{ "revision": "2026-09-07", "currency": "USD", "priceUnit": "per million tokens, before tax", "scenario": { "ratio": 213.16705794137056, "cacheHit": 0.9653282151887312, "cacheWriteShare": 0.19024311548188436, "budget": 100, "days": 30 }, "assumptions": [ "Modeled billing, not measured application quality or completed work.", "Output includes reasoning whenever the provider bills it as output.", "Exclude paid tools, search, additional retries, infrastructure, and long-context premiums.", "Weekly allowances are prorated into a steady-state 30-day equivalent, not a guaranteed calendar-month entitlement.", "Subscription estimates assume full utilization within short-window and concurrency limits.", "Z.ai Flash comparisons use ordinary list API prices and exclude temporary agent promotions.", "Usage ratios are measured from local client records; their transfer to another provider is an assumption, especially cache reuse and tokenizer behavior.", "Cache writes use the ordinary input rate unless an explicit full cache-creation rate is recorded. Free cache storage or write surcharges do not make the original input processing free.", "Processed tokens include repeated cached context. They are not newly inferred output or accepted code.", "Capacity examples allocate the entire shared allowance to one model; examples cannot be added together.", "Normalized subscription costs assume full allowance utilization. At 50% utilization, cost per token doubles.", "Direct API comparisons use explicit same-model references and dated rates. Serving-provider API-credit discounts are recorded separately; model quality and cache portability are not assumed equivalent.", "Fees and quotas are prorated over the same comparison period for economic comparison only; annual commitments and real invoice schedules still apply." ], "models": [ { "name": "MiMo V2.5", "input": 0.14, "cache": 0.0028, "output": 0.28, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/pay-as-you-go", "note": "Cache writes temporarily free." }, { "name": "GLM-5.3-Flash promotional", "input": 0.075, "cache": 0.015, "output": 0.25, "verifiedAt": "2026-09-07", "source": "https://docs.z.ai/guides/overview/pricing", "note": "Promotion expires 2026-09-09 16:00 UTC; retained as a dated observation." }, { "name": "GLM-5.3-Flash list", "input": 0.15, "cache": 0.03, "output": 0.5, "verifiedAt": "2026-09-07", "source": "https://docs.z.ai/guides/overview/pricing", "note": "Ordinary list rate; cache storage temporarily free." }, { "name": "DeepSeek V4 Flash off-peak", "input": 0.22, "cache": 0.007, "output": 0.66, "verifiedAt": "2026-09-07", "source": "https://api-docs.deepseek.com/quick_start/pricing/", "note": "Peak rates double. Peak: weekdays 01-04 and 06-10 UTC." }, { "name": "MiMo V2.5 Pro", "input": 0.435, "cache": 0.0036, "output": 0.87, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/pay-as-you-go", "note": "Cache writes temporarily free." }, { "name": "MiniMax M3", "input": 0.3, "cache": 0.06, "output": 1.2, "verifiedAt": "2026-09-07", "source": "https://platform.minimax.io/docs/guides/pricing-paygo", "note": "Standard tier, at most 512K input per request; priority and longer context cost more." }, { "name": "DeepSeek V4 Pro off-peak", "input": 0.66, "cache": 0.022, "output": 1.98, "verifiedAt": "2026-09-07", "source": "https://api-docs.deepseek.com/quick_start/pricing/", "note": "Peak rates double. Peak: weekdays 01-04 and 06-10 UTC." }, { "name": "GLM-5.3", "input": 1.4, "cache": 0.26, "output": 4.4, "verifiedAt": "2026-09-07", "source": "https://docs.z.ai/guides/overview/pricing", "note": "Cache storage temporarily free." }, { "name": "Kimi K3", "input": 3, "cache": 0.3, "output": 15, "verifiedAt": "2026-09-07", "source": "https://www.kimi.ai/resources/kimi-k3-pricing", "note": "Always reasons; output allowance is not a code-only token count." } ], "plans": [ { "name": "OpenCode Go", "monthly": "$10", "verifiedAt": "2026-09-07", "source": "https://opencode.ai/docs/go/", "summary": "$60 API allowance for MiMo V2.5 and MiniMax M3; $30 for DeepSeek V4 Flash; $15 for K3, GLM-5.3 and DeepSeek V4 Pro. One shared pool, with shorter limits. Coding-agent traffic only.", "models": "Grok 4.6; GLM-5.3/Flash, 5.2, 5.1; GPT-5.6 Luna; Kimi K3, K2.7 Code, K2.6; MiMo V2.5/Pro; MiniMax M3/M2.7; Qwen 3.8 Max/Flash, 3.7 Max/Plus, 3.6 Plus; LongCat 2.0; Muse Spark 1.3/1.2 Contributor; DeepSeek V4 Pro/Flash/Flash Vision Exp; Hy4/Hy3; Omen Alpha. Regional/experimental conditions apply.", "modelSource": "https://opencode.ai/docs/go/", "capacityExamples": [ { "id": "go-mimo", "label": "MiMo V2.5" }, { "id": "go-m3", "label": "MiniMax M3" }, { "id": "go-k3", "label": "Kimi K3" } ], "modelIndex": { "models": [ { "id": "MiMo V2.5", "name": "MiMo V2.5", "conditions": "Go", "offers": [ "go-mimo" ], "openrouterModel": "xiaomi/mimo-v2.5" }, { "id": "MiniMax M3", "name": "MiniMax M3", "conditions": "Go", "offers": [ "go-m3" ], "openrouterModel": "minimax/minimax-m3" }, { "id": "Kimi K3", "name": "Kimi K3", "conditions": "Go", "offers": [ "go-k3" ], "openrouterModel": "moonshotai/kimi-k3" }, { "id": "DeepSeek V4 Flash", "name": "DeepSeek V4 Flash", "conditions": "Go", "offers": [ "go-flash" ], "openrouterModel": "deepseek/deepseek-v4-flash-0731" }, { "id": "GLM-5.3", "name": "GLM-5.3", "conditions": "Go", "offers": [ "go-glm" ], "openrouterModel": "z-ai/glm-5.3" }, { "id": "GPT-5.6 Luna", "name": "GPT-5.6 Luna", "conditions": "Go", "offers": [ "go-luna" ] }, { "id": "MiMo V2.5 Pro", "name": "MiMo V2.5 Pro", "conditions": "Go", "openrouterModel": "xiaomi/mimo-v2.5-pro" }, { "id": "GLM-5.3-Flash", "name": "GLM-5.3-Flash", "conditions": "Go", "openrouterModel": "z-ai/glm-5.3-flash" }, { "id": "DeepSeek V4 Pro", "name": "DeepSeek V4 Pro", "conditions": "Go", "openrouterModel": "deepseek/deepseek-v4-pro-0813" }, { "id": "Grok 4.6", "name": "Grok 4.6", "conditions": "Go" }, { "id": "GLM-5.2", "name": "GLM-5.2", "conditions": "Go" }, { "id": "GLM-5.1", "name": "GLM-5.1", "conditions": "Go" }, { "id": "Kimi K2.7 Code", "name": "Kimi K2.7 Code", "conditions": "Go" }, { "id": "Kimi K2.6", "name": "Kimi K2.6", "conditions": "Go" }, { "id": "MiniMax M2.7", "name": "MiniMax M2.7", "conditions": "Go" }, { "id": "Qwen 3.8 Max", "name": "Qwen 3.8 Max", "conditions": "Go" }, { "id": "Qwen 3.8 Flash", "name": "Qwen 3.8 Flash", "conditions": "Go" }, { "id": "Qwen 3.7 Max", "name": "Qwen 3.7 Max", "conditions": "Go" }, { "id": "Qwen 3.7 Plus", "name": "Qwen 3.7 Plus", "conditions": "Go" }, { "id": "Qwen 3.6 Plus", "name": "Qwen 3.6 Plus", "conditions": "Go" }, { "id": "LongCat 2.0", "name": "LongCat 2.0", "conditions": "Go" }, { "id": "Muse Spark 1.3 Contributor", "name": "Muse Spark 1.3 Contributor", "conditions": "Go" }, { "id": "Muse Spark 1.2 Contributor", "name": "Muse Spark 1.2 Contributor", "conditions": "Go" }, { "id": "DeepSeek V4 Flash Vision Exp", "name": "DeepSeek V4 Flash Vision Exp", "conditions": "Go" }, { "id": "Hy4", "name": "Hy4", "conditions": "Go" }, { "id": "Hy3", "name": "Hy3", "conditions": "Go" }, { "id": "Omen Alpha", "name": "Omen Alpha", "conditions": "Go" } ], "note": "One shared allowance. Regional and experimental conditions apply; uncalculated models retain unknown