": "deepseek-v4-flash",
      "display_name": "DeepSeek V4 Flash",
      "provider": "DeepSeek",
      "availability": "api",
      "benchmark_refs": [
        {
          "benchmark_name": "SWE-bench / Aider",
          "metric_label": "exact public benchmark",
          "metric_value": "not_publicly_benchmarked",
          "source_name": "DeepSeek API Docs + public benchmark sources checked",
          "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
          "last_checked": "2026-05-28",
          "confidence": "low",
          "caveat": "Captured benchmark sources mention DeepSeek V3.2 / R1 variants, not exact DeepSeek V4 Flash."
        }
      ],
      "price_input": {
        "value_usd_per_1m_tokens": 0.14,
        "status": "available",
        "source_name": "DeepSeek API Docs — Models & Pricing",
        "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high",
        "source_note": "Cache-miss input price. Cache-hit price is modeled under cache_price."
      },
      "price_output": {
        "value_usd_per_1m_tokens": 0.28,
        "status": "available",
        "source_name": "DeepSeek API Docs — Models & Pricing",
        "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "cache_price": {
        "read_usd_per_1m_tokens": 0.0028,
        "write_5m_usd_per_1m_tokens": null,
        "write_1h_usd_per_1m_tokens": null,
        "status": "partial",
        "source_name": "DeepSeek API Docs — Models & Pricing",
        "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "context": {
        "tokens": 1000000,
        "status": "available",
        "source_name": "DeepSeek API Docs — Models & Pricing",
        "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "speed_source": null,
      "best_for": ["low_cost_agent", "chinese_coding_workflow", "long_context"],
      "caveat": "Excellent token price and context signal, but exact public coding benchmark row for V4 Flash was not captured; mark coding evidence as incomplete.",
      "source_urls": [
        "https://api-docs.deepseek.com/quick_start/pricing",
        "https://www.swebench.com/",
        "https://aider.chat/docs/leaderboards/"
      ],
      "updated_at": "2026-05-28",
      "data_status": "partial",
      "source_confidence": "medium"
    },
    {
      "model": "deepseek-v4-pro",
      "display_name": "DeepSeek V4 Pro",
      "provider": "DeepSeek",
      "availability": "api",
      "benchmark_refs": [
        {
          "benchmark_name": "SWE-bench / Aider",
          "metric_label": "exact public benchmark",
          "metric_value": "not_publicly_benchmarked",
          "source_name": "DeepSeek API Docs + public benchmark sources checked",
          "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
          "last_checked": "2026-05-28",
          "confidence": "low",
          "caveat": "Captured benchmark sources mention DeepSeek V3.2 / R1 variants, not exact DeepSeek V4 Pro."
        }
      ],
      "price_input": {
        "value_usd_per_1m_tokens": 0.435,
        "status": "available",
        "source_name": "DeepSeek API Docs — Models & Pricing",
        "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high",
        "source_note": "Promotional/current cache-miss input price captured from source; source notes promotion timing and future adjustment."
      },
      "price_output": {
        "value_usd_per_1m_tokens": 0.87,
        "status": "available",
        "source_name": "DeepSeek API Docs — Models & Pricing",
        "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "cache_price": {
        "read_usd_per_1m_tokens": 0.003625,
        "write_5m_usd_per_1m_tokens": null,
        "write_1h_usd_per_1m_tokens": null,
        "status": "partial",
        "source_name": "DeepSeek API Docs — Models & Pricing",
        "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "context": {
        "tokens": 1000000,
        "status": "available",
        "source_name": "DeepSeek API Docs — Models & Pricing",
        "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
        "last_checked": "2026-05-28",
        "confidence": "high"
      },
      "speed_source": null,
      "best_for": ["chinese_coding_workflow", "long_context", "repo_refactor"],
      "caveat": "Pricing/context are source-backed; coding benchmark evidence for the exact V4 Pro model still needs source verification.",
      "source_urls": [
        "https://api-docs.deepseek.com/quick_start/pricing",
        "https://www.swebench.com/",
        "https://aider.chat/docs/leaderboards/"
      ],
      "updated_at": "2026-05-28",
      "data_status": "partial",
      "source_confidence": "medium"
    },
    {
      "model": "kimi-k2-5-high-reasoning",
      "display_name": "Kimi K2.5 — high reasoning",
      "provider": "Moonshot AI / Kimi",
      "availability": "api",
      "benchmark_refs": [
        {
          "benchmark_name": "SWE-bench Verified",
          "metric_label": "% Resolved",
          "metric_value": "70.80%",
          "source_name": "SWE-bench Leaderboards",
          "source_url": "https://www.swebench.com/",
          "last_checked": "2026-05-28",
          "confidence": "medium",
          "caveat": "Captured source names Kimi K2.5 — high reasoning."
