{
  "dataset": "AI Model Pricing Comparison",
  "source": "https://compareai.today",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "attribution": "compareai.today",
  "updated": "2026-10-10",
  "version": "2026-10",
  "unit": "USD per million tokens (MTok)",
  "models": [
    {
      "id": "fable-5.1",
      "name": "Claude Fable 5.1",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "tier": "Premium",
      "inputPerMTok": 10,
      "outputPerMTok": 50,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "Current top tier (Sep 1, 2026), replacing Fable 5 at the same $10/$50. Cache reads cut 75% to $0.25/MTok (0.025x input, against 0.05x on Opus 5.5 and Sonnet 5.5 and 0.1x on the other Claude models). 128K max output; thinking is always on."
    },
    {
      "id": "fable-5",
      "name": "Claude Fable 5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "tier": "Premium",
      "inputPerMTok": 10,
      "outputPerMTok": 50,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "Previous top tier (June 9, 2026), now legacy after Fable 5.1 replaced it at the same $10/$50. Cached read $1.00, four times Fable 5.1's rate."
    },
    {
      "id": "opus-5.5",
      "name": "Claude Opus 5.5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "tier": "Premium",
      "inputPerMTok": 4,
      "outputPerMTok": 20,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "New Opus flagship (Sep 22, 2026), 20% cheaper than Opus 5 on both input and output. Cache reads $0.20/MTok (0.05x input, half the standard Claude multiplier). Fast mode $8/$40. 128K max output; thinking is always on, default effort medium."
    },
    {
      "id": "opus-5",
      "name": "Claude Opus 5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "tier": "Premium",
      "inputPerMTok": 5,
      "outputPerMTok": 25,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "Previous Opus flagship (July 24, 2026), superseded by Opus 5.5 at $4/$20. Launched at the same $5/$25 as Opus 4.8. Cached read $0.50. Fast mode $10/$50. Prompt-cache minimum 512 tokens."
    },
    {
      "id": "opus-4.8",
      "name": "Claude Opus 4.8",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "tier": "Premium",
      "inputPerMTok": 5,
      "outputPerMTok": 25,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "Earlier Opus flagship (May 2026), superseded by Opus 5 at the same $5/$25 price and now legacy. Cached read $0.50. Fast mode $10/$50."
    },
    {
      "id": "opus-4.7",
      "name": "Claude Opus 4.7",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "tier": "Premium",
      "inputPerMTok": 5,
      "outputPerMTok": 25,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "Older Opus release. The 4.7-generation tokenizer bills roughly 30% more tokens than 4.6 for the same text."
    },
    {
      "id": "sonnet-5.5",
      "name": "Claude Sonnet 5.5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "tier": "Standard",
      "inputPerMTok": 2,
      "outputPerMTok": 10,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "Standard flagship (Sep 28, 2026), replacing Sonnet 5 at the same $2/$10. Cached read $0.10 (0.05x input, the same multiplier as Opus 5.5) since Oct 7, 2026, when Anthropic halved it from $0.20; cache writes unchanged at $2.50 (5m) and $4.00 (1h). 128K max output (300K on the Batch API, beta). Same tokenizer as Sonnet 5. Adaptive thinking, default effort high. No fast mode."
    },
    {
      "id": "sonnet-5",
      "name": "Claude Sonnet 5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "tier": "Standard",
      "inputPerMTok": 2,
      "outputPerMTok": 10,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "Previous Standard flagship, now legacy after Sonnet 5.5 replaced it on Sep 28, 2026 at the same $2/$10. That launch rate became the standard price on Aug 10, 2026, when Anthropic cancelled the scheduled Sep 1 rise to $3/$15. Cached read $0.20, 5m cache write $2.50, 1h cache write $4.00. New tokenizer bills ~30% more tokens than Sonnet 4.6 (1.0-1.35x). Full 1M context at standard rates."