capacity." } }, { "name": "Z.ai Lite / Pro / Max", "monthly": "$18 / $80 / $168", "verifiedAt": "2026-09-07", "source": "https://z.ai/subscribe", "summary": "10k / 60k / 140k credits weekly; model and cache weights apply. Half credit consumption off-peak. Supported coding tools; dynamic concurrency.", "models": "GLM-5.3 and GLM-5.3-Flash on all tiers; older model aliases are routed to these.", "modelSource": "https://docs.z.ai/devpack/overview", "capacityExamples": [ { "id": "zai-lite-glm-off-peak", "label": "Lite, GLM-5.3 off-peak" }, { "id": "zai-pro-glm-off-peak", "label": "Pro, GLM-5.3 off-peak" }, { "id": "zai-max-glm-off-peak", "label": "Max, GLM-5.3 off-peak" } ], "modelIndex": { "models": [ { "id": "GLM-5.3", "name": "GLM-5.3", "offers": [ "zai-lite-glm-off-peak", "zai-lite-glm-peak", "zai-pro-glm-off-peak", "zai-pro-glm-peak", "zai-max-glm-off-peak", "zai-max-glm-peak" ], "openrouterModel": "z-ai/glm-5.3" }, { "id": "GLM-5.3-Flash", "name": "GLM-5.3-Flash", "offers": [ "zai-lite-flash-off-peak", "zai-lite-flash-peak", "zai-pro-flash-off-peak", "zai-pro-flash-peak", "zai-max-flash-off-peak", "zai-max-flash-peak" ], "openrouterModel": "z-ai/glm-5.3-flash" } ], "note": "Older aliases route to these models. Each row allocates the entire tier allowance to one model and time window." } }, { "name": "Synthetic", "monthly": "$30 per pack", "verifiedAt": "2026-09-07", "source": "https://synthetic.new/rate-limits", "summary": "$24 of its own API credits weekly; 500 weighted requests per five hours; one concurrent request per model per pack. More packs increase each limit.", "models": "Kimi K3; GLM-5.2, GLM-5.3-Flash beta, GLM-4.7-Flash; Qwen3.8-27B; gpt-oss-120b; Nemotron-3-Super-120B-A12B-NVFP4.", "modelSource": "https://api.synthetic.new/openai/v1/models", "capacityExamples": [ { "id": "synthetic-glm-5.3-flash", "label": "GLM-5.3-Flash" }, { "id": "synthetic-kimi-k3", "label": "Kimi-K3" } ], "modelIndex": { "models": [ { "id": "hf:openai/gpt-oss-120b", "offers": [ "synthetic-gpt-oss-120b" ] }, { "id": "hf:zai-org/GLM-5.3-Flash", "offers": [ "synthetic-glm-5.3-flash" ] }, { "id": "hf:zai-org/GLM-5.2", "offers": [ "synthetic-glm-5.2" ] }, { "id": "hf:moonshotai/Kimi-K3", "offers": [ "synthetic-kimi-k3" ] }, { "id": "hf:Qwen/Qwen3.8-27B", "offers": [ "synthetic-qwen3.8-27b" ] }, { "id": "hf:zai-org/GLM-4.7-Flash", "offers": [ "synthetic-glm-4.7-flash" ] }, { "id": "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", "offers": [ "synthetic-nvidia-nemotron-3-super-120b-a12b-nvfp4" ] } ], "catalog": "synthetic", "note": "The saved served catalog includes four automatic aliases. Catalog availability alone does not establish subscription eligibility." } }, { "name": "camelStream", "monthly": "$5 per stream", "verifiedAt": "2026-09-07", "source": "https://camelai.com/pricing", "summary": "Unmetered tokens; one generation per stream. Provider selects the model. No throughput guarantee; standard terms permit training on submitted content.", "models": "Auto-routed DeepSeek V4 Flash, Gemini 3.7 Flash, GLM-5.3-Flash, GPT-5.6 Luna and Muse Spark 1.2. No model pinning.", "modelSource": "https://camelai.com/docs/stream/fleet", "capacityExamples": [ { "id": "camel-unmetered", "label": "Unmetered; throughput unknown" } ], "modelIndex": { "models": [ { "id": "DeepSeek V4 Flash", "name": "DeepSeek V4 Flash", "conditions": "One stream; automatic routing, no model pinning", "offers": [ "camel-unmetered" ], "openrouterModel": "deepseek/deepseek-v4-flash-0731" }, { "id": "Gemini 3.7 Flash", "name": "Gemini 3.7 Flash", "conditions": "One stream; automatic routing, no model pinning", "offers": [ "camel-unmetered" ] }, { "id": "GLM-5.3-Flash", "name": "GLM-5.3-Flash", "conditions": "One stream; automatic routing, no model pinning", "offers": [ "camel-unmetered" ], "openrouterModel": "z-ai/glm-5.3-flash" }, { "id": "GPT-5.6 Luna", "name": "GPT-5.6 Luna", "conditions": "One stream; automatic routing, no model pinning", "offers": [ "camel-unmetered" ] }, { "id": "Muse Spark 1.2", "name": "Muse Spark 1.2", "conditions": "One stream; automatic routing, no model pinning", "offers": [ "camel-unmetered" ] } ], "note": "Unmetered service has no fixed token entitlement. Named routes are possible automatic choices, not selectable allocations." } }, { "name": "MiniMax Token Plan", "monthly": "$22 / $55 / $132", "verifiedAt": "2026-09-07", "source": "https://platform.minimax.io/docs/guides/pricing-token-plan", "summary": "Five-hour and weekly limits; text, image and speech share quota. Current documentation lacks sufficient numerical quota detail for a defensible API-equivalent calculation.", "models": "Text: MiniMax M3 and M2.7. Eligible image/speech models also share the quota.", "modelSource": "https://platform.minimax.io/docs/guides/pricing-token-plan", "capacityExamples": [ { "id": "minimax-unknown", "label": "Not quantifiable from published terms" } ], "modelIndex": { "models": [ { "id": "MiniMax M3", "name": "MiniMax M3", "offers": [ "minimax-unknown" ], "openrouterModel": "minimax/minimax-m3" }, { "id": "MiniMax M2.7", "name": "MiniMax M2.7", "offers": [ "minimax-unknown" ] } ], "note": "Text models only. Image and speech share quota but are outside this token comparison; published numerical allowance is insufficient." } }, { "name": "Kimi membership / Code", "monthly": "$19 / $39 / $99 / $199", "verifiedAt": "2026-09-07", "source": "https://www.kimi.ai/resources/kimi-k3-pricing", "summary": "Membership and coding benefits share resources. No fixed comparable token entitlement established here; personal Code benefits and production API access differ.", "models": "K3 advertised across Kimi, including Code. Code exposes kimi-for-coding and kimi-for-coding-highspeed aliases; HighSpeed requires Allegretto+. Alias backing version is not pinned here.", "modelSource": "https://www.kimi.ai/help/kimi-code/third-party-agents", "capacityExamples": [ { "id": "kimi-unknown", "label": "Not quantifiable from published terms" } ], "modelIndex": { "models": [ { "id": "Kimi K3", "name": "Kimi K3", "conditions": "Membership; K3 advertised across Kimi", "offers": [ "kimi-unknown" ], "openrouterModel": "moonshotai/kimi-k3" }, { "id": "kimi-for-coding", "name": "kimi-for-coding", "conditions": "Code alias; backing version not pinned", "offers": [ "kimi-unknown" ] }, { "id": "kimi-for-coding-highspeed", "name": "kimi-for-coding-highspeed", "conditions": "Code HighSpeed alias; Allegretto+; backing version not pinned", "offers": [ "kimi-unknown" ] } ], "note": "No fixed comparable entitlement established. Membership K3 and Code aliases are distinguished; alias costs are not assumed to equal K3." } }, { "name": "Alibaba Cloud Coding Plan", "monthly": "$50", "verifiedAt": "2026-09-07", "source": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "summary": "90k requests/month, 45k/week, 6k/five hours. Explicitly excludes automated scripts, application backends and noninteractive use.", "models": "qwen3.7-plus, qwen3.6-plus, kimi-k2.5, glm-5, MiniMax-M2.5, qwen3.5-plus, qwen3-max-2026-01-23, qwen3-coder-next, qwen3-coder-plus, glm-4.7.", "modelSource": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "capacityExamples": [ { "id": "alibaba-requests", "label": "Not quantifiable