+ Flash Max 40,000M credits / month (no time-window or request-frequency caps) $99.00 $0.0001 — — 1,518,343 ~15,337 ~15,337 Subscribe ↗ Models
Step 3.7 Flash Step 3.5 Flash
Ceiling 40,000M credits / month (no time-window or request-frequency caps)
Reachability BYOK — OpenAI-compatible endpoint https://api.stepfun.ai/step_plan/v1 (Claude Code, Cursor, Cline, Kilo Code, Roo Code)
Pricing notes —
Cost rule ~proxy estimate · platform.stepfun.ai/docs/en/step-plan/overview (monthly credits + $1≈7M) + guides/pricing/details (API rates) + Flash Pro 8,000M credits / month (no time-window or request-frequency caps) $29.00 $0.0001 — — 303,668 ~10,471 ~10,471 Subscribe ↗ Models
Step 3.7 Flash Step 3.5 Flash
Ceiling 8,000M credits / month (no time-window or request-frequency caps)
Reachability BYOK — OpenAI-compatible endpoint https://api.stepfun.ai/step_plan/v1 (Claude Code, Cursor, Cline, Kilo Code, Roo Code)
Pricing notes —
Cost rule ~proxy estimate · platform.stepfun.ai/docs/en/step-plan/overview (monthly credits + $1≈7M) + guides/pricing/details (API rates) + Flash Plus 1,600M credits / month (no time-window or request-frequency caps) $9.99 $0.0002 — — 60,733 ~6,079 ~6,079 Subscribe ↗ Models
Step 3.7 Flash Step 3.5 Flash
Ceiling 1,600M credits / month (no time-window or request-frequency caps)
Reachability BYOK — OpenAI-compatible endpoint https://api.stepfun.ai/step_plan/v1 (Claude Code, Cursor, Cline, Kilo Code, Roo Code)
Pricing notes —
Cost rule ~proxy estimate · platform.stepfun.ai/docs/en/step-plan/overview (monthly credits + $1≈7M) + guides/pricing/details (API rates) + Go Cheapest $10 credits · ~15K reqs/mo · $3/5h · $6/7d $1.00 $0.0029 1,044 2,088 3,480 ~3,480 ~1,044 Subscribe ↗ Models
GLM-5.3-Flash DeepSeek V4 Pro GPT-6 Luna GPT-5.6 Luna Qwen3.7-Max MiniMax M3 Grok 4.5 MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.5 Laguna S 2.1 DeepSeek V4 Flash Qwen3.8-Max Qwen3.7-Plus Qwen3.6-Max-Preview Qwen3.6-Plus MiniMax M2.7 MiniMax M2.5 MiMo V2.5 Pro Kimi K3 Kimi K2.7 Code Kimi K2.7 Code HighSpeed Kimi K2.6 Kimi K2.5 GLM-5.2 GLM-5.3 GLM-5.2-Fast GLM-5.1 GLM-5 Hy3 Nemotron 3 Ultra Step 5 Preview Step 3.7 Flash Step 3.5 Flash Muse Spark 1.2 Contributor Muse Spark 1.3 Contributor Qwen3.7-Flash Inkling Inkling Small Qwen3.8 Flash Qwen 3.8 27B Hy4 preview DeepSeek V4 Flash Fast DeepSeek V4 Flash Vision Exp DeepSeek V4.1 Flash
Ceiling $10 credits · ~15K reqs/mo · $3/5h · $6/7d
Reachability command-code CLI only
Pricing notes —
Cost rule ~proxy estimate · commandcode.ai/docs/resources/pricing-limits — DeepSeek V4 Pro row (off-peak headline, 2026-08-18; -75% promo ended, time-of-day pricing since 2026-08-16) + Lite $87/mo usage at provider rates · weekly frontier fair-use 12% $29.00 $0.0009 — — 100,000 ~3,448 ~3,448 Subscribe ↗ Models
Claude Fable 5.1 Claude Opus 5.5 Claude Opus 5 GPT-6 Astra GPT-6 Sol GPT-6 Luna Gemini 3.8 Flash Gemini 3.7 Flash GPT-5.6 Sol Grok 4.6 Grok 4.7 Qwen3.8-Max GLM-5.3 Kimi K3 MiniMax M3 Nemotron 3 Ultra 550B Muse Spark 1.3 Muse Spark 1.2 MiMo V2.6 Pro MiMo V2.6 Flash DeepSeek V4.1 Flash DeepSeek V4 Pro
Ceiling $87/mo usage at provider rates · weekly frontier fair-use 12%
Reachability Any agent · OpenAI-compatible key
Pricing notes —
Cost rule ~proxy estimate · llmgateway.io/models — DeepSeek V4 Pro row (deepseek + tencent mappings $0.435/$0.87/$0.0036 per 1M cached read — the mappings this row stores; read 2026-09-23) + Max $537/mo usage at provider rates · weekly frontier fair-use 18% $179.00 $0.0009 — — 617,241 ~3,448 ~3,448 Subscribe ↗ Models
Claude Fable 5.1 Claude Opus 5.5 Claude Opus 5 GPT-6 Astra GPT-6 Sol GPT-6 Luna Gemini 3.8 Flash Gemini 3.7 Flash GPT-5.6 Sol Grok 4.6 Grok 4.7 Qwen3.8-Max GLM-5.3 Kimi K3 MiniMax M3 Nemotron 3 Ultra 550B Muse Spark 1.3 Muse Spark 1.2 MiMo V2.6 Pro MiMo V2.6 Flash DeepSeek V4.1 Flash DeepSeek V4 Pro
Ceiling $537/mo usage at provider rates · weekly frontier fair-use 18%
Reachability Any agent · OpenAI-compatible key
Pricing notes —
Cost rule ~proxy estimate · llmgateway.io/models — DeepSeek V4 Pro row (deepseek + tencent mappings $0.435/$0.87/$0.0036 per 1M cached read — the mappings this row stores; read 2026-09-23) + Pro $237/mo usage at provider rates · weekly frontier fair-use 15% $79.00 $0.0009 — — 272,413 ~3,448 ~3,448 Subscribe ↗ Models
Claude Fable 5.1 Claude Opus 5.5 Claude Opus 5 GPT-6 Astra GPT-6 Sol GPT-6 Luna Gemini 3.8 Flash Gemini 3.7 Flash GPT-5.6 Sol Grok 4.6 Grok 4.7 Qwen3.8-Max GLM-5.3 Kimi K3 MiniMax M3 Nemotron 3 Ultra 550B Muse Spark 1.3 Muse Spark 1.2 MiMo V2.6 Pro MiMo V2.6 Flash DeepSeek V4.1 Flash DeepSeek V4 Pro
Ceiling $237/mo usage at provider rates · weekly frontier fair-use 15%