    },
    {
      "id": "sonnet-4.6",
      "name": "Claude Sonnet 4.6",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "tier": "Standard",
      "inputPerMTok": 3,
      "outputPerMTok": 15,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "Older Sonnet, superseded by Sonnet 5 and now Sonnet 5.5. Still strong for production workloads, and on the older tokenizer, so the same text counts as fewer tokens than on Sonnet 5.x."
    },
    {
      "id": "haiku-5.5",
      "name": "Claude Haiku 5.5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "tier": "Budget",
      "inputPerMTok": 0.1,
      "outputPerMTok": 0.5,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "Budget flagship (Oct 7, 2026), replacing Haiku 4.5 at a tenth of its price. Rates shown are for prompts up to 100K tokens: a prompt over 100K bills the whole request at $0.50/$2.50, and cache reads and writes count toward the threshold. Cached read $0.01 (0.1x input), 5m cache write $0.125, 1h cache write $0.20, all 5x above 100K. Batch $0.05/$0.25 ($0.25/$1.25 above 100K). Ties GPT-6 Luna's $0.10/$0.50 on short prompts. Newer tokenizer counts the same text as ~30% more tokens than Haiku 4.5. 128K max output (300K on the Batch API, beta). Adaptive thinking, default effort medium."
    },
    {
      "id": "haiku-4.5",
      "name": "Claude Haiku 4.5",
      "provider": "anthropic",
      "providerName": "Anthropic",
      "tier": "Budget",
      "inputPerMTok": 1,
      "outputPerMTok": 5,
      "contextWindow": "200k tokens",
      "batchDiscount": true,
      "notes": "Previous budget model, now legacy after Haiku 5.5 replaced it on Oct 7, 2026. Haiku 5.5 is cheaper at every prompt length: a tenth of the price up to 100K tokens and half above. Cached read $0.10, 5m cache write $1.25, 1h cache write $2.00. 64K max output. On the older tokenizer, so the same text counts as fewer tokens than on Haiku 5.5."
    },
    {
      "id": "gpt-6-astra",
      "name": "GPT-6 Astra",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Premium",
      "inputPerMTok": 10,
      "outputPerMTok": 50,
      "contextWindow": "1.05M",
      "batchDiscount": true,
      "notes": "OpenAI's most capable model (Sep 3, 2026). Cached read $1.00, cache write $12.50 (1.25x input). $20/$75 above 272K. Fast mode bills 2x, and the Ultrafast tier (late Sep 2026) bills 6x ($60/$300). 128K max output. No 'none' reasoning effort or custom temperature/top_p, and tool calling requires the Responses API."
    },
    {
      "id": "gpt-6.1-sol",
      "name": "GPT-6.1 Sol",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Standard",
      "inputPerMTok": 2,
      "outputPerMTok": 10,
      "contextWindow": "1.05M",
      "batchDiscount": true,
      "notes": "Mid tier (Sep 29, 2026), which OpenAI pitches as near-Astra performance at a fifth of the price. Replaced GPT-6 Sol (Sep 22, also $2/$10) a week after launch. Cached input $0.10, 5% of input where most OpenAI models charge 10%. Cache write $2.50. $4/$15 above 272K. 128K max output."
    },
    {
      "id": "gpt-6-luna",
      "name": "GPT-6 Luna",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Budget",
      "inputPerMTok": 0.1,
      "outputPerMTok": 0.5,
      "contextWindow": "1.05M",
      "batchDiscount": true,
      "notes": "Budget tier (Sep 22, 2026) and OpenAI's cheapest current-generation model, half the price of GPT-5.6 Luna on input. OpenAI's named replacement for GPT-5.4 Nano. Cached input $0.01, cache write $0.125. $0.20/$0.75 above 272K. 128K max output. Claude Haiku 5.5 (Oct 7) matches $0.10/$0.50, but only on prompts up to 100K tokens."
