{
    "title": "LLM API pricing per million tokens",
    "currency": "USD",
    "unit": "per 1,000,000 tokens",
    "verified_on": "2026-10-17",
    "html": "https://agentping.io/llm-api-pricing",
    "markdown": "https://agentping.io/llm-api-pricing.md",
    "providers": {
        "anthropic": {
            "name": "Anthropic",
            "source": "https://platform.claude.com/docs/en/about-claude/pricing",
            "note": "Cache write is the 5-minute cache; the 1-hour cache is 2x input. Cache reads are 0.1x input on most models, 0.05x on Opus 5.5 and Sonnet 5.5, 0.025x on Fable 5.1 and Mythos 5.1. Batch API is 50% off. Haiku 5.5 prompts over 100k tokens bill at $0.50 / $2.50."
        },
        "openai": {
            "name": "OpenAI",
            "source": "https://developers.openai.com/api/docs/pricing",
            "note": "No charge for cache writes. Batch API is 50% off. GPT-5.4 and later, GPT-5.5 and the GPT-6 family bill prompts over 272k input tokens at roughly 2x input and 1.5x output. Pro models have no cached-input rate."
        },
        "gemini": {
            "name": "Google Gemini",
            "source": "https://ai.google.dev/gemini-api/docs/pricing",
            "note": "Paid tier, text input. Context caching bills storage per hour instead of a per-token write. Batch is 50% off. Pro models bill prompts over 200k tokens at 2x input and 1.5x output. Gemini 4 Argon list price doubles on 1 December 2026; the 3.6 and 3.8 Flash introductory prices end 1 January 2027."
        },
        "xai": {
            "name": "xAI",
            "source": "https://docs.x.ai/docs/models",
            "note": "Every model bills a prompt of 200k tokens or more at 2x on all tokens in the request. Priority processing is also 2x. No batch tier."
        },
        "mistral": {
            "name": "Mistral AI",
            "source": "https://docs.mistral.ai/inference/pricing",
            "note": "Cached input is 0.1x. Batch is 50% off. Mistral Large 4 is listed at a sale price (list is $1.36 / $4.18) with no published end date. The -latest aliases are priced the same as the dated id they point to."
        },
        "deepseek": {
            "name": "DeepSeek",
            "source": "https://api-docs.deepseek.com/quick_start/pricing",
            "note": "Peak rates (01:00 to 04:00 and 06:00 to 10:00 UTC, Monday to Friday). Off-peak is half on every line. Cache hits are billed as cached input. No batch tier."
        },
        "cohere": {
            "name": "Cohere",
            "source": "https://cohere.com/pricing",
            "note": "Cohere publishes no cached-input or batch rate. Command A+ pricing is taken from Cohere's OpenRouter listing because cohere.com does not expose it in HTML; confirm against your invoice. Deprecated models are listed at their existing-customer rates."
        }
    },
    "models": [
        {
            "provider": "anthropic",
            "model": "claude-fable-5-1",
            "name": "Claude Fable 5.1",
            "input": 10,
            "cached": 0.25,
            "output": 50,
            "batch": 0.5,
            "status": "current",
            "cache_write": 12.5
        },
        {
            "provider": "anthropic",
            "model": "claude-mythos-5-1",
            "name": "Claude Mythos 5.1",
            "input": 10,
            "cached": 0.25,
            "output": 50,
            "batch": 0.5,
            "status": "current",
            "cache_write": 12.5,
            "note": "Limited availability."
        },
        {
            "provider": "anthropic",
            "model": "claude-fable-5",
            "name": "Claude Fable 5",
            "input": 10,
            "cached": 1,
            "output": 50,
            "batch": 0.5,
            "status": "current",
            "cache_write": 12.5
        },
        {
            "provider": "anthropic",
            "model": "claude-mythos-5",
            "name": "Claude Mythos 5",
            "input": 10,
            "cached": 1,
            "output": 50,
            "batch": 0.5,
            "status": "current",
            "cache_write": 12.5,
            "note": "Limited availability."