Reachability Any agent · OpenAI-compatible key
Pricing notes —
Cost rule ~proxy estimate · llmgateway.io/models — DeepSeek V4 Pro row (deepseek + tencent mappings $0.435/$0.87/$0.0036 per 1M cached read — the mappings this row stores; read 2026-09-23) + Flash Mini 400M credits / month (no time-window or request-frequency caps) $6.99 $0.0005 — — 15,183 ~2,172 ~2,172 Subscribe ↗ Models
Step 3.7 Flash Step 3.5 Flash
Ceiling 400M credits / month (no time-window or request-frequency caps)
Reachability BYOK — OpenAI-compatible endpoint https://api.stepfun.ai/step_plan/v1 (Claude Code, Cursor, Cline, Kilo Code, Roo Code)
Pricing notes —
Cost rule ~proxy estimate · platform.stepfun.ai/docs/en/step-plan/overview (monthly credits + $1≈7M) + guides/pricing/details (API rates) + Max 12% off 1st mo $88 first month 82 Billion Credits · 20× Lite · unlimited usage, no weekly/5h caps $100.00 $0.0007 — — 135,761 ~1,358 ~1,358 Subscribe ↗ Models
MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.5 Pro MiMo V2.5
Ceiling 82 Billion Credits · 20× Lite · unlimited usage, no weekly/5h caps
Reachability —
Pricing notes MiMo V2.5 / V2.5 Pro retire 2026-10-21 (10:00 Beijing) — V2.6 Pro and V2.6 Flash are the forward path
Cost rule ~proxy estimate · https://mimo.mi.com/docs/price/pay-as-you-go — Max tier multiplier + Pro 12% off 1st mo $44 first month 38 Billion Credits · 9.3× Lite · unlimited usage, no weekly/5h caps $50.00 $0.0008 — — 63,129 ~1,263 ~1,263 Subscribe ↗ Models
MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.5 Pro MiMo V2.5
Ceiling 38 Billion Credits · 9.3× Lite · unlimited usage, no weekly/5h caps
Reachability —
Pricing notes MiMo V2.5 / V2.5 Pro retire 2026-10-21 (10:00 Beijing) — V2.6 Pro and V2.6 Flash are the forward path
Cost rule ~proxy estimate · https://mimo.mi.com/docs/price/pay-as-you-go — Pro tier multiplier + Ultra ~12.5B tokens/mo · 5h rolling + weekly windows · 6-7 agents $120.00 $0.0008 17,463 — 150,141 ~1,251 ~146 Subscribe ↗ Models
MiniMax M3 MiniMax M2.7
Ceiling ~12.5B tokens/mo · 5h rolling + weekly windows · 6-7 agents
Reachability —
Pricing notes —
Cost rule ~proxy estimate · migration guide §5: Ultra "roughly 12.5B tokens of monthly capacity" (≈7.35× Plus ~1.7B); 5h from published "29,077 M2.7 calls / 5h" + Max ~5.1B tokens/mo · 5h rolling + weekly windows · 4-5 agents $50.00 $0.0008 9,008 — 61,257 ~1,225 ~180 Subscribe ↗ Models
MiniMax M3 MiniMax M2.7
Ceiling ~5.1B tokens/mo · 5h rolling + weekly windows · 4-5 agents
Reachability —
Pricing notes —
Cost rule ~proxy estimate · https://platform.minimax.io/docs/guides/pricing-token-plan — Max capacity and 5h quota + Standard 12% off 1st mo $14.08 first month 11 Billion Credits · 2.7× Lite · unlimited usage, no weekly/5h caps $16.00 $0.0009 — — 18,327 ~1,145 ~1,145 Subscribe ↗ Models
MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.5 Pro MiMo V2.5
Ceiling 11 Billion Credits · 2.7× Lite · unlimited usage, no weekly/5h caps
Reachability —
Pricing notes MiMo V2.5 / V2.5 Pro retire 2026-10-21 (10:00 Beijing) — V2.6 Pro and V2.6 Flash are the forward path
Cost rule ~proxy estimate · https://mimo.mi.com/docs/price/pay-as-you-go — Standard tier multiplier + Lite 12% off 1st mo $5.28 first month 4.1 Billion Credits · unlimited usage · no weekly/5h caps $6.00 $0.0009 — — 6,788 ~1,131 ~1,131 Subscribe ↗ Models
MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.5 Pro MiMo V2.5
Ceiling 4.1 Billion Credits · unlimited usage · no weekly/5h caps
Reachability —
Pricing notes MiMo V2.5 / V2.5 Pro retire 2026-10-21 (10:00 Beijing) — V2.6 Pro and V2.6 Flash are the forward path
Cost rule ~proxy estimate · Xiaomi pricing page (mimo.mi.com/docs/price/pay-as-you-go) + token-plan deduction table (mimo.mi.com/docs/tokenplan/subscription, re-read 2026-09-23) + Plus ~1.7B tokens/mo · 5h rolling + weekly windows · 3-4 agents $20.00 $0.0010 2,702 — 20,419 ~1,021 ~135 Subscribe ↗ Models
MiniMax M3 MiniMax M2.7
Ceiling ~1.7B tokens/mo · 5h rolling + weekly windows · 3-4 agents
Reachability —
Pricing notes —
Cost rule ~proxy estimate · platform.minimax.io/docs/guides/pricing-token-plan + pricing-paygo + GOAT New $70 credits · ~75K reqs/mo · $14/5h · $35/7d $10.00 $0.0029 1,392 3,480 6,960 ~696 ~139 Subscribe ↗ Models
GLM-5.3-Flash GLM-5.2 GLM-5.3 GPT-6 Luna GPT-5.6 Luna GPT-5.6 Sol DeepSeek V4 Pro DeepSeek V4 Flash Hy3 Qwen3.7-Max MiniMax M3 Grok 4.5 Grok 4.6 Grok 4.7 Gemini 3.8 Flash Gemini 3.7 Flash MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.6 Pro UltraSpeed MiMo V2.5 Laguna S 2.1 Qwen3.8-Max Qwen3.7-Plus Qwen3.6-Max-Preview Qwen3.6-Plus MiniMax M2.7 MiniMax M2.5 MiMo V2.5 Pro Kimi K3 Kimi K2.7 Code Kimi K2.7 Code HighSpeed Kimi K2.6 Kimi K2.5 GLM-5.2-Fast GLM-5.1 GLM-5 Nemotron 3 Ultra Step 5 Preview Step 3.7 Flash Step 3.5 Flash Muse Spark 1.2 Muse Spark 1.2 Contributor Muse Spark 1.3 Muse Spark 1.3 Contributor Qwen3.7-Flash Inkling Inkling Small Qwen3.8 Flash Qwen 3.8 27B Hy4 preview DeepSeek V4 Flash Fast DeepSeek V4 Flash Vision Exp DeepSeek V4.1 Flash