        }
      ],
      "price_input": {
        "value_usd_per_1m_tokens": null,
        "status": "not_disclosed",
        "source_name": "Kimi API Platform pricing index",
        "source_url": "https://platform.moonshot.ai/docs/pricing",
        "last_checked": "2026-05-28",
        "confidence": "low",
        "source_note": "Pricing index was reachable, but exact Kimi K2.5 price page/value was not captured in this seed."
      },
      "price_output": {
        "value_usd_per_1m_tokens": null,
        "status": "not_disclosed",
        "source_name": "Kimi API Platform pricing index",
        "source_url": "https://platform.moonshot.ai/docs/pricing",
        "last_checked": "2026-05-28",
        "confidence": "low"
      },
      "cache_price": {
        "read_usd_per_1m_tokens": null,
        "write_5m_usd_per_1m_tokens": null,
        "write_1h_usd_per_1m_tokens": null,
        "status": "not_disclosed"
      },
      "context": {
        "tokens": null,
        "status": "not_disclosed",
        "source_note": "Kimi pricing index mentions long-context coding stability for K2.6 but does not provide a verified numeric context value in captured content."
      },
      "speed_source": null,
      "best_for": ["chinese_coding_workflow", "coding_agent", "repo_refactor"],
      "caveat": "Useful Chinese coding workflow candidate, but price/context must remain unknown until exact Moonshot pricing/model docs are captured.",
      "source_urls": [
        "https://www.swebench.com/",
        "https://platform.moonshot.ai/docs/pricing"
      ],
      "updated_at": "2026-05-28",
      "data_status": "partial",
      "source_confidence": "low"
    },
    {
      "model": "qwen3-235b-a22b",
      "display_name": "Qwen3 235B A22B",
      "provider": "Alibaba Cloud / Qwen",
      "availability": "api",
      "benchmark_refs": [
        {
          "benchmark_name": "Aider polyglot coding benchmark",
          "metric_label": "Percent Correct",
          "metric_value": "59.6%",
          "source_name": "Aider LLM Leaderboards",
          "source_url": "https://aider.chat/docs/leaderboards/",
          "last_checked": "2026-05-28",
          "confidence": "medium",
          "caveat": "Captured source row: Qwen3 235B A22B diff, no think, Alibaba API."
        }
      ],
      "price_input": {
        "value_usd_per_1m_tokens": null,
        "status": "not_disclosed",
        "source_name": "Alibaba Cloud Model Studio pricing search result",
        "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
        "last_checked": "2026-05-28",
        "confidence": "low",
        "source_note": "Official pricing page was discovered, but exact Qwen3 235B A22B pricing was not extracted/verified in this seed."
      },
      "price_output": {
        "value_usd_per_1m_tokens": null,
        "status": "not_disclosed",
        "source_name": "Alibaba Cloud Model Studio pricing search result",
        "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
        "last_checked": "2026-05-28",
        "confidence": "low"
      },
      "cache_price": {
        "read_usd_per_1m_tokens": null,
        "write_5m_usd_per_1m_tokens": null,
        "write_1h_usd_per_1m_tokens": null,
        "status": "not_disclosed"
      },
      "context": {
        "tokens": null,
        "status": "not_disclosed"
      },
      "speed_source": null,
      "best_for": ["chinese_coding_workflow", "low_cost_agent"],
      "caveat": "Benchmark-backed partial row only. Do not show price until exact Alibaba Cloud model pricing is captured.",
      "source_urls": [
        "https://aider.chat/docs/leaderboards/",
        "https://www.alibabacloud.com/help/en/model-studio/model-pricing"
      ],
      "updated_at": "2026-05-28",
      "data_status": "partial",
      "source_confidence": "low"
    }
  ]
}