from published terms" } ], "modelIndex": { "models": [ { "id": "qwen3.7-plus", "name": "qwen3.7-plus", "offers": [ "alibaba-requests" ] }, { "id": "qwen3.6-plus", "name": "qwen3.6-plus", "offers": [ "alibaba-requests" ] }, { "id": "kimi-k2.5", "name": "kimi-k2.5", "offers": [ "alibaba-requests" ] }, { "id": "glm-5", "name": "glm-5", "offers": [ "alibaba-requests" ] }, { "id": "MiniMax-M2.5", "name": "MiniMax-M2.5", "offers": [ "alibaba-requests" ] }, { "id": "qwen3.5-plus", "name": "qwen3.5-plus", "offers": [ "alibaba-requests" ] }, { "id": "qwen3-max-2026-01-23", "name": "qwen3-max-2026-01-23", "offers": [ "alibaba-requests" ] }, { "id": "qwen3-coder-next", "name": "qwen3-coder-next", "offers": [ "alibaba-requests" ] }, { "id": "qwen3-coder-plus", "name": "qwen3-coder-plus", "offers": [ "alibaba-requests" ] }, { "id": "glm-4.7", "name": "glm-4.7", "offers": [ "alibaba-requests" ] } ], "note": "Request quotas cannot be converted without tokens per billable request. Automated scripts and application backends are excluded." } }, { "name": "deepseekv4pro.com", "monthly": "$19.90 / $49.90; Agent $29.90", "verifiedAt": "2026-09-07", "source": "https://deepseekv4pro.com/pricing", "summary": "Independent reseller. Recurring promotional prices observed. Pricing cards and integration pages disagree on some quotas; model weighting and upstream plan rules apply.", "models": "DeepSeek plans: V4 Flash/Pro. Agent plan adds GLM-5.3/5.2, MiniMax M3 and Kimi K3.", "modelSource": "https://deepseekv4pro.com/pricing", "capacityExamples": [ { "id": "reseller-conflict", "label": "Not quantifiable from published terms" } ], "modelIndex": { "models": [ { "id": "DeepSeek V4 Flash", "name": "DeepSeek V4 Flash", "conditions": "DeepSeek plans / Agent plan", "offers": [ "reseller-conflict" ], "openrouterModel": "deepseek/deepseek-v4-flash-0731" }, { "id": "DeepSeek V4 Pro", "name": "DeepSeek V4 Pro", "conditions": "DeepSeek plans / Agent plan", "offers": [ "reseller-conflict" ], "openrouterModel": "deepseek/deepseek-v4-pro-0813" }, { "id": "GLM-5.3", "name": "GLM-5.3", "conditions": "Agent plan only", "offers": [ "reseller-conflict" ], "openrouterModel": "z-ai/glm-5.3" }, { "id": "GLM-5.2", "name": "GLM-5.2", "conditions": "Agent plan only", "offers": [ "reseller-conflict" ] }, { "id": "MiniMax M3", "name": "MiniMax M3", "conditions": "Agent plan only", "offers": [ "reseller-conflict" ], "openrouterModel": "minimax/minimax-m3" }, { "id": "Kimi K3", "name": "Kimi K3", "conditions": "Agent plan only", "offers": [ "reseller-conflict" ], "openrouterModel": "moonshotai/kimi-k3" } ], "note": "Independent reseller; published quotas conflict. Models added by the Agent plan are marked separately." } }, { "name": "MiMo Token Plan", "monthly": "$6 / $16 / $50 / $100", "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "summary": "4.1B / 11B / 38B / 82B credits, with model-specific deductions. These are not raw tokens. Programming-tool restrictions apply.", "models": "MiMo V2.5 and V2.5 Pro across tiers; additional speech models are outside this text calculation.", "modelSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "capacityExamples": [ { "id": "mimo-lite-v25-daytime", "label": "Lite, V2.5 daytime" }, { "id": "mimo-standard-v25-daytime", "label": "Standard, V2.5 daytime" }, { "id": "mimo-pro-v25-daytime", "label": "Pro, V2.5 daytime" }, { "id": "mimo-max-v25-daytime", "label": "Max, V2.5 daytime" } ], "modelIndex": { "models": [ { "id": "MiMo V2.5", "name": "MiMo V2.5", "offers": [ "mimo-lite-v25-daytime", "mimo-lite-v25-off-peak", "mimo-standard-v25-daytime", "mimo-standard-v25-off-peak", "mimo-pro-v25-daytime", "mimo-pro-v25-off-peak", "mimo-max-v25-daytime", "mimo-max-v25-off-peak" ], "openrouterModel": "xiaomi/mimo-v2.5" }, { "id": "MiMo V2.5 Pro", "name": "MiMo V2.5 Pro", "offers": [ "mimo-lite-pro-daytime", "mimo-lite-pro-off-peak", "mimo-standard-pro-daytime", "mimo-standard-pro-off-peak", "mimo-pro-pro-daytime", "mimo-pro-pro-off-peak", "mimo-max-pro-daytime", "mimo-max-pro-off-peak" ], "openrouterModel": "xiaomi/mimo-v2.5-pro" } ], "note": "Text models only. Credit pools are shared across models; daytime and off-peak rows are alternative allocations." } }, { "name": "Chutes", "monthly": "$10 / $20", "verifiedAt": "2026-09-07", "source": "https://chutes.ai/pricing", "summary": "Daily quotas and discounted overage. Published February policy caps subscription value at 5× its PAYG rates; confirm current rolling limits in the account.", "models": "Served catalog includes DeepSeek V4 Flash/V3.2, Kimi K3/K2.6, GLM-5.2/5.1, Qwen 3/3.5/3.6/3.8, Gemma 4, Mistral Nemo and Nemotron. Exact tier eligibility needs account confirmation.", "modelSource": "https://llm.chutes.ai/v1/models", "capacityExamples": [ { "id": "chutes-plus", "label": "Plus, Flash conditional ceiling" }, { "id": "chutes-pro", "label": "Pro, Flash conditional ceiling" } ], "modelIndex": { "models": [ { "id": "deepseek-ai/DeepSeek-V4-Flash-0731-TEE", "offers": [ "chutes-plus", "chutes-pro" ], "openrouterModel": "deepseek/deepseek-v4-flash-0731" }, { "id": "moonshotai/Kimi-K3-TEE", "openrouterModel": "moonshotai/kimi-k3" } ], "catalog": "chutes", "note": "Served catalog; exact subscription tier eligibility needs account confirmation. Flash capacity remains a conditional ceiling." } }, { "name": "NanoGPT", "monthly": "$12 advertised", "verifiedAt": "2026-09-07", "source": "https://nano-gpt.com/blog/how-to-save-money-on-ai", "summary": "Help lists 60M input-token units weekly, including cached input, with model multipliers. New subscription terms exclude commercial products; signup availability requires checking.", "models": "296 included model/variant IDs in the subscription endpoint: e.g. GLM-5.3/Flash, MiniMax M3, DeepSeek V4 Pro/Flash, gpt-oss and Qwen. Multipliers vary; this is not 296 distinct base models.", "modelSource": "https://nano-gpt.com/api/subscription/v1/models?detailed=true", "capacityExamples": [ { "id": "nano-1x", "label": "1× input weight" }, { "id": "nano-2x", "label": "2× input weight" } ], "modelIndex": { "models": [], "catalog": "nano", "note": "Subscription-included model/variant catalog. Per-model multipliers were not captured, so the 1x/2x quota examples cannot be assigned to individual IDs.", "unassignedOffers": [ "nano-1x", "nano-2x" ] } }, { "name": "Kilo Pass", "monthly": "$19 / $49 / $199", "verifiedAt": "2026-09-07", "source": "https://kilo.ai/pricing/kilo-pass", "summary": "Credits plus welcome/loyalty bonuses; annual billing gives 50% extra monthly credits. Full use yields a 33.3% effective discount. Bonus credits expire monthly; Gateway supported.", "models": "Gateway catalog includes Claude Sonnet 5/Opus 4.8, GPT, Gemini, Kimi K3, MiniMax M3, GLM, DeepSeek and MiMo; 371 route IDs in this snapshot, including free variants.", "modelSource": "https://api.kilo.ai/api/gateway/models", "capacityExamples": [ { "id": "kilo-starter-sonnet", "label": "Starter, Sonnet 5 annual" }, { "id": "kilo-pro-sonnet", "label": "Pro, Sonnet 5 annual" }, { "id": "kilo-expert-sonnet", "label": "Expert, Sonnet 5 annual" } ], "modelIndex": { "models": [ { "id": "anthropic/claude-sonnet-5", "offers": [ "kilo-starter-sonnet", "kilo-pro-sonnet", "kilo-expert-sonnet" ] }, { "id": "minimax/minimax-m3", "offers": [ "kilo-starter-m3", "kilo-pro-m3", "kilo-expert-m3" ] } ], "catalog": "kilo", "note": "Gateway catalog includes free and paid variants. Annual credit bonus is modeled only where provider rates were captured; catalog presence alone does not establish eligibility." } } ], "zai": { "verifiedAt": "2026-09-07", "priceSource": "https://z.ai/subscribe", "quotaSource": "https://docs.z.ai/devpack/overview", "plans": [ { "name": "Lite", "monthly": 18, "weeklyCredits": 10000, "fiveHourCredits": 2000 }, { "name": "Pro", "monthly": 80, "weeklyCredits": 60000, "fiveHourCredits": 12000 }, { "name": "Max", "monthly": 168, "weeklyCredits": 140000, "fiveHourCredits": 28000 } ], "models": [ { "name": "GLM-5.3", "input": 6.9, "cache": 1.7, "output": 24 }, { "name": "GLM-5.3-Flash list", "input": 2.3, "cache": 0.56, "output": 8 } ] }, "usage": { "capturedAt": "2026-09-07T14:55:53Z", "tool": "Tokscale 4.15.1", "toolSource": "https://github.com/junhoyeo/tokscale/tree/v4.15.1", "scope": "All locally discovered history in one scan; Claude Code, Codex and ZCode. Not a monthly billing export or a deduplicated multi-machine fleet total.", "input": 2293232314, "output": 383174954, "cacheRead": 78848276612, "cacheWrite": 538768695, "total": 82063452575, "messages": 871701, "accounting": "Tokscale 4.15.1 model-report output excludes its separate reasoning bucket. Billable output here equals scanner totalOutput plus sum(entries.reasoning), once. Input excludes cache reads and writes. Claude Code reasoning, when present, is already in its output and has no separate bucket.", "privacy": "Aggregate counters only; no prompts, responses, project names, sessions or account identifiers.", "scannerOutputExcludingSeparateReasoning": 345676932, "separatelyReportedReasoning": 37498022, "accountingSource": "https://github.com/junhoyeo/tokscale/blob/v4.15.1/crates/tokscale-core/src/lib.rs#L3804" }, "capacityOffers": [ { "id": "go-mimo", "plan": "OpenCode Go", "tier": "Go", "model": "MiMo V2.5", "monthly": 10, "verifiedAt": "2026-09-07", "source": "https://opencode.ai/docs/go/", "status": "modeled", "note": "Alternative full allocation of one shared pool. Five-hour/week/month caps. Excludes temporary Flash bonus and long-context premiums.", "allowance": 60, "rates": { "input": 0.14, "cache": 0.0028, "output": 0.28 }, "periodDays": 30, "unit": "USD", "rateSource": "https://opencode.ai/docs/go/", "directApiModel": "MiMo V2.5" }, { "id": "go-m3", "plan": "OpenCode Go", "tier": "Go", "model": "MiniMax M3", "monthly": 10, "verifiedAt": "2026-09-07", "source": "https://opencode.ai/docs/go/", "status": "modeled", "note": "Alternative full allocation of one shared pool. Five-hour/week/month caps. Excludes temporary Flash bonus and long-context premiums.", "allowance": 60, "rates": { "input": 0.3, "cache": 0.06, "output": 1.2 }, "periodDays": 30, "unit": "USD", "rateSource": "https://opencode.ai/docs/go/", "directApiModel": "MiniMax M3" }, { "id": "go-k3", "plan": "OpenCode Go", "tier": "Go", "model": "Kimi K3", "monthly": 10, "verifiedAt": "2026-09-07", "source": "https://opencode.ai/docs/go/", "status": "modeled", "note": "Alternative full allocation of one shared pool. Five-hour/week/month caps. Excludes temporary Flash bonus and long-context premiums.", "allowance": 15, "rates": { "input": 3, "cache": 0.3, "output": 15 }, "periodDays": 30, "unit": "USD", "rateSource": "https://opencode.ai/docs/go/", "directApiModel": "Kimi K3" }, { "id": "go-flash", "plan": "OpenCode Go", "tier": "Go", "model": "DeepSeek V4 Flash off-peak", "monthly": 10, "verifiedAt": "2026-09-07", "source": "https://opencode.ai/docs/go/", "status": "modeled", "note": "Alternative full allocation of one shared pool. Five-hour/week/month caps. Excludes temporary Flash bonus and long-context premiums.", "allowance": 30, "rates": { "input": 0.22, "cache": 0.007, "output": 0.66 }, "periodDays": 30, "unit": "USD", "rateSource": "https://opencode.ai/docs/go/", "directApiModel": "DeepSeek V4 Flash off-peak" }, { "id": "go-glm", "plan": "OpenCode Go", "tier": "Go", "model": "GLM-5.3", "monthly": 10, "verifiedAt": "2026-09-07", "source": "https://opencode.ai/docs/go/", "status": "modeled", "note": "Alternative full allocation of one shared pool. Five-hour/week/month caps. Excludes temporary Flash bonus and long-context premiums.", "allowance": 15, "rates": { "input": 1.4, "cache": 0.26, "output": 4.4 }, "periodDays": 30, "unit": "USD", "rateSource": "https://opencode.ai/docs/go/", "directApiModel": "GLM-5.3" }, { "id": "go-luna", "plan": "OpenCode Go", "tier": "Go", "model": "GPT-5.6 Luna", "monthly": 10, "verifiedAt": "2026-09-07", "source": "https://opencode.ai/docs/go/", "status": "modeled", "note": "Alternative full allocation of one shared pool. Five-hour/week/month caps. Excludes temporary Flash bonus and long-context premiums.", "allowance": 15, "rates": { "input": 0.2, "cache": 0.02, "output": 1.2, "cacheWrite": 0.25 }, "periodDays": 30, "unit": "USD", "rateSource": "https://opencode.ai/docs/go/" }, { "id": "synthetic-gpt-oss-120b", "plan": "Synthetic", "tier": "One pack", "model": "gpt-oss-120b", "monthly": 30, "verifiedAt": "2026-09-07", "source": "https://synthetic.new/rate-limits", "status": "modeled", "note": "500 weighted requests/five hours; one concurrent request/model/pack. Cache writes billed as ordinary input with no added write fee.", "allowance": 24, "rates": { "input": 0.09999999999999999, "cache": 0.02, "output": 0.09999999999999999 }, "periodDays": 7, "unit": "USD", "rateSource": "https://api.synthetic.new/openai/v1/models" }, { "id": "synthetic-glm-5.3-flash", "plan": "Synthetic", "tier": "One pack", "model": "GLM-5.3-Flash", "monthly": 30, "verifiedAt": "2026-09-07", "source": "https://synthetic.new/rate-limits", "status": "modeled", "note": "500 weighted requests/five hours; one concurrent request/model/pack. Cache writes billed as ordinary input with no added write fee.", "allowance": 24, "rates": { "input": 0.15, "cache": 0.04, "output": 0.5 }, "periodDays": 7, "unit": "USD", "rateSource": "https://api.synthetic.new/openai/v1/models", "directApiModel": "GLM-5.3-Flash list" }, { "id": "synthetic-glm-5.2", "plan": "Synthetic", "tier": "One pack", "model": "GLM-5.2", "monthly": 30, "verifiedAt": "2026-09-07", "source": "https://synthetic.new/rate-limits", "status": "modeled", "note": "500 weighted requests/five hours; one concurrent request/model/pack. Cache writes billed as ordinary input with no added write fee.", "allowance": 24, "rates": { "input": 1, "cache": 0.16, "output": 3 }, "periodDays": 7, "unit": "USD", "rateSource": "https://api.synthetic.new/openai/v1/models" }, { "id": "synthetic-kimi-k3", "plan": "Synthetic", "tier": "One pack", "model": "Kimi-K3", "monthly": 30, "verifiedAt": "2026-09-07", "source": "https://synthetic.new/rate-limits", "status": "modeled", "note": "500 weighted requests/five hours; one concurrent request/model/pack. Cache writes billed as ordinary input with no added write fee.", "allowance": 24, "rates": { "input": 3, "cache": 0.44999999999999996, "output": 15 }, "periodDays": 7, "unit": "USD", "rateSource": "https://api.synthetic.new/openai/v1/models", "directApiModel": "Kimi