    },
    {
      "id": "gpt-5.6-sol",
      "name": "GPT-5.6 Sol",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Premium",
      "inputPerMTok": 4,
      "outputPerMTok": 20,
      "contextWindow": "1.05M",
      "batchDiscount": true,
      "notes": "GA Jul 9, 2026. GPT-6.1 Sol ($2/$10) now sits between it and GPT-6 Astra at half its promotional price. Promotional $4/$20 since Aug 21, 2026 (list $5/$30), which OpenAI says runs at least through Nov 21, 2026. Cached read $0.40, cache write $5.00 (1.25x input). 2x in/1.5x out above 272K."
    },
    {
      "id": "gpt-5.6-terra",
      "name": "GPT-5.6 Terra",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Standard",
      "inputPerMTok": 2,
      "outputPerMTok": 12,
      "contextWindow": "1.05M",
      "batchDiscount": true,
      "notes": "Previous mid tier (GA Jul 9, 2026). Cut 20% from $2.50/$15.00 on Jul 30, 2026. GPT-6.1 Sol now matches its input price and undercuts it on output ($10 vs $12). Cached read $0.20, cache write $2.50 (1.25x input). 2x in/1.5x out above 272K."
    },
    {
      "id": "gpt-5.6-luna",
      "name": "GPT-5.6 Luna",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Budget",
      "inputPerMTok": 0.2,
      "outputPerMTok": 1.2,
      "contextWindow": "1.05M",
      "batchDiscount": true,
      "notes": "Previous budget tier (GA Jul 9, 2026). Cut 80% from $1.00/$6.00 on Jul 30, 2026. GPT-6 Luna ($0.10/$0.50, Sep 22) now undercuts it on both input and output. Cached read $0.02, cache write $0.25 (1.25x input). 2x in/1.5x out above 272K."
    },
    {
      "id": "gpt-5.5",
      "name": "GPT-5.5",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Premium",
      "inputPerMTok": 5,
      "outputPerMTok": 30,
      "contextWindow": "1.05M",
      "batchDiscount": true,
      "notes": "Earlier flagship (Apr 2026). GPT-5.6 Sol's promotional rate and GPT-6.1 Sol ($2/$10) both undercut it. Cached input $0.50. 2x in/1.5x out above 272K."
    },
    {
      "id": "gpt-5.5-pro",
      "name": "GPT-5.5 Pro",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Premium",
      "inputPerMTok": 30,
      "outputPerMTok": 180,
      "contextWindow": "1.05M",
      "batchDiscount": true,
      "notes": "Highest-precision flagship variant (GA). Most expensive model tracked."
    },
    {
      "id": "gpt-5.4",
      "name": "GPT-5.4",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Premium",
      "inputPerMTok": 2.5,
      "outputPerMTok": 15,
      "contextWindow": "1.05M",
      "batchDiscount": true,
      "notes": "Previous flagship. Cached input $0.25. 2x in/1.5x out above 272K."
    },
    {
      "id": "gpt-5.4-mini",
      "name": "GPT-5.4 Mini",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Standard",
      "inputPerMTok": 0.75,
      "outputPerMTok": 4.5,
      "contextWindow": "400K",
      "batchDiscount": true,
      "notes": "Balanced performance and cost."
    },
    {
      "id": "gpt-5.4-nano",
      "name": "GPT-5.4 Nano",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Budget",
      "inputPerMTok": 0.2,
      "outputPerMTok": 1.25,
      "contextWindow": "400K",
      "batchDiscount": true,
      "notes": "Cheapest GPT-5.4 model. Deprecated Oct 1, 2026: API shutdown Apr 1, 2027, with GPT-6 Luna ($0.10/$0.50) as OpenAI's recommended replacement."
    },
    {
      "id": "o4-mini",
      "name": "o4-mini",
      "provider": "openai",
      "providerName": "OpenAI",
      "tier": "Standard",
      "inputPerMTok": 1.1,
      "outputPerMTok": 4.4,
      "contextWindow": "200K",
      "batchDiscount": true,
      "notes": "Reasoning model. Cached input $0.275. Deprecated — API shutdown Oct 23, 2026; OpenAI points migrations at GPT-5.6 Terra."