Ceiling $70 credits · ~75K reqs/mo · $14/5h · $35/7d
Reachability Any agent · Provider API (GOAT credits) + command-code CLI
Pricing notes —
Cost rule ~proxy estimate · commandcode.ai/docs/resources/pricing-limits — DeepSeek V4 Pro row (off-peak headline, 2026-08-18; -75% promo ended, time-of-day pricing since 2026-08-16) + Pass 2-5× standard API rate limits $9.99 $0.0029 1,044 2,610 5,220 523 105 Subscribe ↗ Models
GLM-5.2 Kimi K3 DeepSeek V4 Pro Kimi K2.7 Code Kimi K2.6 DeepSeek V4 Flash MiMo V2.5 MiMo V2.5 Pro MiniMax M3 Qwen3.8-Max Qwen3.7-Max Qwen3.7-Plus GLM-5.3 GLM-5.3-Flash DeepSeek V4.1 Flash Muse Spark 1.3 Contributor
Ceiling 2-5× standard API rate limits
Reachability Any agent · ClinePass API key
Pricing notes —
Cost rule exact · borrowed cap · docs.cline.bot/getting-started/clinepass — DeepSeek V4 Pro (Off-peak) row ($0.66/$1.98/$0.022 cached read; peak row $1.32/$3.96/$0.044; read 2026-09-24) + Max 20× $300 credits · ~370K reqs/mo · $90/5h · $180/7d $200.00 $0.0029 31,323 62,647 104,413 ~522 ~157 Subscribe ↗ Models
GLM-5.3-Flash DeepSeek V4 Pro DeepSeek V4 Flash GPT-6 Sol GPT-6 Luna GPT-5.6 Luna GPT-5.6 Terra GPT-5.6 Sol GPT-5.5 GPT-5.4 GPT-5.4 Mini GPT-5.3 Codex GPT-6 Astra Claude Opus 5.5 Claude Opus 4.8 Claude Opus 5 Claude Opus 4.7 Claude Opus 4.6 Claude Sonnet 5 Claude Sonnet 4.6 Claude Haiku 4.5 Claude Fable 5.1 Claude Fable 5 Qwen3.7-Max Qwen3.8-Max Qwen3.7-Plus Qwen3.6-Max-Preview Qwen3.6-Plus MiniMax M3 MiniMax M2.7 MiniMax M2.5 MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.6 Pro UltraSpeed MiMo V2.5 MiMo V2.5 Pro Kimi K3 Kimi K2.7 Code Kimi K2.7 Code HighSpeed Kimi K2.6 Kimi K2.5 GLM-5.2 GLM-5.3 GLM-5.2-Fast GLM-5.1 GLM-5 Grok 4.5 Grok 4.6 Grok 4.7 Gemini 3.8 Flash Gemini 3.7 Flash Gemini 3.6 Flash Gemini 3.5 Flash Gemini 3.5 Flash Lite Gemini 3.1 Flash Lite Laguna S 2.1 Hy3 Nemotron 3 Ultra Step 5 Preview Step 3.7 Flash Step 3.5 Flash Fugu Ultra Muse Spark 1.1 Muse Spark 1.2 Muse Spark 1.2 Contributor Muse Spark 1.3 Muse Spark 1.3 Contributor Qwen3.7-Flash Inkling Inkling Small Qwen3.8 Flash Qwen 3.8 27B Hy4 preview DeepSeek V4 Flash Fast DeepSeek V4 Flash Vision Exp DeepSeek V4.1 Flash
Ceiling $300 credits · ~370K reqs/mo · $90/5h · $180/7d
Reachability command-code CLI only
Pricing notes —
Cost rule ~proxy estimate · commandcode.ai/docs/resources/pricing-limits — DeepSeek V4 Pro row (off-peak headline, 2026-08-18; -75% promo ended, time-of-day pricing since 2026-08-16) + Max 10× $150 credits · ~230K reqs/mo · $45/5h · $90/7d $100.00 $0.0029 15,661 31,323 52,206 ~522 ~157 Subscribe ↗ Models
GLM-5.3-Flash DeepSeek V4 Pro DeepSeek V4 Flash GPT-6 Sol GPT-6 Luna GPT-5.6 Luna GPT-5.6 Terra GPT-5.6 Sol GPT-5.5 GPT-5.4 GPT-5.4 Mini GPT-5.3 Codex GPT-6 Astra Claude Opus 5.5 Claude Opus 4.8 Claude Opus 5 Claude Opus 4.7 Claude Opus 4.6 Claude Sonnet 5 Claude Sonnet 4.6 Claude Haiku 4.5 Claude Fable 5.1 Claude Fable 5 Qwen3.7-Max Qwen3.8-Max Qwen3.7-Plus Qwen3.6-Max-Preview Qwen3.6-Plus MiniMax M3 MiniMax M2.7 MiniMax M2.5 MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.6 Pro UltraSpeed MiMo V2.5 MiMo V2.5 Pro Kimi K3 Kimi K2.7 Code Kimi K2.7 Code HighSpeed Kimi K2.6 Kimi K2.5 GLM-5.2 GLM-5.3 GLM-5.2-Fast GLM-5.1 GLM-5 Grok 4.5 Grok 4.6 Grok 4.7 Gemini 3.8 Flash Gemini 3.7 Flash Gemini 3.6 Flash Gemini 3.5 Flash Gemini 3.5 Flash Lite Gemini 3.1 Flash Lite Laguna S 2.1 Hy3 Nemotron 3 Ultra Step 5 Preview Step 3.7 Flash Step 3.5 Flash Fugu Ultra Muse Spark 1.1 Muse Spark 1.2 Muse Spark 1.2 Contributor Muse Spark 1.3 Muse Spark 1.3 Contributor Qwen3.7-Flash Inkling Inkling Small Qwen3.8 Flash Qwen 3.8 27B Hy4 preview DeepSeek V4 Flash Fast DeepSeek V4 Flash Vision Exp DeepSeek V4.1 Flash
Ceiling $150 credits · ~230K reqs/mo · $45/5h · $90/7d
Reachability command-code CLI only
Pricing notes —
Cost rule ~proxy estimate · commandcode.ai/docs/resources/pricing-limits — DeepSeek V4 Pro row (off-peak headline, 2026-08-18; -75% promo ended, time-of-day pricing since 2026-08-16) + Pro $80 credits · ~100K reqs/mo · $16/5h · $40/7d $20.00 $0.0029 2,088 5,220 10,441 ~522 ~104 Subscribe ↗ Models