        },
        {
            "provider": "anthropic",
            "model": "claude-opus-5-5",
            "name": "Claude Opus 5.5",
            "input": 4,
            "cached": 0.2,
            "output": 20,
            "batch": 0.5,
            "status": "current",
            "cache_write": 5
        },
        {
            "provider": "anthropic",
            "model": "claude-opus-5",
            "name": "Claude Opus 5",
            "input": 5,
            "cached": 0.5,
            "output": 25,
            "batch": 0.5,
            "status": "current",
            "cache_write": 6.25
        },
        {
            "provider": "anthropic",
            "model": "claude-opus-4-8",
            "name": "Claude Opus 4.8",
            "input": 5,
            "cached": 0.5,
            "output": 25,
            "batch": 0.5,
            "status": "current",
            "cache_write": 6.25
        },
        {
            "provider": "anthropic",
            "model": "claude-opus-4-7",
            "name": "Claude Opus 4.7",
            "input": 5,
            "cached": 0.5,
            "output": 25,
            "batch": 0.5,
            "status": "current",
            "cache_write": 6.25
        },
        {
            "provider": "anthropic",
            "model": "claude-opus-4-6",
            "name": "Claude Opus 4.6",
            "input": 5,
            "cached": 0.5,
            "output": 25,
            "batch": 0.5,
            "status": "current",
            "cache_write": 6.25
        },
        {
            "provider": "anthropic",
            "model": "claude-opus-4-5",
            "name": "Claude Opus 4.5",
            "input": 5,
            "cached": 0.5,
            "output": 25,
            "batch": 0.5,
            "status": "current",
            "cache_write": 6.25
        },
        {
            "provider": "anthropic",
            "model": "claude-opus-4-1",
            "name": "Claude Opus 4.1",
            "input": 15,
            "cached": 1.5,
            "output": 75,
            "batch": 0.5,
            "status": "retired",
            "cache_write": 18.75,
            "note": "Retired on the Claude API; still on Bedrock and Google Cloud."
        },
        {
            "provider": "anthropic",
            "model": "claude-opus-4",
            "name": "Claude Opus 4",
            "input": 15,
            "cached": 1.5,
            "output": 75,
            "batch": 0.5,
            "status": "retired",
            "cache_write": 18.75,
            "note": "Retired on the Claude API; still on Google Cloud."
        },
        {
            "provider": "anthropic",
            "model": "claude-sonnet-5-5",
            "name": "Claude Sonnet 5.5",
            "input": 2,
            "cached": 0.1,
            "output": 10,
            "batch": 0.5,
            "status": "current",
            "cache_write": 2.5
        },
        {
            "provider": "anthropic",
            "model": "claude-sonnet-5",
            "name": "Claude Sonnet 5",
            "input": 2,
            "cached": 0.2,
            "output": 10,
            "batch": 0.5,
            "status": "current",
            "cache_write": 2.5
        },
        {
            "provider": "anthropic",
            "model": "claude-sonnet-4-6",
            "name": "Claude Sonnet 4.6",
            "input": 3,
            "cached": 0.3,
            "output": 15,
            "batch": 0.5,
            "status": "current",
            "cache_write": 3.75
        },
        {
            "provider": "anthropic",
            "model": "claude-sonnet-4-5",
            "name": "Claude Sonnet 4.5",
            "input": 3,
            "cached": 0.3,
            "output": 15,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 3.75
        },
        {
            "provider": "anthropic",
            "model": "claude-sonnet-4",
            "name": "Claude Sonnet 4",
            "input": 3,
            "cached": 0.3,
            "output": 15,
            "batch": 0.5,
            "status": "retired",
            "cache_write": 3.75,
            "note": "Retired on the Claude API; still on Bedrock and Google Cloud."
        },
        {
            "provider": "anthropic",
            "model": "claude-haiku-5-5",
            "name": "Claude Haiku 5.5",
            "input": 0.1,
            "cached": 0.01,
            "output": 0.5,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0.125,
            "note": "Prompts over 100k tokens bill at $0.50 input / $2.50 output."
        },
        {
            "provider": "anthropic",
            "model": "claude-haiku-4-5",
            "name": "Claude Haiku 4.5",
            "input": 1,
            "cached": 0.1,
            "output": 5,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 1.25
        },
        {
            "provider": "anthropic",
            "model": "claude-3-5-haiku",
            "name": "Claude Haiku 3.5",
            "input": 0.8,
            "cached": 0.08,
            "output": 4,
            "batch": 0.5,
            "status": "retired",
            "cache_write": 1,
            "note": "Retired on the Claude API; still on Google Cloud."