    },
    {
      "id": "gemini-3.1-pro",
      "name": "Gemini 3.1 Pro Preview",
      "provider": "google",
      "providerName": "Google",
      "tier": "Premium",
      "inputPerMTok": 2,
      "outputPerMTok": 12,
      "contextWindow": "1M",
      "batchDiscount": true,
      "notes": "Preview release. 1M context. $4/$18 above 200K tokens. Cached input $0.20."
    },
    {
      "id": "gemini-3.8-flash",
      "name": "Gemini 3.8 Flash",
      "provider": "google",
      "providerName": "Google",
      "tier": "Standard",
      "inputPerMTok": 0.75,
      "outputPerMTok": 3.75,
      "contextWindow": "1M",
      "batchDiscount": true,
      "notes": "Newest GA Flash (Sep 2, 2026), Google's most intelligent Flash model. Introductory $0.75/$3.75 through Dec 31, 2026; list price $1.50/$7.50 from Jan 1, 2027. Cached input $0.075 (list $0.15). Google warns it can use more tokens on long, complex tasks by design."
    },
    {
      "id": "gemini-3.6-flash",
      "name": "Gemini 3.6 Flash",
      "provider": "google",
      "providerName": "Google",
      "tier": "Standard",
      "inputPerMTok": 0.75,
      "outputPerMTok": 3.75,
      "contextWindow": "1M",
      "batchDiscount": true,
      "notes": "Previous GA Flash (July 21, 2026), superseded by 3.7 and 3.8 Flash. Halved to an introductory $0.75/$3.75 in mid-August 2026, running through Dec 31, 2026; the $1.50/$7.50 list price returns Jan 1, 2027. Cached input $0.075 (list $0.15)."
    },
    {
      "id": "gemini-3-flash",
      "name": "Gemini 3 Flash Preview",
      "provider": "google",
      "providerName": "Google",
      "tier": "Standard",
      "inputPerMTok": 0.5,
      "outputPerMTok": 3,
      "contextWindow": "1M",
      "batchDiscount": true,
      "notes": "Legacy preview (Dec 2025). Google names 3.6 Flash as its replacement; no shutdown date announced. Cached input $0.05."
    },
    {
      "id": "gemini-3.5-flash",
      "name": "Gemini 3.5 Flash",
      "provider": "google",
      "providerName": "Google",
      "tier": "Standard",
      "inputPerMTok": 1.5,
      "outputPerMTok": 9,
      "contextWindow": "1M",
      "batchDiscount": true,
      "notes": "Legacy GA workhorse (Google I/O, May 2026). Now twice the price of the newer 3.6-3.8 Flash models while their introductory rates last. Cached input $0.15."
    },
    {
      "id": "gemini-3.5-flash-lite",
      "name": "Gemini 3.5 Flash-Lite",
      "provider": "google",
      "providerName": "Google",
      "tier": "Budget",
      "inputPerMTok": 0.3,
      "outputPerMTok": 2.5,
      "contextWindow": "1M",
      "batchDiscount": true,
      "notes": "Newest Flash-Lite (GA, July 21, 2026). Higher-capability tier above 3.1 Flash-Lite. Cached input $0.03."
    },
    {
      "id": "gemini-3.1-flash-lite",
      "name": "Gemini 3.1 Flash-Lite",
      "provider": "google",
      "providerName": "Google",
      "tier": "Budget",
      "inputPerMTok": 0.25,
      "outputPerMTok": 1.5,
      "contextWindow": "1M",
      "batchDiscount": true,
      "notes": "Previous Flash-Lite (GA, May 2026), superseded by 3.5 Flash-Lite. Shuts down May 7, 2027. Native multimodal input."