GLM-5.3-Flash DeepSeek V4 Pro GPT-6 Sol GPT-6 Luna GPT-5.6 Luna Qwen3.7-Max MiniMax M3 Grok 4.5 Grok 4.6 Grok 4.7 MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.6 Pro UltraSpeed MiMo V2.5 Laguna S 2.1 DeepSeek V4 Flash GPT-5.6 Terra GPT-5.6 Sol GPT-5.5 GPT-5.4 GPT-5.4 Mini GPT-5.3 Codex Claude Sonnet 5 Claude Sonnet 4.6 Claude Haiku 4.5 Qwen3.8-Max Qwen3.7-Plus Qwen3.6-Max-Preview Qwen3.6-Plus MiniMax M2.7 MiniMax M2.5 MiMo V2.5 Pro Kimi K3 Kimi K2.7 Code Kimi K2.7 Code HighSpeed Kimi K2.6 Kimi K2.5 GLM-5.2 GLM-5.3 GLM-5.2-Fast GLM-5.1 GLM-5 Gemini 3.8 Flash Gemini 3.7 Flash Gemini 3.6 Flash Gemini 3.5 Flash Gemini 3.5 Flash Lite Gemini 3.1 Flash Lite Hy3 Nemotron 3 Ultra Step 5 Preview Step 3.7 Flash Step 3.5 Flash Muse Spark 1.1 Muse Spark 1.2 Muse Spark 1.2 Contributor Muse Spark 1.3 Muse Spark 1.3 Contributor Qwen3.7-Flash Inkling Inkling Small Qwen3.8 Flash Qwen 3.8 27B Hy4 preview DeepSeek V4 Flash Fast DeepSeek V4 Flash Vision Exp DeepSeek V4.1 Flash
Ceiling $80 credits · ~100K reqs/mo · $16/5h · $40/7d
Reachability command-code CLI only
Pricing notes —
Cost rule ~proxy estimate · commandcode.ai/docs/resources/pricing-limits — DeepSeek V4 Pro row (off-peak headline, 2026-08-18; -75% promo ended, time-of-day pricing since 2026-08-16) + Go $60/mo usage · $30/wk · $12/5h $10.00 $0.0029 1,044 2,610 5,220 522 104 Subscribe ↗ Models
Grok 4.6 Grok 4.7 GLM-5.2 GLM-5.3 GLM-5.3-Flash Kimi K3 GPT-6 Luna GPT-5.6 Luna GLM-5.1 Kimi K2.7 Code Kimi K2.6 LongCat-2.0 MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.5 MiMo V2.5 Pro MiniMax M3 MiniMax M2.7 MiniMax M2.5 Muse Spark 1.2 Contributor Muse Spark 1.3 Contributor Qwen3.8-Max Qwen3.8 Flash Qwen3.7-Max Qwen3.7-Plus Qwen3.6-Plus DeepSeek V4 Pro DeepSeek V4 Flash DeepSeek V4 Flash Vision Exp DeepSeek V4.1 Flash Hy4 preview Hy3
Ceiling $60/mo usage · $30/wk · $12/5h
Reachability Any agent · OpenAI-compatible key
Pricing notes Usage caps: V4.1 Flash $15/mo, V4 Flash $30/mo, V4 Pro $15/mo, Grok 4.7/4.6 $15/mo · retention 0d (Grok 4.7, Grok 4.6, Luna 30d)
Cost rule exact · borrowed cap · opencode.ai/docs/go — DeepSeek V4 Pro (Off-Peak) row ($0.66/$1.98/$0.022 cached read; peak 2× $0.044; read 2026-09-24) + Pro $269/mo compute budget · no 5h/week windows · highest-priority scheduling $249.00 $0.0029 — — 93,623 ~376 ~376 Subscribe ↗ Models
GPT-6 Astra Claude Fable 5.1 Claude Opus 5 Gemini 3.8 Flash Gemini 3.1 Pro Qwen3.8-Max Kimi K3 GLM-5.3 GLM-5.2 GLM-5.3-Flash MiniMax M3 DeepSeek V4.1 Flash DeepSeek V4 Pro DeepSeek V4 Flash
Ceiling $269/mo compute budget · no 5h/week windows · highest-priority scheduling
Reachability Any agent · OpenAI-compatible key
Pricing notes Dollar budget spent at provider list rates — provider claims it does the work of up to $880/mo of direct API spend; no overage charges.
Cost rule ~proxy estimate · opencode.ai/docs/go — DeepSeek V4 Pro (Off-Peak) row ($0.66/$1.98/$0.022 cached read; read 2026-09-24) + Standard $95/mo compute budget · no 5h/week windows · priority scheduling $89.00 $0.0029 — — 33,064 ~372 ~372 Subscribe ↗ Models
GPT-6 Astra Claude Fable 5.1 Claude Opus 5 Gemini 3.8 Flash Gemini 3.1 Pro Qwen3.8-Max Kimi K3 GLM-5.3 GLM-5.2 GLM-5.3-Flash MiniMax M3 DeepSeek V4.1 Flash DeepSeek V4 Pro DeepSeek V4 Flash
Ceiling $95/mo compute budget · no 5h/week windows · priority scheduling
Reachability Any agent · OpenAI-compatible key
Pricing notes Dollar budget spent at provider list rates — provider claims it does the work of up to $310/mo of direct API spend; no overage charges.
Cost rule ~proxy estimate · opencode.ai/docs/go — DeepSeek V4 Pro (Off-Peak) row ($0.66/$1.98/$0.022 cached read; read 2026-09-24) + Starter $20/mo compute budget · no 5h/week windows · one agent at a time $19.00 $0.0029 — — 6,960 ~366 ~366 Subscribe ↗ Models
GPT-6 Astra Claude Fable 5.1 Claude Opus 5 Gemini 3.8 Flash Gemini 3.1 Pro Qwen3.8-Max Kimi K3 GLM-5.3 GLM-5.2 GLM-5.3-Flash MiniMax M3 DeepSeek V4.1 Flash DeepSeek V4 Pro DeepSeek V4 Flash
Ceiling $20/mo compute budget · no 5h/week windows · one agent at a time
Reachability Any agent · OpenAI-compatible key
Pricing notes Dollar budget spent at provider list rates — provider claims it does the work of up to $60/mo of direct API spend; no overage charges.
Cost rule ~proxy estimate · opencode.ai/docs/go — DeepSeek V4 Pro (Off-Peak) row ($0.66/$1.98/$0.022 cached read; read 2026-09-24) + Economy $41/mo compute budget · no 5h/week windows · parallel agents $39.00 $0.0029 — — 14,269 ~366 ~366 Subscribe ↗ Models
GPT-6 Astra Claude Fable 5.1 Claude Opus 5 Gemini 3.8 Flash Gemini 3.1 Pro Qwen3.8-Max Kimi K3 GLM-5.3 GLM-5.2 GLM-5.3-Flash MiniMax M3 DeepSeek V4.1 Flash DeepSeek V4 Pro DeepSeek V4 Flash
Ceiling $41/mo compute budget · no 5h/week windows · parallel agents
Reachability Any agent · OpenAI-compatible key
Pricing notes Dollar budget spent at provider list rates — provider claims it does the work of up to $130/mo of direct API spend; no overage charges.