K3" }, { "id": "synthetic-qwen3.8-27b", "plan": "Synthetic", "tier": "One pack", "model": "Qwen3.8-27B", "monthly": 30, "verifiedAt": "2026-09-07", "source": "https://synthetic.new/rate-limits", "status": "modeled", "note": "500 weighted requests/five hours; one concurrent request/model/pack. Cache writes billed as ordinary input with no added write fee.", "allowance": 24, "rates": { "input": 0.44999999999999996, "cache": 0.09, "output": 2.2 }, "periodDays": 7, "unit": "USD", "rateSource": "https://api.synthetic.new/openai/v1/models" }, { "id": "synthetic-glm-4.7-flash", "plan": "Synthetic", "tier": "One pack", "model": "GLM-4.7-Flash", "monthly": 30, "verifiedAt": "2026-09-07", "source": "https://synthetic.new/rate-limits", "status": "modeled", "note": "500 weighted requests/five hours; one concurrent request/model/pack. Cache writes billed as ordinary input with no added write fee.", "allowance": 24, "rates": { "input": 0.09999999999999999, "cache": 0.02, "output": 0.5 }, "periodDays": 7, "unit": "USD", "rateSource": "https://api.synthetic.new/openai/v1/models" }, { "id": "synthetic-nvidia-nemotron-3-super-120b-a12b-nvfp4", "plan": "Synthetic", "tier": "One pack", "model": "NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", "monthly": 30, "verifiedAt": "2026-09-07", "source": "https://synthetic.new/rate-limits", "status": "modeled", "note": "500 weighted requests/five hours; one concurrent request/model/pack. Cache writes billed as ordinary input with no added write fee.", "allowance": 24, "rates": { "input": 0.3, "cache": 0.06, "output": 1 }, "periodDays": 7, "unit": "USD", "rateSource": "https://api.synthetic.new/openai/v1/models" }, { "id": "camel-unmetered", "plan": "camelStream", "tier": "One stream", "model": "Automatic routing", "monthly": 5, "verifiedAt": "2026-09-07", "source": "https://camelai.com/pricing", "status": "unmetered", "note": "No token entitlement or guaranteed sustained throughput to convert." }, { "id": "minimax-unknown", "plan": "MiniMax Token Plan", "tier": "All listed tiers", "model": "See supported models", "monthly": null, "verifiedAt": "2026-09-07", "source": "https://platform.minimax.io/docs/guides/pricing-token-plan", "status": "unknown", "note": "Numerical token-plan quota not established by current public documentation." }, { "id": "kimi-unknown", "plan": "Kimi membership / Code", "tier": "All listed tiers", "model": "See supported models", "monthly": null, "verifiedAt": "2026-09-07", "source": "https://www.kimi.ai/resources/kimi-k3-pricing", "status": "unknown", "note": "No fixed token allowance and conversion established; shared membership resources." }, { "id": "alibaba-requests", "plan": "Alibaba Cloud Coding Plan", "tier": "All listed tiers", "model": "See supported models", "monthly": null, "verifiedAt": "2026-09-07", "source": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "status": "unknown", "note": "90,000 requests/month. Ratios alone do not establish tokens/request; local message count is not assumed to be API request count." }, { "id": "reseller-conflict", "plan": "deepseekv4pro.com", "tier": "All listed tiers", "model": "See supported models", "monthly": null, "verifiedAt": "2026-09-07", "source": "https://deepseekv4pro.com/pricing", "status": "unknown", "note": "Pricing and integration quotas conflict; cache and context weighting cannot be reconciled confidently." }, { "id": "mimo-lite-v25-daytime", "plan": "MiMo Token Plan", "tier": "Lite", "model": "MiMo V2.5 daytime", "monthly": 6, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 4100000000, "rates": { "input": 100000000, "cache": 2000000, "output": 200000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5" }, { "id": "mimo-lite-v25-off-peak", "plan": "MiMo Token Plan", "tier": "Lite", "model": "MiMo V2.5 off-peak", "monthly": 6, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 4100000000, "rates": { "input": 80000000, "cache": 1600000, "output": 160000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5" }, { "id": "mimo-lite-pro-daytime", "plan": "MiMo Token Plan", "tier": "Lite", "model": "MiMo V2.5 Pro daytime", "monthly": 6, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 4100000000, "rates": { "input": 300000000, "cache": 2500000, "output": 600000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5 Pro" }, { "id": "mimo-lite-pro-off-peak", "plan": "MiMo Token Plan", "tier": "Lite", "model": "MiMo V2.5 Pro off-peak", "monthly": 6, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 4100000000, "rates": { "input": 240000000, "cache": 2000000, "output": 480000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5 Pro" }, { "id": "mimo-standard-v25-daytime", "plan": "MiMo Token Plan", "tier": "Standard", "model": "MiMo V2.5 daytime", "monthly": 16, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 11000000000, "rates": { "input": 100000000, "cache": 2000000, "output": 200000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5" }, { "id": "mimo-standard-v25-off-peak", "plan": "MiMo Token Plan", "tier": "Standard", "model": "MiMo V2.5 off-peak", "monthly": 16, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 11000000000, "rates": { "input": 80000000, "cache": 1600000, "output": 160000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5" }, { "id": "mimo-standard-pro-daytime", "plan": "MiMo Token Plan", "tier": "Standard", "model": "MiMo V2.5 Pro daytime", "monthly": 16, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 11000000000, "rates": { "input": 300000000, "cache": 2500000, "output": 600000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5 Pro" }, { "id": "mimo-standard-pro-off-peak", "plan": "MiMo Token Plan", "tier": "Standard", "model": "MiMo V2.5 Pro off-peak", "monthly": 16, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 11000000000, "rates": { "input": 240000000, "cache": 2000000, "output": 480000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5 Pro" }, { "id": "mimo-pro-v25-daytime", "plan": "MiMo Token Plan", "tier": "Pro", "model": "MiMo V2.5 daytime", "monthly": 50, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 38000000000, "rates": { "input": 100000000, "cache": 2000000, "output": 200000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5" }, { "id": "mimo-pro-v25-off-peak", "plan": "MiMo Token Plan", "tier": "Pro", "model": "MiMo V2.5 off-peak", "monthly": 50, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 38000000000, "rates": { "input": 80000000, "cache": 1600000, "output": 160000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5" }, { "id": "mimo-pro-pro-daytime", "plan": "MiMo Token Plan", "tier": "Pro", "model": "MiMo V2.5 Pro daytime", "monthly": 50, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 38000000000, "rates": { "input": 300000000, "cache": 2500000, "output": 600000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5 Pro" }, { "id": "mimo-pro-pro-off-peak", "plan": "MiMo Token Plan", "tier": "Pro", "model": "MiMo V2.5 Pro off-peak", "monthly": 50, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 38000000000, "rates": { "input": 240000000, "cache": 2000000, "output": 480000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5 Pro" }, { "id": "mimo-max-v25-daytime", "plan": "MiMo Token