    },
    {
      "id": "gemini-2.5-pro",
      "name": "Gemini 2.5 Pro",
      "provider": "google",
      "providerName": "Google",
      "tier": "Premium",
      "inputPerMTok": 1.25,
      "outputPerMTok": 10,
      "contextWindow": "1M",
      "batchDiscount": true,
      "notes": "Earlier GA flagship. 1M context. $2.50/$15 above 200K tokens. Cached input $0.125. Since Sep 18, 2026 Google limits the 2.5 models to developers who have used them before: they are not deprecated and keep serving existing users, but new projects should start on 3.5 Flash-Lite or 3.8 Flash."
    },
    {
      "id": "gemini-2.5-flash",
      "name": "Gemini 2.5 Flash",
      "provider": "google",
      "providerName": "Google",
      "tier": "Standard",
      "inputPerMTok": 0.3,
      "outputPerMTok": 2.5,
      "contextWindow": "1M",
      "batchDiscount": true,
      "notes": "Output price includes thinking tokens. Cached input $0.03. Since Sep 18, 2026 Google limits the 2.5 models to developers who have used them before: they are not deprecated and keep serving existing users, but new projects should start on 3.5 Flash-Lite or 3.8 Flash."
    },
    {
      "id": "gemini-2.5-flash-lite",
      "name": "Gemini 2.5 Flash-Lite",
      "provider": "google",
      "providerName": "Google",
      "tier": "Budget",
      "inputPerMTok": 0.1,
      "outputPerMTok": 0.4,
      "contextWindow": "1M",
      "batchDiscount": true,
      "notes": "Lightweight 2.5 variant and the cheapest first-party rate tracked, but closed to new users. Native multimodal input. Cached input $0.01. Since Sep 18, 2026 Google limits the 2.5 models to developers who have used them before: they are not deprecated and keep serving existing users, but new projects should start on 3.5 Flash-Lite or 3.8 Flash."
    },
    {
      "id": "grok-4.7",
      "name": "Grok 4.7",
      "provider": "xai",
      "providerName": "xAI",
      "tier": "Premium",
      "inputPerMTok": 2,
      "outputPerMTok": 6,
      "contextWindow": "500K tokens",
      "batchDiscount": false,
      "notes": "Flagship (Sep 21, 2026), xAI's frontier model for coding, agentic tasks and knowledge work. Same $2/$6 and $0.50 cached input as Grok 4.6. $4/$12 above 200K prompt tokens. No batch discount and no output limit. Reasoning effort low to xhigh, default high. Served from US regions only."
    },
    {
      "id": "grok-4.6",
      "name": "Grok 4.6",
      "provider": "xai",
      "providerName": "xAI",
      "tier": "Premium",
      "inputPerMTok": 2,
      "outputPerMTok": 6,
      "contextWindow": "500K tokens",
      "batchDiscount": false,
      "notes": "Previous flagship (Aug 12, 2026), superseded by Grok 4.7 at the same $2/$6. Same token rates as Grok 4.5, but cached input is $0.50 (4.5 charges $0.30). $4/$12 above 200K prompt tokens. No batch discount. Served from US regions only."
    },
    {
      "id": "grok-4.5",
      "name": "Grok 4.5",
      "provider": "xai",
      "providerName": "xAI",
      "tier": "Premium",
      "inputPerMTok": 2,
      "outputPerMTok": 6,
      "contextWindow": "500K tokens",
      "batchDiscount": false,
      "notes": "Earlier flagship (Jul 8, 2026), superseded by Grok 4.6 and then 4.7, all at the same $2/$6. $4/$12 above 200K prompt tokens. Cached input $0.30. No batch discount. Served from US regions only."
    },
    {
      "id": "grok-4.3",
      "name": "Grok 4.3",
      "provider": "xai",
      "providerName": "xAI",
      "tier": "Premium",
      "inputPerMTok": 1.25,
      "outputPerMTok": 2.5,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "Earlier flagship (May 2026). Cheaper than Grok 4.5 and 4.6 with a larger 1M context. $2.50/$5.00 above 200K prompt tokens. Cached input $0.20. Batch 20% off."