Cost rule ~proxy estimate · opencode.ai/docs/go — DeepSeek V4 Pro (Off-Peak) row ($0.66/$1.98/$0.022 cached read; read 2026-09-24) + Coding Plan Pro New ~9,500 req/5h · ~60,000/wk · ~120,000/mo · ~3× Claude Max usage · quota shared across tools $50.00 $0.0028 1,399 8,841 17,682 ~354 ~28 Subscribe ↗ Models
Dola Seed 2.0 Pro GLM-5.2 Kimi K2.5 GPT-OSS 120B DeepSeek V4 Flash DeepSeek V4 Pro GLM-5.1
Ceiling ~9,500 req/5h · ~60,000/wk · ~120,000/mo · ~3× Claude Max usage · quota shared across tools
Reachability Any agent · plan-specific key + ark.ap-southeast.bytepluses.com/api/coding base URL
Pricing notes Interactive coding tools only (automated API calls prohibited) · ArkClaw included
Cost rule ~proxy estimate · docs.byteplus.com/en/docs/ModelArk/1544106 — deepseek-v4-pro-260425 row ($1.74/$3.48, cache-hit $0.145) + Coding Plan Lite New ~1,900 req/5h · ~12,000/wk · ~24,000/mo · ~3× Claude Pro usage · quota shared across tools $10.00 $0.0028 279 1,768 3,536 ~354 ~28 Subscribe ↗ Models
Dola Seed 2.0 Pro GLM-5.2 Kimi K2.5 GPT-OSS 120B DeepSeek V4 Flash DeepSeek V4 Pro GLM-5.1
Ceiling ~1,900 req/5h · ~12,000/wk · ~24,000/mo · ~3× Claude Pro usage · quota shared across tools
Reachability Any agent · plan-specific key + ark.ap-southeast.bytepluses.com/api/coding base URL
Pricing notes Interactive coding tools only (automated API calls prohibited)
Cost rule ~proxy estimate · docs.byteplus.com/en/docs/ModelArk/1544106 — deepseek-v4-pro-260425 row ($1.74/$3.48, cache-hit $0.145) + Builder Max 300 Flows / 5h rolling window (6× Starter) · weekly limit · 10-15 RPM $100.00 $0.0029 — — 34,804 ≈348 ≈348 Subscribe ↗ Models
Claude Opus 4.8 GPT-5.6 Sol Claude Sonnet 5 GPT-6 Astra Claude Fable 5.1 Gemini 3.8 Flash Gemini 3.1 Pro GPT-5.5 Qwen3.8-Max Kimi K3 GLM-5.3 MiniMax M3 DeepSeek V4 Pro DeepSeek V4.1 Flash Grok 4.6
Ceiling 300 Flows / 5h rolling window (6× Starter) · weekly limit · 10-15 RPM
Reachability Any agent · OpenAI/Anthropic-compatible key
Pricing notes Basic + premium models, covering the mainstream flagships. Non-production use (personal dev / prototyping — PAYG is the production tier). Flow ≈ $0.03283 (floats live); per-model Flow burn and per-tier model lists are not published in text. Provider "Worth" claim: $180/mo equivalent API value (≈1.8× the fee), from its published equivalent-pay-as-you-go table.
Cost rule ≈coarse estimate · zenmux.ai/api/v1/models — DeepSeek: DeepSeek V4 Pro 0813, off-peak row ($0.66/$1.98/$0.022 cached read; peak row is 2x; read 2026-09-24) + Builder Ultra 800 Flows / 5h rolling window (16× Starter) · weekly limit · 10-15 RPM $200.00 $0.0029 — — 69,608 ≈348 ≈348 Subscribe ↗ Models
Claude Opus 4.8 GPT-5.6 Sol Claude Sonnet 5 GPT-6 Astra Claude Fable 5.1 Gemini 3.8 Flash Gemini 3.1 Pro GPT-5.5 Qwen3.8-Max Kimi K3 GLM-5.3 MiniMax M3 DeepSeek V4 Pro DeepSeek V4.1 Flash Grok 4.6
Ceiling 800 Flows / 5h rolling window (16× Starter) · weekly limit · 10-15 RPM
Reachability Any agent · OpenAI/Anthropic-compatible key
Pricing notes All models (Max and Ultra currently cover nearly identical lists — the difference is quota, not model selection). Non-production use (personal dev / prototyping — PAYG is the production tier). Flow ≈ $0.03283 (floats live); per-model Flow burn and per-tier model lists are not published in text. Provider "Worth" claim: $480/mo equivalent API value (≈2.4× the fee), from its published equivalent-pay-as-you-go table.
Cost rule ≈coarse estimate · zenmux.ai/api/v1/models — DeepSeek: DeepSeek V4 Pro 0813, off-peak row ($0.66/$1.98/$0.022 cached read; peak row is 2x; read 2026-09-24) + Provider PAYG · top-ups roll over, never expire · zero markup $15.00 $0.0029 — — 5,220 ~348 ~348 Subscribe ↗ Models
GLM-5.3-Flash DeepSeek V4 Pro DeepSeek V4 Flash GPT-6 Sol GPT-6 Luna GPT-5.6 Luna GPT-5.6 Terra GPT-5.6 Sol GPT-5.5 GPT-5.4 GPT-5.4 Mini GPT-5.3 Codex GPT-6 Astra Claude Opus 5.5 Claude Opus 4.8 Claude Opus 5 Claude Opus 4.7 Claude Opus 4.6 Claude Sonnet 5 Claude Sonnet 4.6 Claude Haiku 4.5 Claude Fable 5.1 Claude Fable 5 Qwen3.7-Max Qwen3.8-Max Qwen3.7-Plus Qwen3.6-Max-Preview Qwen3.6-Plus MiniMax M3 MiniMax M2.7 MiniMax M2.5 MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.6 Pro UltraSpeed MiMo V2.5 MiMo V2.5 Pro Kimi K3 Kimi K2.7 Code Kimi K2.7 Code HighSpeed Kimi K2.6 Kimi K2.5 GLM-5.2 GLM-5.3 GLM-5.2-Fast GLM-5.1 GLM-5 Grok 4.5 Grok 4.6 Grok 4.7 Gemini 3.8 Flash Gemini 3.7 Flash Gemini 3.6 Flash Gemini 3.5 Flash Gemini 3.5 Flash Lite Gemini 3.1 Flash Lite Laguna S 2.1 Hy3 Nemotron 3 Ultra Step 5 Preview Step 3.7 Flash Step 3.5 Flash Fugu Ultra Muse Spark 1.1 Muse Spark 1.2 Muse Spark 1.2 Contributor Muse Spark 1.3 Muse Spark 1.3 Contributor Qwen3.7-Flash Inkling Inkling Small Qwen3.8 Flash Qwen 3.8 27B Hy4 preview DeepSeek V4 Flash Fast DeepSeek V4 Flash Vision Exp DeepSeek V4.1 Flash
Ceiling PAYG · top-ups roll over, never expire · zero markup
Reachability Any agent · OpenAI/Anthropic-compatible API
Pricing notes —
Cost rule ~proxy estimate · commandcode.ai/docs/resources/pricing-limits — DeepSeek V4 Pro row (off-peak headline, 2026-08-18; -75% promo ended, time-of-day pricing since 2026-08-16) + Builder Starter 50 Flows / 5h rolling window · weekly limit · 10-15 RPM $20.00 $0.0029 — — 6,960 ≈348 ≈348 Subscribe ↗ Models
Claude Opus 4.8 GPT-5.6 Sol Claude Sonnet 5 GPT-6 Astra Claude Fable 5.1 Gemini 3.8 Flash Gemini 3.1 Pro GPT-5.5 Qwen3.8-Max Kimi K3 GLM-5.3 MiniMax M3 DeepSeek V4 Pro DeepSeek V4.1 Flash Grok 4.6
Ceiling 50 Flows / 5h rolling window · weekly limit · 10-15 RPM
Reachability Any agent · OpenAI/Anthropic-compatible key
Pricing notes Basic models plus rotating limited-time premium models. Non-production use (personal dev / prototyping — PAYG is the production tier). Flow ≈ $0.03283 (floats live); per-model Flow burn and per-tier model lists are not published in text. Provider "Worth" claim: $30/mo equivalent API value (≈1.5× the fee), from its published equivalent-pay-as-you-go table.