        },
        {
            "provider": "openai",
            "model": "gpt-6-astra",
            "name": "GPT-6 Astra",
            "input": 10,
            "cached": 1,
            "output": 50,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Over 272k input tokens: $20 / $75."
        },
        {
            "provider": "openai",
            "model": "gpt-6.1-sol",
            "name": "GPT-6.1 Sol",
            "input": 2,
            "cached": 0.1,
            "output": 10,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Over 272k input tokens: $4 / $15."
        },
        {
            "provider": "openai",
            "model": "gpt-6-sol",
            "name": "GPT-6 Sol",
            "input": 2,
            "cached": 0.2,
            "output": 10,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Over 272k input tokens: $4 / $15."
        },
        {
            "provider": "openai",
            "model": "gpt-6-luna",
            "name": "GPT-6 Luna",
            "input": 0.1,
            "cached": 0.01,
            "output": 0.5,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Over 272k input tokens: $0.20 / $0.75."
        },
        {
            "provider": "openai",
            "model": "gpt-5.6-sol",
            "name": "GPT-5.6 Sol",
            "input": 4,
            "cached": 0.4,
            "output": 20,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Over 272k input tokens: $8 / $30."
        },
        {
            "provider": "openai",
            "model": "gpt-5.6-terra",
            "name": "GPT-5.6 Terra",
            "input": 2,
            "cached": 0.2,
            "output": 12,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Over 272k input tokens: $4 / $18."
        },
        {
            "provider": "openai",
            "model": "gpt-5.6-luna",
            "name": "GPT-5.6 Luna",
            "input": 0.2,
            "cached": 0.02,
            "output": 1.2,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Over 272k input tokens: $0.40 / $1.80."
        },
        {
            "provider": "openai",
            "model": "gpt-5.5",
            "name": "GPT-5.5",
            "input": 5,
            "cached": 0.5,
            "output": 30,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Over 272k input tokens: $10 / $45."
        },
        {
            "provider": "openai",
            "model": "gpt-5.5-pro",
            "name": "GPT-5.5 Pro",
            "input": 30,
            "cached": 30,
            "output": 180,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "No cached-input rate. Over 272k input tokens: $60 / $270."
        },
        {
            "provider": "openai",
            "model": "gpt-5.4",
            "name": "GPT-5.4",
            "input": 2.5,
            "cached": 0.25,
            "output": 15,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Over 272k input tokens: $5 / $22.50."
        },
        {
            "provider": "openai",
            "model": "gpt-5.4-mini",
            "name": "GPT-5.4 Mini",
            "input": 0.75,
            "cached": 0.075,
            "output": 4.5,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "gpt-5.4-nano",
            "name": "GPT-5.4 Nano",
            "input": 0.2,
            "cached": 0.02,
            "output": 1.25,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "gpt-5.4-pro",
            "name": "GPT-5.4 Pro",
            "input": 30,
            "cached": 30,
            "output": 180,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "No cached-input rate. Over 272k input tokens: $60 / $270."
        },
        {
            "provider": "openai",
            "model": "gpt-5.2",
            "name": "GPT-5.2",
            "input": 1.75,
            "cached": 0.175,
            "output": 14,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "gpt-5.2-pro",
            "name": "GPT-5.2 Pro",
            "input": 21,
            "cached": 21,
            "output": 168,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "No cached-input rate."
        },
        {
            "provider": "openai",
            "model": "gpt-5.1",
            "name": "GPT-5.1",
            "input": 1.25,
            "cached": 0.125,
            "output": 10,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "gpt-5",
            "name": "GPT-5",
            "input": 1.25,
            "cached": 0.125,
            "output": 10,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "gpt-5-mini",
            "name": "GPT-5 Mini",
            "input": 0.25,
            "cached": 0.025,
            "output": 2,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "gpt-5-nano",
            "name": "GPT-5 Nano",
            "input": 0.05,
            "cached": 0.005,
            "output": 0.4,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "gpt-5-pro",
            "name": "GPT-5 Pro",
            "input": 15,
            "cached": 15,
            "output": 120,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "No cached-input rate."