    },
    {
      "id": "grok-4.20",
      "name": "Grok 4.20",
      "provider": "xai",
      "providerName": "xAI",
      "tier": "Standard",
      "inputPerMTok": 1.25,
      "outputPerMTok": 2.5,
      "contextWindow": "1M tokens",
      "batchDiscount": true,
      "notes": "Repriced to match 4.3, including $2.50/$5.00 above 200K prompt tokens. Lowest hallucination rate; reasoning and multi-agent variants."
    },
    {
      "id": "grok-build-0.1",
      "name": "Grok Build 0.1",
      "provider": "xai",
      "providerName": "xAI",
      "tier": "Budget",
      "inputPerMTok": 1,
      "outputPerMTok": 2,
      "contextWindow": "256K tokens",
      "batchDiscount": false,
      "notes": "No batch discount. Coding specialist. $2.00/$4.00 above 200K prompt tokens. grok-code-fast-1 is now an alias for this model. Cached input $0.20."
    },
    {
      "id": "sonar",
      "name": "Sonar",
      "provider": "perplexity",
      "providerName": "Perplexity AI",
      "tier": "Budget",
      "inputPerMTok": 0.25,
      "outputPerMTok": 2.5,
      "contextWindow": "N/A",
      "batchDiscount": false,
      "notes": "Perplexity's own model, now billed through its Agent API (cached input $0.0625). Web search is a separate tool charge of $2.50 per 1,000 calls ($1 with Fast Search), replacing the old per-request fee. Sonar Chat Completions support ended Sep 27, 2026: synchronous and streaming calls are rewritten as Agent API requests, and asynchronous calls no longer work. Sonar Pro, Reasoning Pro and Deep Research map to Agent API presets that bill the underlying OpenAI or Anthropic model's rates."
    },
    {
      "id": "azure-gpt-6-astra",
      "name": "Azure GPT-6 Astra",
      "provider": "azure",
      "providerName": "Microsoft Azure",
      "tier": "Premium",
      "inputPerMTok": 10,
      "outputPerMTok": 50,
      "contextWindow": "1.05M",
      "batchDiscount": false,
      "notes": "Foundry Global Standard (GA Sep 3, 2026), matching OpenAI direct. Cached input $1.00, cache write $12.50. $20/$75 above 272K. Data Zone deployments cost 10-20% more ($11/$55 to $12/$60, depending on zone). No batch pricing on Azure yet."
    },
    {
      "id": "azure-gpt-5.5",
      "name": "Azure GPT-5.5",
      "provider": "azure",
      "providerName": "Microsoft Azure",
      "tier": "Premium",
      "inputPerMTok": 5,
      "outputPerMTok": 30,
      "contextWindow": "1.05M",
      "batchDiscount": true,
      "notes": "Azure-hosted GPT-5.5 (Foundry Global Standard). Cached input $0.50. 2x in/1.5x out above 272K."
    },
    {
      "id": "azure-gpt-5.4",
      "name": "Azure GPT-5.4",
      "provider": "azure",
      "providerName": "Microsoft Azure",
      "tier": "Premium",
      "inputPerMTok": 2.5,
      "outputPerMTok": 15,
      "contextWindow": "1.05M",
      "batchDiscount": true,
      "notes": "Foundry Global Standard. $5/$22.50 above 272K. Cached input $0.25."
    },
    {
      "id": "azure-gpt-5.2",
      "name": "Azure GPT-5.2",
      "provider": "azure",
      "providerName": "Microsoft Azure",
      "tier": "Standard",
      "inputPerMTok": 1.75,
      "outputPerMTok": 14,
      "contextWindow": "400K",
      "batchDiscount": true,
      "notes": "Previous Azure flagship."
    },
    {
      "id": "azure-gpt-5-mini",
      "name": "Azure GPT-5 Mini",
      "provider": "azure",
      "providerName": "Microsoft Azure",
      "tier": "Budget",
      "inputPerMTok": 0.25,
      "outputPerMTok": 2,
      "contextWindow": "400K",
      "batchDiscount": true,
      "notes": "Budget-friendly Azure option."