Cost rule ≈coarse estimate · zenmux.ai/api/v1/models — DeepSeek: DeepSeek V4 Pro 0813, off-peak row ($0.66/$1.98/$0.022 cached read; peak row is 2x; read 2026-09-24) + GLM Coding Max 140,000 Credits / 7 days (14× Lite) · 28,000 Credits / 5 hours $168.00 $0.0042 1,847 9,238 39,591 236 11 Subscribe ↗ Models
GLM-5.3 GLM-5.3-Flash
Ceiling 140,000 Credits / 7 days (14× Lite) · 28,000 Credits / 5 hours
Reachability Limited to officially supported tools (per docs.z.ai/devpack/tool/others) · Anthropic/OpenAI-compatible API key
Pricing notes Legacy GLM-5.2/5.1 auto-routes to GLM-5.3; GLM-4.7 requests auto-route to GLM-5.3-Flash
Cost rule exact · https://docs.z.ai/devpack/overview — Max weekly credit allowance + GLM Coding Pro 60,000 Credits / 7 days (6× Lite) · 12,000 Credits / 5 hours $80.00 $0.0047 791 3,959 16,967 212 10 Subscribe ↗ Models
GLM-5.3 GLM-5.3-Flash
Ceiling 60,000 Credits / 7 days (6× Lite) · 12,000 Credits / 5 hours
Reachability Limited to officially supported tools (per docs.z.ai/devpack/tool/others) · Anthropic/OpenAI-compatible API key
Pricing notes Legacy GLM-5.2/5.1 auto-routes to GLM-5.3; GLM-4.7 requests auto-route to GLM-5.3-Flash
Cost rule exact · https://docs.z.ai/devpack/overview — Pro weekly credit allowance + Max 10 concurrent requests · $300/mo usage credits $100.00 $0.0057 — — 17,402 174 174 Subscribe ↗ Models
GLM-5.3 GLM-5.3-Flash DeepSeek V4 Pro DeepSeek V4 Flash DeepSeek V4.1 Flash Kimi K3 Kimi K2.7 Code Kimi K2.6 MiniMax M3 MiniMax M2.7 GLM-5.2 GLM-5.1 Gemma 4 GPT-OSS 120B GPT-OSS 20B Mistral Large 3 Nemotron 3 Nano Nemotron 3 Super 120B Nemotron 3 Ultra Qwen3.5
Ceiling 10 concurrent requests · $300/mo usage credits
Reachability OpenAI-compatible · Ollama Cloud
Pricing notes —
Cost rule exact · ollama.com/pricing (2026-09-24 dump) — deepseek-v4-pro row ($1.32/$3.96, cached $0.044) + Pro $60/mo usage credits · access to larger pro models $20.00 $0.0057 — — 3,480 174 174 Subscribe ↗ Models
GLM-5.3 GLM-5.3-Flash DeepSeek V4 Pro DeepSeek V4 Flash DeepSeek V4.1 Flash Kimi K3 Kimi K2.7 Code Kimi K2.6 MiniMax M3 MiniMax M2.7 GLM-5.2 GLM-5.1 Gemma 4 GPT-OSS 120B GPT-OSS 20B Mistral Large 3 Nemotron 3 Nano Nemotron 3 Super 120B Nemotron 3 Ultra Qwen3.5
Ceiling $60/mo usage credits · access to larger pro models
Reachability OpenAI-compatible · Ollama Cloud
Pricing notes —
Cost rule exact · ollama.com/pricing (2026-09-24 dump) — deepseek-v4-pro row ($1.32/$3.96, cached $0.044) + GLM Coding Lite 10,000 Credits / 7 days · 2,000 Credits / 5 hours $18.00 $0.0064 131 659 2,824 157 7 Subscribe ↗ Models
GLM-5.3 GLM-5.3-Flash
Ceiling 10,000 Credits / 7 days · 2,000 Credits / 5 hours
Reachability Limited to officially supported tools (per docs.z.ai/devpack/tool/others) · Anthropic/OpenAI-compatible API key
Pricing notes Legacy GLM-5.2/5.1 auto-routes to GLM-5.3; GLM-4.7 requests auto-route to GLM-5.3-Flash
Cost rule exact · docs.z.ai/devpack/overview (credit allowances + model multipliers) + Subscription 60M input tokens/week · 2x on GLM 5/5.1/5.3, Kimi K2.7 Code, DeepSeek V4 Pro/Pro 0813 · 100 images/day $12.00 $0.0077 — — 1,553 ~129 ~129 Subscribe ↗ Models
GLM-5.2 MiniMax M3 DeepSeek V4 Pro GLM-5 GLM-5.1 MiMo V2.5 MiMo V2.5 Pro Kimi K2.7 Code GLM-5.3 GLM-5.3-Flash
Ceiling 60M input tokens/week · 2x on GLM 5/5.1/5.3, Kimi K2.7 Code, DeepSeek V4 Pro/Pro 0813 · 100 images/day
Reachability Any agent · OpenAI-compatible key
Pricing notes Not the best fit for coding agents — large prompts/context burn the weekly cap fast; PAYG safer for heavy coding. Web search is not included in PRO’s subscription coverage.