        },
        {
            "provider": "openai",
            "model": "gpt-4.1",
            "name": "GPT-4.1",
            "input": 2,
            "cached": 0.5,
            "output": 8,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "gpt-4.1-mini",
            "name": "GPT-4.1 Mini",
            "input": 0.4,
            "cached": 0.1,
            "output": 1.6,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "gpt-4.1-nano",
            "name": "GPT-4.1 Nano",
            "input": 0.1,
            "cached": 0.025,
            "output": 0.4,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "gpt-4o",
            "name": "GPT-4o",
            "input": 2.5,
            "cached": 1.25,
            "output": 10,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "gpt-4o-mini",
            "name": "GPT-4o Mini",
            "input": 0.15,
            "cached": 0.075,
            "output": 0.6,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "o3",
            "name": "o3",
            "input": 2,
            "cached": 0.5,
            "output": 8,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "o3-pro",
            "name": "o3-pro",
            "input": 20,
            "cached": 20,
            "output": 80,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0,
            "note": "No cached-input rate."
        },
        {
            "provider": "openai",
            "model": "o3-mini",
            "name": "o3-mini",
            "input": 1.1,
            "cached": 0.55,
            "output": 4.4,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "o4-mini",
            "name": "o4-mini",
            "input": 1.1,
            "cached": 0.275,
            "output": 4.4,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "openai",
            "model": "o1",
            "name": "o1",
            "input": 15,
            "cached": 7.5,
            "output": 60,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "gemini",
            "model": "gemini-4-argon",
            "name": "Gemini 4 Argon",
            "input": 2,
            "cached": 0.1,
            "output": 10,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Rises to $4 / $20 on 1 December 2026. Not on the free tier."
        },
        {
            "provider": "gemini",
            "model": "gemini-3.8-flash",
            "name": "Gemini 3.8 Flash",
            "input": 0.75,
            "cached": 0.075,
            "output": 3.75,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Introductory; $1.50 / $7.50 from 1 January 2027."
        },
        {
            "provider": "gemini",
            "model": "gemini-3.6-flash",
            "name": "Gemini 3.6 Flash",
            "input": 0.75,
            "cached": 0.075,
            "output": 3.75,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0,
            "note": "Introductory; $1.50 / $7.50 from 1 January 2027."
        },
        {
            "provider": "gemini",
            "model": "gemini-3.5-flash-lite",
            "name": "Gemini 3.5 Flash-Lite",
            "input": 0.3,
            "cached": 0.03,
            "output": 2.5,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "gemini",
            "model": "gemini-3.1-flash-lite",
            "name": "Gemini 3.1 Flash-Lite",
            "input": 0.25,
            "cached": 0.025,
            "output": 1.5,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "gemini",
            "model": "gemini-3.1-pro-preview",
            "name": "Gemini 3.1 Pro Preview",
            "input": 2,
            "cached": 0.2,
            "output": 12,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Over 200k tokens: $4 / $18."
        },
        {
            "provider": "gemini",
            "model": "gemini-3-flash-preview",
            "name": "Gemini 3 Flash Preview",
            "input": 0.5,
            "cached": 0.05,
            "output": 3,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "gemini",
            "model": "gemini-2.5-pro",
            "name": "Gemini 2.5 Pro",
            "input": 1.25,
            "cached": 0.125,
            "output": 10,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0,
            "note": "Over 200k tokens: $2.50 / $15."
        },
        {
            "provider": "gemini",
            "model": "gemini-2.5-flash",
            "name": "Gemini 2.5 Flash",
            "input": 0.3,
            "cached": 0.03,
            "output": 2.5,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "gemini",
            "model": "gemini-2.5-flash-lite",
            "name": "Gemini 2.5 Flash-Lite",
            "input": 0.1,
            "cached": 0.01,
            "output": 0.4,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "xai",
            "model": "grok-4.7",
            "name": "Grok 4.7",
            "input": 2,
            "cached": 0.5,
            "output": 6,
            "batch": 1,
            "status": "current",
            "cache_write": 0,
            "note": "Prompts of 200k tokens or more: $4 / $12."