    },
    {
      "id": "azure-o4-mini",
      "name": "Azure o4-mini",
      "provider": "azure",
      "providerName": "Microsoft Azure",
      "tier": "Standard",
      "inputPerMTok": 1.1,
      "outputPerMTok": 4.4,
      "contextWindow": "200K",
      "batchDiscount": true,
      "notes": "Reasoning model on Azure. Deprecated: Azure retires it on Nov 19, 2026 (a month after OpenAI's own API shutdown on Oct 23), with GPT-5.6 Terra as the recommended replacement."
    },
    {
      "id": "mistral-large",
      "name": "Mistral Large 3",
      "provider": "mistral",
      "providerName": "Mistral AI",
      "tier": "Premium",
      "inputPerMTok": 0.5,
      "outputPerMTok": 1.5,
      "contextWindow": "256K",
      "batchDiscount": true,
      "notes": "Flagship 675B open-weight MoE. Context expanded from 32K to 256K."
    },
    {
      "id": "mistral-medium-3.5",
      "name": "Mistral Medium 3.5",
      "provider": "mistral",
      "providerName": "Mistral AI",
      "tier": "Premium",
      "inputPerMTok": 1.5,
      "outputPerMTok": 7.5,
      "contextWindow": "256K",
      "batchDiscount": true,
      "notes": "Frontier-class multimodal model for agentic and coding work (v26.04). Open weights under a modified MIT licence."
    },
    {
      "id": "mistral-small",
      "name": "Mistral Small 4",
      "provider": "mistral",
      "providerName": "Mistral AI",
      "tier": "Standard",
      "inputPerMTok": 0.15,
      "outputPerMTok": 0.6,
      "contextWindow": "256K",
      "batchDiscount": true,
      "notes": "Latest small generation (v26.03). 256K context."
    },
    {
      "id": "codestral",
      "name": "Codestral",
      "provider": "mistral",
      "providerName": "Mistral AI",
      "tier": "Standard",
      "inputPerMTok": 0.3,
      "outputPerMTok": 0.9,
      "contextWindow": "128K",
      "batchDiscount": true,
      "notes": "Specialized for code generation (codestral-2508). Price cut in May 2026. 128K context. Mistral's only dedicated coding model since Devstral 2 retired on Jul 31, 2026."
    },
    {
      "id": "muse-spark-1.1",
      "name": "Muse Spark 1.3",
      "provider": "meta",
      "providerName": "Meta",
      "tier": "Standard",
      "inputPerMTok": 1.25,
      "outputPerMTok": 4.25,
      "contextWindow": "1M tokens",
      "batchDiscount": false,
      "notes": "Latest Muse Spark (Sep 2, 2026) on the Meta Model API, Meta's first paid first-party API. Same $1.25/$4.25 as 1.1 (Jul 9) and 1.2 (Aug 5), which stay available. Cached input $0.15. Multimodal agentic model with computer use. A Contributor tier bills $0.10/$0.20 (cached $0.002) in exchange for Meta training on your prompts and outputs, capped at 100 requests a minute. Still a public preview, but no longer US-only: access widened beyond the US with 1.2 on Aug 5."
    },
    {
      "id": "llama4-scout",
      "name": "Llama 4 Scout",
      "provider": "meta",
      "providerName": "Meta",
      "tier": "Budget",
      "inputPerMTok": 0.1,
      "outputPerMTok": 0.3,
      "contextWindow": "10M tokens",
      "batchDiscount": false,
      "notes": "10M native context window, but DeepInfra, whose rate is shown, serves 327K. Hosts vary in both price and served context."
    },
    {
      "id": "llama4-maverick",
      "name": "Llama 4 Maverick",
      "provider": "meta",
      "providerName": "Meta",
      "tier": "Standard",
      "inputPerMTok": 0.27,
      "outputPerMTok": 0.85,
      "contextWindow": "1M tokens",
      "batchDiscount": false,
      "notes": "Rate shown is Novita's, with the full 1M context: DeepInfra, our usual reference host, retired Maverick on Oct 1, 2026. DigitalOcean charges $0.25/$0.87. Varies by host."