Cost rule ~proxy estimate · nano-gpt.com/subscription — PRO included model, fair-use cap + Pro Plan -15% off $68/mo 40,000 Credits / 7 days $80.00 $0.0091 612 2,041 8,747 ~109 ~8 Subscribe ↗ Models
Qwen3.8-Max Qwen3.7-Max Qwen3.7-Plus Qwen3.6-Flash GLM-5.2 DeepSeek V4 Pro DeepSeek V4 Flash Qwen3.8 Flash GLM-5.3 DeepSeek V4.1 Flash
Ceiling 40,000 Credits / 7 days
Reachability —
Pricing notes —
Cost rule ~proxy estimate · qwencloud.com/models/deepseek-v4-pro — list row + Standard Plan -28% off $18/mo 10,000 Credits / 7 days $25.00 $0.0114 153 510 2,185 ~87 ~6 Subscribe ↗ Models
Qwen3.8-Max Qwen3.7-Max Qwen3.7-Plus Qwen3.6-Flash GLM-5.2 DeepSeek V4 Pro DeepSeek V4 Flash Qwen3.8 Flash GLM-5.3 DeepSeek V4.1 Flash
Ceiling 10,000 Credits / 7 days
Reachability —
Pricing notes —
Cost rule ~proxy estimate · qwencloud.com/models/deepseek-v4-pro — list row + Pro $70 in credits/mo · + Smart Compression, Analytics Pro, Privacy Pack, 10 extra API keys, Custom Router, Fusion $35.00 $0.0236 — — 2,970 ~≥85 ~≥85 Subscribe ↗ Models
GPT-6 Astra Claude Fable 5.1 Claude Opus 5.5 Claude Opus 5 GPT-6 Sol GPT-6 Luna GPT-5.6 Sol Gemini 3.8 Flash Gemini 3.7 Flash GLM-5.3 DeepSeek V4 Pro MiniMax M3 MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.5 Pro Grok 4.6 Grok 4.7 GLM-5.3-Flash DeepSeek V4.1 Flash Hy3 Nemotron 3 Ultra GPT-5.5 Claude Opus 4.7 Claude Sonnet 5 Claude Sonnet 4.6 GPT-5.4 Kimi K3 Gemini 3.5 Flash GLM-5.1 Kimi K2.6 Grok Build GPT-5.6 Luna GPT-5.6 Terra Claude Fable 5 GLM-5.2 GLM-5-Turbo Grok 4.3 Grok 4.5 Kimi K2.7 Code Muse Spark 1.1 Muse Spark 1.3 Contributor Qwen3.7-Max Gemini 3.6 Flash Gemini 3.1 Pro Fugu Ultra Claude Opus 4.8 MiMo V2.5 DeepSeek V4 Flash MiniMax M2.7 Gemini 3.1 Flash Lite Gemini 3.5 Flash Lite GPT-5.4 Nano GPT-OSS 120B Step 3.5 Flash Step 3.7 Flash Nex N2 Pro Mistral Small 4 Trinity Large Thinking Agnes 2.0 Flash North Mini Code Ling 3.0 Flash
Ceiling $70 in credits/mo · + Smart Compression, Analytics Pro, Privacy Pack, 10 extra API keys, Custom Router, Fusion
Reachability Any agent · OpenAI-compatible key
Pricing notes Includes Custom Router, so you can pin a lineup and Ozore routes only among your picks. Cached-read pricing is not published, so the calculator estimates it at 10% of the input rate.
Cost rule ~proxy estimate · floor: cached reads bill at the input rate · ozore.com/api/credits/pricing (live 2026-09-22, billed row deepseek/deepseek-v4-pro $0.2828/0.5655 per 1M = 35% off list $0.435/0.87 — the pricing hero table rounds this to $0.28/$0.57); cached-read not published → cached tokens billed at the input rate + Basic $20 in credits/mo · spend on any model at discounted rates · cancel anytime $10.00 $0.0236 — — 848 ~≥85 ~≥85 Subscribe ↗ Models
GPT-6 Astra Claude Fable 5.1 Claude Opus 5.5 Claude Opus 5 GPT-6 Sol GPT-6 Luna GPT-5.6 Sol Gemini 3.8 Flash Gemini 3.7 Flash GLM-5.3 DeepSeek V4 Pro MiniMax M3 MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.5 Pro Grok 4.6 Grok 4.7 GLM-5.3-Flash DeepSeek V4.1 Flash Hy3 Nemotron 3 Ultra GPT-5.5 Claude Opus 4.7 Claude Sonnet 5 Claude Sonnet 4.6 GPT-5.4 Kimi K3 Gemini 3.5 Flash GLM-5.1 Kimi K2.6 Grok Build GPT-5.6 Luna GPT-5.6 Terra Claude Fable 5 GLM-5.2 GLM-5-Turbo Grok 4.3 Grok 4.5 Kimi K2.7 Code Muse Spark 1.1 Muse Spark 1.3 Contributor Qwen3.7-Max Gemini 3.6 Flash Gemini 3.1 Pro Fugu Ultra Claude Opus 4.8 MiMo V2.5 DeepSeek V4 Flash MiniMax M2.7 Gemini 3.1 Flash Lite Gemini 3.5 Flash Lite GPT-5.4 Nano GPT-OSS 120B Step 3.5 Flash Step 3.7 Flash Nex N2 Pro Mistral Small 4 Trinity Large Thinking Agnes 2.0 Flash North Mini Code Ling 3.0 Flash
Ceiling $20 in credits/mo · spend on any model at discounted rates · cancel anytime
Reachability Any agent · OpenAI-compatible key
Pricing notes Requests are auto-routed — you do not pick the model, so a per-model figure is an upper bound on this tier; Direct Pin and Custom Router are Pro features. Cached-read pricing is not published, so the calculator estimates it at 10% of the input rate.