Plan", "tier": "Max", "model": "MiMo V2.5 daytime", "monthly": 100, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 82000000000, "rates": { "input": 100000000, "cache": 2000000, "output": 200000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5" }, { "id": "mimo-max-v25-off-peak", "plan": "MiMo Token Plan", "tier": "Max", "model": "MiMo V2.5 off-peak", "monthly": 100, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 82000000000, "rates": { "input": 80000000, "cache": 1600000, "output": 160000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5" }, { "id": "mimo-max-pro-daytime", "plan": "MiMo Token Plan", "tier": "Max", "model": "MiMo V2.5 Pro daytime", "monthly": 100, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 82000000000, "rates": { "input": 300000000, "cache": 2500000, "output": 600000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5 Pro" }, { "id": "mimo-max-pro-off-peak", "plan": "MiMo Token Plan", "tier": "Max", "model": "MiMo V2.5 Pro off-peak", "monthly": 100, "verifiedAt": "2026-09-07", "source": "https://mimo.mi.com/docs/en-US/price/token-plan", "status": "modeled", "note": "Monthly credits. Off-peak 16:00-24:00 UTC. Full single-model allocation; programming-tool restrictions.", "allowance": 82000000000, "rates": { "input": 240000000, "cache": 2000000, "output": 480000000 }, "periodDays": 30, "unit": "credits", "rateSource": "https://mimo.mi.com/docs/en-US/price/token-plan", "directApiModel": "MiMo V2.5 Pro" }, { "id": "chutes-plus", "plan": "Chutes", "tier": "Plus", "model": "DeepSeek V4 Flash", "monthly": 10, "verifiedAt": "2026-09-07", "source": "https://web.archive.org/web/20260712093051/https://chutes.ai/news/community-announcement-february", "status": "conditional ceiling", "note": "Conditional on continued 5x policy and model eligibility. Current rolling limits may bind earlier. Served-model API does not prove tier inclusion. Direct API comparison uses official DeepSeek off-peak prices.", "allowance": 50, "rates": { "input": 0.44, "cache": 0.04399999999999999, "output": 1.32 }, "periodDays": 30, "unit": "USD", "rateSource": "https://llm.chutes.ai/v1/models", "directApiModel": "DeepSeek V4 Flash off-peak" }, { "id": "chutes-pro", "plan": "Chutes", "tier": "Pro", "model": "DeepSeek V4 Flash", "monthly": 20, "verifiedAt": "2026-09-07", "source": "https://web.archive.org/web/20260712093051/https://chutes.ai/news/community-announcement-february", "status": "conditional ceiling", "note": "Conditional on continued 5x policy and model eligibility. Current rolling limits may bind earlier. Served-model API does not prove tier inclusion. Direct API comparison uses official DeepSeek off-peak prices.", "allowance": 100, "rates": { "input": 0.44, "cache": 0.04399999999999999, "output": 1.32 }, "periodDays": 30, "unit": "USD", "rateSource": "https://llm.chutes.ai/v1/models", "directApiModel": "DeepSeek V4 Flash off-peak" }, { "id": "nano-1x", "plan": "NanoGPT", "tier": "Pro", "model": "Included model at 1x input weight", "monthly": 12, "verifiedAt": "2026-09-07", "source": "https://nano-gpt.com/help", "status": "modeled", "note": "Cached input consumes full weight. Output is inferred from measured ratio, not a separate output entitlement. Personal/noncommercial eligibility and availability require checking.", "allowance": 60000000, "rates": { "input": 1000000, "cache": 1000000, "output": 0 }, "periodDays": 7, "unit": "input-token units", "rateSource": "https://nano-gpt.com/api/subscription/v1/models?detailed=true" }, { "id": "nano-2x", "plan": "NanoGPT", "tier": "Pro", "model": "Included model at 2x input weight", "monthly": 12, "verifiedAt": "2026-09-07", "source": "https://nano-gpt.com/help", "status": "modeled", "note": "Cached input consumes full weight. Output is inferred from measured ratio, not a separate output entitlement. Personal/noncommercial eligibility and availability require checking.", "allowance": 60000000, "rates": { "input": 2000000, "cache": 2000000, "output": 0 }, "periodDays": 7, "unit": "input-token units", "rateSource": "https://nano-gpt.com/api/subscription/v1/models?detailed=true" }, { "id": "kilo-starter-sonnet", "plan": "Kilo Pass", "tier": "Starter annual billing", "model": "Anthropic: Claude Sonnet 5", "monthly": 19, "verifiedAt": "2026-09-07", "source": "https://kilo.ai/pricing/kilo-pass", "status": "modeled", "note": "Annual commitment; fee shown as monthly equivalent. 50% monthly bonus assumed fully used before expiry. Monthly-billed loyalty bonuses differ.", "allowance": 28.5, "rates": { "input": 2, "cache": 0.19999999999999998, "output": 10, "cacheWrite": 2.5 }, "periodDays": 30, "unit": "USD", "rateSource": "https://api.kilo.ai/api/gateway/models" }, { "id": "kilo-starter-m3", "plan": "Kilo Pass", "tier": "Starter annual billing", "model": "MiniMax: MiniMax M3", "monthly": 19, "verifiedAt": "2026-09-07", "source": "https://kilo.ai/pricing/kilo-pass", "status": "modeled", "note": "Annual commitment; fee shown as monthly equivalent. 50% monthly bonus assumed fully used before expiry. Monthly-billed loyalty bonuses differ.", "allowance": 28.5, "rates": { "input": 0.3, "cache": 0.06, "output": 1.2 }, "periodDays": 30, "unit": "USD", "rateSource": "https://api.kilo.ai/api/gateway/models", "directApiModel": "MiniMax M3" }, { "id": "kilo-pro-sonnet", "plan": "Kilo Pass", "tier": "Pro annual billing", "model": "Anthropic: Claude Sonnet 5", "monthly": 49, "verifiedAt": "2026-09-07", "source": "https://kilo.ai/pricing/kilo-pass", "status": "modeled", "note": "Annual commitment; fee shown as monthly equivalent. 50% monthly bonus assumed fully used before expiry. Monthly-billed loyalty bonuses differ.", "allowance": 73.5, "rates": { "input": 2, "cache": 0.19999999999999998, "output": 10, "cacheWrite": 2.5 }, "periodDays": 30, "unit": "USD", "rateSource": "https://api.kilo.ai/api/gateway/models" }, { "id": "kilo-pro-m3", "plan": "Kilo Pass", "tier": "Pro annual billing", "model": "MiniMax: MiniMax M3", "monthly": 49, "verifiedAt": "2026-09-07", "source": "https://kilo.ai/pricing/kilo-pass", "status": "modeled", "note": "Annual commitment; fee shown as monthly equivalent. 50% monthly bonus assumed fully used before expiry. Monthly-billed loyalty bonuses differ.", "allowance": 73.5, "rates": { "input": 0.3, "cache": 0.06, "output": 1.2 }, "periodDays": 30, "unit": "USD", "rateSource": "https://api.kilo.ai/api/gateway/models", "directApiModel": "MiniMax M3" }, { "id": "kilo-expert-sonnet", "plan": "Kilo Pass", "tier": "Expert annual billing", "model": "Anthropic: Claude Sonnet 5", "monthly": 199, "verifiedAt": "2026-09-07", "source": "https://kilo.ai/pricing/kilo-pass", "status": "modeled", "note": "Annual commitment; fee shown as monthly equivalent. 50% monthly bonus assumed fully used before expiry. Monthly-billed loyalty bonuses differ.", "allowance": 298.5, "rates": { "input": 2, "cache": 0.19999999999999998, "output": 10, "cacheWrite": 2.5 }, "periodDays": 30, "unit": "USD", "rateSource": "https://api.kilo.ai/api/gateway/models" }, { "id": "kilo-expert-m3", "plan": "Kilo Pass", "tier": "Expert annual billing", "model": "MiniMax: MiniMax M3", "monthly": 199, "verifiedAt": "2026-09-07", "source": "https://kilo.ai/pricing/kilo-pass", "status": "modeled", "note": "Annual commitment; fee shown as monthly equivalent. 