    },
    {
      "id": "llama-3.3-70b",
      "name": "Llama 3.3 70B",
      "provider": "meta",
      "providerName": "Meta",
      "tier": "Standard",
      "inputPerMTok": 0.1,
      "outputPerMTok": 0.32,
      "contextWindow": "128K",
      "batchDiscount": false,
      "notes": "Commodity host rates $0.10/$0.32 (DeepInfra); Together is $1.04. Varies widely by host."
    },
    {
      "id": "llama-3-8b",
      "name": "Llama 3.1 8B",
      "provider": "meta",
      "providerName": "Meta",
      "tier": "Budget",
      "inputPerMTok": 0.02,
      "outputPerMTok": 0.04,
      "contextWindow": "128K",
      "batchDiscount": false,
      "notes": "Llama 3.1 8B on hosted providers ($0.02/$0.04 on DeepInfra) — 128K context, the cheapest rate tracked. Supersedes the original Llama 3 8B (8K)."
    },
    {
      "id": "deepseek-v4-flash",
      "name": "DeepSeek V4.1 Flash",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "tier": "Budget",
      "inputPerMTok": 0.3,
      "outputPerMTok": 1.2,
      "contextWindow": "1M tokens",
      "batchDiscount": false,
      "notes": "Listed at the peak rate. Since Aug 16, 2026 DeepSeek bills peak/off-peak: off-peak is half ($0.15/$0.60), and peak runs 01:00-04:00 and 06:00-10:00 UTC on weekdays (09:00-12:00 and 14:00-18:00 Beijing time); all other hours are off-peak, including weekends and Chinese public holidays in full. V4.1 Flash (Sep 10, 2026) replaced V4 Flash as deepseek-flash; the old model names route to it. Cache hits $0.006 peak / $0.003 off-peak. Native vision."
    },
    {
      "id": "deepseek-v4-pro",
      "name": "DeepSeek V4 Pro",
      "provider": "deepseek",
      "providerName": "DeepSeek",
      "tier": "Standard",
      "inputPerMTok": 1.32,
      "outputPerMTok": 3.96,
      "contextWindow": "1M tokens",
      "batchDiscount": false,
      "notes": "Listed at the peak rate after DeepSeek's Aug 16, 2026 price rise; off-peak is half ($0.66/$1.98) and covers weekends and Chinese public holidays in full. Cache hits $0.044 peak / $0.022 off-peak. A planned Sep 14 retirement was reversed, so V4 Pro stays available at unchanged billing."
    }
  ],
  "creditPlans": [
    {
      "id": "manus-free",
      "name": "Free",
      "provider": "manus",
      "providerName": "Manus",
      "monthlyPriceUSD": 0,
      "monthlyCredits": 1500,
      "dailyRefresh": 300,
      "notes": "300 credits refreshed daily, capped at 1,500 a month and usable only for Manus 2.0 Lite tasks. Add-on credit packs require a paid plan."
    },
    {
      "id": "manus-standard",
      "name": "Pro (Standard)",
      "provider": "manus",
      "providerName": "Manus",
      "monthlyPriceUSD": 20,
      "monthlyCredits": 4000,
      "dailyRefresh": 300,
      "notes": "For everyday research and projects."
    },
    {
      "id": "manus-custom",
      "name": "Pro (Customizable)",
      "provider": "manus",
      "providerName": "Manus",
      "monthlyPriceUSD": 40,
      "monthlyCredits": 8000,
      "dailyRefresh": 300,
      "notes": "Deeper research and project generation."
    },
    {
      "id": "manus-extended",
      "name": "Pro (Extended)",
      "provider": "manus",
      "providerName": "Manus",
      "monthlyPriceUSD": 200,
      "monthlyCredits": 40000,
      "dailyRefresh": 300,
      "notes": "Large-scale tasks and batch production."
    }
  ]
}