        },
        {
            "provider": "xai",
            "model": "grok-4.6",
            "name": "Grok 4.6",
            "input": 2,
            "cached": 0.5,
            "output": 6,
            "batch": 1,
            "status": "current",
            "cache_write": 0,
            "note": "Prompts of 200k tokens or more: $4 / $12."
        },
        {
            "provider": "xai",
            "model": "grok-4.5",
            "name": "Grok 4.5",
            "input": 2,
            "cached": 0.3,
            "output": 6,
            "batch": 1,
            "status": "legacy",
            "cache_write": 0,
            "note": "Prompts of 200k tokens or more: $4 / $12."
        },
        {
            "provider": "xai",
            "model": "grok-4.3",
            "name": "Grok 4.3",
            "input": 1.25,
            "cached": 0.2,
            "output": 2.5,
            "batch": 1,
            "status": "current",
            "cache_write": 0,
            "note": "Prompts of 200k tokens or more: $2.50 / $5."
        },
        {
            "provider": "xai",
            "model": "grok-4.20-0309-reasoning",
            "name": "Grok 4.20 Reasoning",
            "input": 1.25,
            "cached": 0.2,
            "output": 2.5,
            "batch": 1,
            "status": "legacy",
            "cache_write": 0,
            "note": "Prompts of 200k tokens or more: $2.50 / $5."
        },
        {
            "provider": "xai",
            "model": "grok-4.20-0309-non-reasoning",
            "name": "Grok 4.20 Non-reasoning",
            "input": 1.25,
            "cached": 0.2,
            "output": 2.5,
            "batch": 1,
            "status": "legacy",
            "cache_write": 0,
            "note": "Prompts of 200k tokens or more: $2.50 / $5."
        },
        {
            "provider": "xai",
            "model": "grok-4.20-multi-agent-0309",
            "name": "Grok 4.20 Multi-agent",
            "input": 1.25,
            "cached": 0.2,
            "output": 2.5,
            "batch": 1,
            "status": "legacy",
            "cache_write": 0,
            "note": "Prompts of 200k tokens or more: $2.50 / $5."
        },
        {
            "provider": "xai",
            "model": "grok-build-0.1",
            "name": "Grok Build 0.1",
            "input": 1,
            "cached": 0.2,
            "output": 2,
            "batch": 1,
            "status": "current",
            "cache_write": 0,
            "note": "Prompts of 200k tokens or more: $2 / $4."
        },
        {
            "provider": "mistral",
            "model": "mistral-large-2610",
            "name": "Mistral Large 4",
            "input": 0.68,
            "cached": 0.07,
            "output": 2.09,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Sale price; list is $1.36 / $4.18."
        },
        {
            "provider": "mistral",
            "model": "mistral-large-latest",
            "name": "Mistral Large 4",
            "input": 0.68,
            "cached": 0.07,
            "output": 2.09,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0,
            "note": "Sale price; list is $1.36 / $4.18."
        },
        {
            "provider": "mistral",
            "model": "mistral-large-2512",
            "name": "Mistral Large 3",
            "input": 0.5,
            "cached": 0.05,
            "output": 1.5,
            "batch": 0.5,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "mistral-medium-2604",
            "name": "Mistral Medium 3.5",
            "input": 1.5,
            "cached": 0.15,
            "output": 7.5,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "mistral-medium-latest",
            "name": "Mistral Medium 3.5",
            "input": 1.5,
            "cached": 0.15,
            "output": 7.5,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "mistral-small-2603",
            "name": "Mistral Small 4",
            "input": 0.15,
            "cached": 0.015,
            "output": 0.6,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "mistral-small-latest",
            "name": "Mistral Small 4",
            "input": 0.15,
            "cached": 0.015,
            "output": 0.6,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "ministral-14b-2512",
            "name": "Ministral 3 14B",
            "input": 0.2,
            "cached": 0.02,
            "output": 0.2,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "ministral-14b-latest",
            "name": "Ministral 3 14B",
            "input": 0.2,
            "cached": 0.02,
            "output": 0.2,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "ministral-8b-2512",
            "name": "Ministral 3 8B",
            "input": 0.15,
            "cached": 0.015,
            "output": 0.15,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "ministral-8b-latest",
            "name": "Ministral 3 8B",
            "input": 0.15,
            "cached": 0.015,
            "output": 0.15,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "ministral-3b-2512",
            "name": "Ministral 3 3B",
            "input": 0.1,
            "cached": 0.01,
            "output": 0.1,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "ministral-3b-latest",
            "name": "Ministral 3 3B",
            "input": 0.1,
            "cached": 0.01,
            "output": 0.1,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "codestral-2508",
            "name": "Codestral",
            "input": 0.3,
            "cached": 0.03,
            "output": 0.9,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "mistral",
            "model": "codestral-latest",
            "name": "Codestral",
            "input": 0.3,
            "cached": 0.03,
            "output": 0.9,
            "batch": 0.5,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "deepseek",
            "model": "deepseek-flash",
            "name": "DeepSeek V4.1 Flash",
            "input": 0.3,
            "cached": 0.006,
            "output": 1.2,
            "batch": 1,
            "status": "current",
            "cache_write": 0,
            "note": "Off-peak: $0.15 / $0.003 cached / $0.60."