50% monthly bonus assumed fully used before expiry. Monthly-billed loyalty bonuses differ.", "allowance": 298.5, "rates": { "input": 0.3, "cache": 0.06, "output": 1.2 }, "periodDays": 30, "unit": "USD", "rateSource": "https://api.kilo.ai/api/gateway/models", "directApiModel": "MiniMax M3" } ], "openrouter": { "verifiedAt": "2026-09-07", "capturedAt": "2026-09-07T16:11:37Z", "fee": { "rate": 0.055, "minimumUsd": 0.8, "referenceTopupCreditsUsd": 100, "source": "https://openrouter.ai/blog/insights/governing-team-ai-spend/" }, "selection": "Selected lower-cost route was chosen for the measured profile from status-zero endpoints with tool support and explicit cached-input pricing. This is a dated quote, not a default routing guarantee; different ratios can change the best route. Reference quotes use model-author endpoints, including nonzero status where disclosed.", "assumptions": [ "Standard card-funded PAYG. Amortize the larger of 5.5% of credit purchase or USD 0.80 across that purchase; exclude taxes, BYOK, crypto and enterprise arrangements.", "Default reference purchase is USD 100 inference credits with USD 5.50 surcharge. Cash budget estimates divide by the resulting 1.055 multiplier.", "Each quote uses all prices from one endpoint. Listed discounts are already embedded in quote prices.", "Assume the measured cache-hit/write proportions are reproducible and every request fits the selected endpoint and standard price tier. Recheck actual cache hits and routing after purchase.", "Current quotes only; DeepSeek author reference is off-peak and GLM Flash includes its dated promotion.", "Selected quotes are fixed in this snapshot. Calculator ratio overrides reprice these routes without claiming that they remain the cheapest." ], "models": [ { "id": "xiaomi/mimo-v2.5", "name": "MiMo V2.5", "directApiModel": "MiMo V2.5", "reference": { "provider": "Xiaomi", "tag": "xiaomi/fp8", "status": 0, "quantization": "fp8", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 0.14, "cache": 0.0028, "output": 0.28 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "selected": { "provider": "Xiaomi", "tag": "xiaomi/fp8", "status": 0, "quantization": "fp8", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 0.14, "cache": 0.0028, "output": 0.28 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "observedEndpointCount": 5, "source": "https://openrouter.ai/api/v1/models/xiaomi/mimo-v2.5/endpoints", "page": "https://openrouter.ai/xiaomi/mimo-v2.5/providers", "comparisonOffers": [ "go-mimo", "mimo-lite-v25-daytime", "mimo-max-v25-daytime" ], "note": "Quoted endpoint prices already include any displayed discount; do not apply the discount metadata again.", "capturedAt": "2026-09-07T16:11:37Z", "cacheComparison": { "provider": "DeepInfra", "tag": "deepinfra/fp8", "contextLength": 262144, "rates": { "input": 0.13, "cache": 0.026000000000000002, "output": 0.65 } } }, { "id": "xiaomi/mimo-v2.5-pro", "name": "MiMo V2.5 Pro", "directApiModel": "MiMo V2.5 Pro", "reference": { "provider": "Xiaomi", "tag": "xiaomi/fp8", "status": -2, "quantization": "fp8", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 0.435, "cache": 0.0036, "output": 0.87 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "selected": { "provider": "DeepInfra", "tag": "deepinfra/fp8", "status": 0, "quantization": "fp8", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 0.39, "cache": 0.078, "output": 1.17 }, "quotedDiscountMetadata": 0.61, "pricingOverrides": [] }, "observedEndpointCount": 7, "source": "https://openrouter.ai/api/v1/models/xiaomi/mimo-v2.5-pro/endpoints", "page": "https://openrouter.ai/xiaomi/mimo-v2.5-pro/providers", "comparisonOffers": [ "mimo-max-pro-daytime" ], "note": "Reference Xiaomi route reported nonzero status (-2); the selected eligible route has status zero and a higher modeled cost. Availability can materially change actual cost.", "capturedAt": "2026-09-07T16:11:37Z" }, { "id": "minimax/minimax-m3", "name": "MiniMax M3", "directApiModel": "MiniMax M3", "reference": { "provider": "Minimax", "tag": "minimax/fp8", "status": 0, "quantization": "fp8", "contextLength": 524288, "supportsTools": true, "rates": { "input": 0.3, "cache": 0.06, "output": 1.2 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "selected": { "provider": "DeepInfra", "tag": "deepinfra/fp8", "status": 0, "quantization": "fp8", "contextLength": 524288, "supportsTools": true, "rates": { "input": 0.28, "cache": 0.056, "output": 1.1 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "observedEndpointCount": 12, "source": "https://openrouter.ai/api/v1/models/minimax/minimax-m3/endpoints", "page": "https://openrouter.ai/minimax/minimax-m3/providers", "comparisonOffers": [ "go-m3", "kilo-starter-m3" ], "note": "Lower GMICloud quote excluded because endpoint metadata did not advertise tool support. Endpoint prices already embed displayed discounts; do not apply discount metadata again.", "capturedAt": "2026-09-07T16:11:37Z", "excludedLowerQuote": { "provider": "GMICloud", "tag": "gmicloud/fp8", "status": 0, "quantization": "fp8", "contextLength": 1048576, "supportsTools": false, "rates": { "input": 0.24, "cache": 0.048, "output": 0.96 }, "quotedDiscountMetadata": 0.6, "pricingOverrides": [] } }, { "id": "z-ai/glm-5.3", "name": "GLM-5.3", "directApiModel": "GLM-5.3", "reference": { "provider": "Z.AI", "tag": "z-ai/fp8", "status": 0, "quantization": "fp8", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 1.4, "cache": 0.26, "output": 4.4 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "selected": { "provider": "BaseTen", "tag": "baseten/fp4", "status": 0, "quantization": "fp4", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 1.4, "cache": 0.14, "output": 4.4 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "observedEndpointCount": 28, "source": "https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints", "page": "https://openrouter.ai/z-ai/glm-5.3/providers", "comparisonOffers": [ "zai-max-glm-off-peak" ], "note": "Quoted endpoint prices already include any displayed discount; do not apply the discount metadata again.", "capturedAt": "2026-09-07T16:11:37Z" }, { "id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash promotional", "directApiModel": "GLM-5.3-Flash list", "reference": { "provider": "Z.AI", "tag": "z-ai/fp8", "status": 0, "quantization": "fp8", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 0.075, "cache": 0.015, "output": 0.25 }, "quotedDiscountMetadata": 0.5, "pricingOverrides": [] }, "selected": { "provider": "Relace", "tag": "relace/fp4", "status": 0, "quantization": "fp4", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 0.07125000000000001, "cache": 0.01425, "output": 0.2375 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "observedEndpointCount": 24, "source": "https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints", "page": "https://openrouter.ai/z-ai/glm-5.3-flash/providers", "comparisonOffers": [ "synthetic-glm-5.3-flash", "zai-max-flash-off-peak" ], "note": "Current promotional quotes; author promotion ends 2026-09-09 16:00 UTC. Do not project these rates past the offer.", "capturedAt": "2026-09-07T16:11:37Z" }, { "id": "moonshotai/kimi-k3", "name": "Kimi K3", "directApiModel": "Kimi K3", "reference": { "provider": "Moonshot AI", "tag": "moonshotai/mxfp4", "status": 0, "quantization": "mxfp4", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 3, "cache": 0.3, "output": 15 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "selected": { "provider": "Sail Research", "tag": "sail-research/fp4", "status": 0, "quantization": "fp4", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 2.6, "cache": 0.29, "output": 13 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "observedEndpointCount": 18, "source": "https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints", "page": "https://openrouter.ai/moonshotai/kimi-k3/providers", "comparisonOffers": [ "synthetic-kimi-k3", "go-k3" ], "note": "Quoted endpoint prices already include any displayed discount; do not apply the discount metadata again.", "capturedAt": "2026-09-07T16:11:37Z" }, { "id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "directApiModel": null, "reference": { "provider": "Anthropic", "tag": "anthropic", "status": 0, "quantization": "unknown", "contextLength": 1000000, "supportsTools": true, "rates": { "input": 2, "cache": 0.19999999999999998, "output": 10, "cacheWrite": 2.5 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "selected": { "provider": "Anthropic", "tag": "anthropic", "status": 0, "quantization": "unknown", "contextLength": 1000000, "supportsTools": true, "rates": { "input": 2, "cache": 0.19999999999999998, "output": 10, "cacheWrite": 2.5 }, "quotedDiscountMetadata": 0, "pricingOverrides": [] }, "observedEndpointCount": 9, "source": "https://openrouter.ai/api/v1/models/anthropic/claude-sonnet-5/endpoints", "page": "https://openrouter.ai/anthropic/claude-sonnet-5/providers", "comparisonOffers": [ "kilo-starter-sonnet" ], "note": "Standard service with five-minute cache writes. One-hour cache creation and paid tools are excluded.", "capturedAt": "2026-09-07T16:11:37Z", "additionalOfferIds": [ "kilo-pro-sonnet", "kilo-expert-sonnet" ] }, { "id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek V4 Flash 0731", "directApiModel": "DeepSeek V4 Flash off-peak", "reference": { "provider": "DeepSeek", "tag": "deepseek", "status": 0, "quantization": "unknown", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 0.22, "cache": 0.007, "output": 0.66 }, "quotedDiscountMetadata": 0, "pricingOverrides": [ { "utc_days": [ "saturday", "sunday" ], "prompt": "0.00000022", "completion": "0.00000066", "input_cache_read": "0.000000007" }, { "utc_start": 0, "utc_end": 100, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000022", "completion": "0.00000066", "input_cache_read": "0.000000007" }, { "utc_start": 100, "utc_end": 400, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000044", "completion": "0.00000132", "input_cache_read": "0.000000014" }, { "utc_start": 400, "utc_end": 600, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000022", "completion": "0.00000066", "input_cache_read": "0.000000007" }, { "utc_start": 600, "utc_end": 1000, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000044", "completion": "0.00000132", "input_cache_read": "0.000000014" }, { "utc_start": 1000, "utc_end": 0, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000022", "completion": "0.00000066", "input_cache_read": "0.000000007" } ] }, "selected": { "provider": "StreamLake", "tag": "streamlake/fp8", "status": 0, "quantization": "fp8", "contextLength": 1024000, "supportsTools": true, "rates": { "input": 0.13199999999999998, "cache": 0.004200000000000001, "output": 0.396 }, "quotedDiscountMetadata": 0.7, "pricingOverrides": [] }, "observedEndpointCount": 29, "source": "https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-flash-0731/endpoints", "page": "https://openrouter.ai/deepseek/deepseek-v4-flash-0731/providers", "comparisonOffers": [ "go-flash", "chutes-pro" ], "note": "Reference author quote is off-peak; weekday 01:00-04:00 and 06:00-10:00 UTC doubles it. Pinned OpenRouter version; subscription aliases may not pin the same checkpoint.", "capturedAt": "2026-09-07T16:11:37Z" }, { "id": "deepseek/deepseek-v4-pro-0813", "name": "DeepSeek V4 Pro 0813", "directApiModel": "DeepSeek V4 Pro off-peak", "reference": { "provider": "DeepSeek", "tag": "deepseek", "status": 0, "quantization": "unknown", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 0.66, "cache": 0.022, "output": 1.9800000000000002 }, "quotedDiscountMetadata": 0, "pricingOverrides": [ { "utc_days": [ "saturday", "sunday" ], "prompt": "0.00000066", "completion": "0.00000198", "input_cache_read": "0.000000022" }, { "utc_start": 0, "utc_end": 100, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000066", "completion": "0.00000198", "input_cache_read": "0.000000022" }, { "utc_start": 100, "utc_end": 400, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000132", "completion": "0.00000396", "input_cache_read": "0.000000044" }, { "utc_start": 400, "utc_end": 600, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000066", "completion": "0.00000198", "input_cache_read": "0.000000022" }, { "utc_start": 600, "utc_end": 1000, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000132", "completion": "0.00000396", "input_cache_read": "0.000000044" }, { "utc_start": 1000, "utc_end": 0, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000066", "completion": "0.00000198", "input_cache_read": "0.000000022" } ] }, "selected": { "provider": "DeepSeek", "tag": "deepseek", "status": 0, "quantization": "unknown", "contextLength": 1048576, "supportsTools": true, "rates": { "input": 0.66, "cache": 0.022, "output": 1.9800000000000002 }, "quotedDiscountMetadata": 0, "pricingOverrides": [ { "utc_days": [ "saturday", "sunday" ], "prompt": "0.00000066", "completion": "0.00000198", "input_cache_read": "0.000000022" }, { "utc_start": 0, "utc_end": 100, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000066", "completion": "0.00000198", "input_cache_read": "0.000000022" }, { "utc_start": 100, "utc_end": 400, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000132", "completion": "0.00000396", "input_cache_read": "0.000000044" }, { "utc_start": 400, "utc_end": 600, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000066", "completion": "0.00000198", "input_cache_read": "0.000000022" }, { "utc_start": 600, "utc_end": 1000, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000132", "completion": "0.00000396", "input_cache_read": "0.000000044" }, { "utc_start": 1000, "utc_end": 0, "utc_days": [ "monday", "tuesday", "wednesday", "thursday", "friday" ], "prompt": "0.00000066", "completion": "0.00000198", "input_cache_read": "0.000000022" } ] }, "observedEndpointCount": 20, "source": "https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints", "page": "https://openrouter.ai/deepseek/deepseek-v4-pro-0813/providers", "comparisonOffers": [], "note": "Reference author quote is off-peak; weekday 01:00-04:00 and 06:00-10:00 UTC doubles it. Pinned OpenRouter version; subscription aliases may not pin the same checkpoint.", "capturedAt": "2026-09-07T16:11:37Z" } ], "cacheSource": "https://openrouter.ai/docs/guides/best-practices/prompt-caching", "routingSource": "https://openrouter.ai/docs/guides/routing/provider-selection" } }