        },
        {
            "provider": "deepseek",
            "model": "deepseek-v4-flash",
            "name": "DeepSeek V4 Flash (alias)",
            "input": 0.3,
            "cached": 0.006,
            "output": 1.2,
            "batch": 1,
            "status": "legacy",
            "cache_write": 0,
            "note": "Retired id, served by V4.1 Flash at Flash prices."
        },
        {
            "provider": "deepseek",
            "model": "deepseek-v4-pro",
            "name": "DeepSeek V4 Pro",
            "input": 1.32,
            "cached": 0.044,
            "output": 3.96,
            "batch": 1,
            "status": "current",
            "cache_write": 0,
            "note": "Off-peak: $0.66 / $0.022 cached / $1.98."
        },
        {
            "provider": "cohere",
            "model": "command-a-plus-05-2026",
            "name": "Command A+",
            "input": 0.3,
            "cached": 0.3,
            "output": 1.5,
            "batch": 1,
            "status": "current",
            "cache_write": 0,
            "note": "From Cohere's OpenRouter listing; not shown on cohere.com."
        },
        {
            "provider": "cohere",
            "model": "command-a-03-2025",
            "name": "Command A",
            "input": 2.5,
            "cached": 2.5,
            "output": 10,
            "batch": 1,
            "status": "current",
            "cache_write": 0
        },
        {
            "provider": "cohere",
            "model": "command-r-plus-08-2024",
            "name": "Command R+ (08-2024)",
            "input": 2.5,
            "cached": 2.5,
            "output": 10,
            "batch": 1,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "cohere",
            "model": "command-r-08-2024",
            "name": "Command R (08-2024)",
            "input": 0.15,
            "cached": 0.15,
            "output": 0.6,
            "batch": 1,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "cohere",
            "model": "command-r7b-12-2024",
            "name": "Command R7B",
            "input": 0.0375,
            "cached": 0.0375,
            "output": 0.15,
            "batch": 1,
            "status": "legacy",
            "cache_write": 0
        },
        {
            "provider": "cohere",
            "model": "command-r-plus-04-2024",
            "name": "Command R+ (04-2024)",
            "input": 3,
            "cached": 3,
            "output": 15,
            "batch": 1,
            "status": "retired",
            "cache_write": 0,
            "note": "Deprecated September 2025; existing-customer rate."
        },
        {
            "provider": "cohere",
            "model": "command-r-03-2024",
            "name": "Command R (03-2024)",
            "input": 0.5,
            "cached": 0.5,
            "output": 1.5,
            "batch": 1,
            "status": "retired",
            "cache_write": 0,
            "note": "Deprecated September 2025; existing-customer rate."
        },
        {
            "provider": "cohere",
            "model": "command",
            "name": "Command",
            "input": 1,
            "cached": 1,
            "output": 2,
            "batch": 1,
            "status": "retired",
            "cache_write": 0,
            "note": "Deprecated September 2025; existing-customer rate."
        },
        {
            "provider": "cohere",
            "model": "command-light",
            "name": "Command Light",
            "input": 0.3,
            "cached": 0.3,
            "output": 0.6,
            "batch": 1,
            "status": "retired",
            "cache_write": 0,
            "note": "Deprecated September 2025; existing-customer rate."
        }
    ]
}