Cost rule ~proxy estimate · floor: cached reads bill at the input rate · ozore.com/api/credits/pricing (live 2026-09-22, billed row deepseek/deepseek-v4-pro $0.2828/0.5655 per 1M = 35% off list $0.435/0.87 — the pricing hero table rounds this to $0.28/$0.57); cached-read not published → cached tokens billed at the input rate + Essential Plan -37.5% off $10/mo 5,625 Credits / 7 days $16.00 $0.0130 80 287 1,230 ~77 ~5 Subscribe ↗ Models
Qwen3.8-Max Qwen3.7-Max Qwen3.7-Plus Qwen3.6-Flash GLM-5.2 DeepSeek V4 Pro DeepSeek V4 Flash Qwen3.8 Flash GLM-5.3 DeepSeek V4.1 Flash
Ceiling 5,625 Credits / 7 days
Reachability —
Pricing notes —
Cost rule ~proxy estimate · qwencloud.com/models/deepseek-v4-pro — list row + Lite Plan -25% off $6/mo 2,500 Credits / 7 days $8.00 $0.0147 35 127 544 ~68 ~4 Subscribe ↗ Models
Qwen3.8-Max Qwen3.7-Max Qwen3.7-Plus Qwen3.6-Flash GLM-5.2 DeepSeek V4 Pro DeepSeek V4 Flash Qwen3.8 Flash GLM-5.3 DeepSeek V4.1 Flash
Ceiling 2,500 Credits / 7 days
Reachability —
Pricing notes —
Cost rule ~proxy estimate · qwencloud.com/models/deepseek-v4-pro — list row + Ultra ~665M tokens/mo (3.3B+ light) · 7 agents $99.00 $0.0258 — — 3,831 ~39 ~39 Subscribe ↗ Models
GLM-5.2 GLM-5.3 DeepSeek V4.1 Flash GLM-5.3-Flash Qwen 3.8 2.4T Kimi K3 DeepSeek V4 Flash DeepSeek V4 Pro Kimi K2.7 Code Kimi K2.6 MiniMax M3 Qwen 3.8 27B MiMo V2.5 MiMo V2.5 Pro Nemotron 3 Ultra Nemotron 3 Super 120B Gemma 4 31B
Ceiling ~665M tokens/mo (3.3B+ light) · 7 agents
Reachability Any agent · OpenAI-compatible key
Pricing notes 8× Basic headroom
Cost rule ~proxy estimate · api.pgsgrove.com/docs/usage-rates — relative-draw table row "deepseek-v4-pro / -0813" (2.09x) + Elite ~335M tokens/mo (1.8B+ light) · 6 agents $50.00 $0.0259 — — 1,930 ~39 ~39 Subscribe ↗ Models
GLM-5.2 GLM-5.3 DeepSeek V4.1 Flash GLM-5.3-Flash Qwen 3.8 2.4T Kimi K3 DeepSeek V4 Flash DeepSeek V4 Pro Kimi K2.7 Code Kimi K2.6 MiniMax M3 Qwen 3.8 27B MiMo V2.5 MiMo V2.5 Pro Nemotron 3 Ultra Nemotron 3 Super 120B Gemma 4 31B
Ceiling ~335M tokens/mo (1.8B+ light) · 6 agents
Reachability Any agent · OpenAI-compatible key
Pricing notes 4× Basic headroom
Cost rule ~proxy estimate · api.pgsgrove.com/docs/usage-rates — relative-draw table row "deepseek-v4-pro / -0813" (2.09x) + Canopy ~1.3B tokens/mo (6.6B+ light) · 8 agents $195.00 $0.0260 — — 7,490 ~38 ~38 Subscribe ↗ Models
GLM-5.2 GLM-5.3 DeepSeek V4.1 Flash GLM-5.3-Flash Qwen 3.8 2.4T Kimi K3 DeepSeek V4 Flash DeepSeek V4 Pro Kimi K2.7 Code Kimi K2.6 MiniMax M3 Qwen 3.8 27B MiMo V2.5 MiMo V2.5 Pro Nemotron 3 Ultra Nemotron 3 Super 120B Gemma 4 31B
Ceiling ~1.3B tokens/mo (6.6B+ light) · 8 agents
Reachability Any agent · OpenAI-compatible key
Pricing notes 16× Basic headroom · the most headroom PGS sells
Cost rule ~proxy estimate · api.pgsgrove.com/docs/usage-rates — relative-draw table row "deepseek-v4-pro / -0813" (2.09x) + Pro ~165M tokens/mo (890M+ light) · 5 agents $25.00 $0.0263 — — 950 ~38 ~38 Subscribe ↗ Models
GLM-5.2 GLM-5.3 DeepSeek V4.1 Flash GLM-5.3-Flash Qwen 3.8 2.4T Kimi K3 DeepSeek V4 Flash DeepSeek V4 Pro Kimi K2.7 Code Kimi K2.6 MiniMax M3 Qwen 3.8 27B MiMo V2.5 MiMo V2.5 Pro Nemotron 3 Ultra Nemotron 3 Super 120B Gemma 4 31B
Ceiling ~165M tokens/mo (890M+ light) · 5 agents
Reachability Any agent · OpenAI-compatible key
Pricing notes 2× Basic headroom · highlight tier
Cost rule ~proxy estimate · api.pgsgrove.com/docs/usage-rates — relative-draw table row "deepseek-v4-pro / -0813" (2.09x) + Basic ~85M tokens/mo (450M+ light) · 3 agents $12.95 $0.0265 — — 489 ~38 ~38 Subscribe ↗ Models
GLM-5.2 GLM-5.3 DeepSeek V4.1 Flash GLM-5.3-Flash Qwen 3.8 2.4T Kimi K3 DeepSeek V4 Flash DeepSeek V4 Pro Kimi K2.7 Code Kimi K2.6 MiniMax M3 Qwen 3.8 27B MiMo V2.5 MiMo V2.5 Pro Nemotron 3 Ultra Nemotron 3 Super 120B Gemma 4 31B
Ceiling ~85M tokens/mo (450M+ light) · 3 agents
Reachability Any agent · OpenAI-compatible key
Pricing notes The baseline · standard-model monthly allowance + ~5× larger light-model budget
Cost rule ~proxy estimate · api.pgsgrove.com/docs/usage-rates — relative-draw table row "deepseek-v4-pro / -0813" (2.09x) + Ultra $220 credits/mo · $100 rollover $200.00 $0.0527 — — 3,793 ~≥19 ~≥19 Subscribe ↗ Models
Claude Opus 5.5 Claude Opus 5 GPT-6 Sol GPT-6 Luna GPT-5.6 Sol Gemini 3.7 Flash Claude Opus 4.7 GPT-5.5 Gemini 3.1 Pro Grok 4.5 Grok 4.6 Grok 4.7 GPT-5.6 Luna GPT-5.6 Terra GPT-6 Astra GLM-5-Turbo GLM-5.1 GLM-5.3-Flash GLM-4.7 Kimi K2.6 Kimi K2.7 Code MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.6 Pro UltraSpeed MiMo V2.5 MiMo V2.5 Pro MiniMax M3 MiniMax M2.7 MiniMax M2.5 Qwen3.6-Plus Qwen3.7-Max Qwen3.7-Plus DeepSeek V4 Pro DeepSeek V4 Flash DeepSeek V4.1 Flash Hy3
Ceiling $220 credits/mo · $100 rollover
Reachability OAuth (Hermes) or NOUS key
Pricing notes —
Cost rule ~proxy estimate · floor: cached reads bill at the input rate · inference-api.nousresearch.com/v1/models — deepseek/deepseek-v4-pro row (2026-09-08) + Super $110 credits/mo · $50 rollover $100.00 $0.0527 — — 1,896 ~≥19 ~≥19 Subscribe ↗ Models
Claude Opus 5.5 Claude Opus 5 GPT-6 Sol GPT-6 Luna GPT-5.6 Sol Gemini 3.7 Flash Claude Opus 4.7 GPT-5.5 Gemini 3.1 Pro Grok 4.5 Grok 4.6 Grok 4.7 GPT-5.6 Luna GPT-5.6 Terra GPT-6 Astra GLM-5-Turbo GLM-5.1 GLM-5.3-Flash GLM-4.7 Kimi K2.6 Kimi K2.7 Code MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.6 Pro UltraSpeed MiMo V2.5 MiMo V2.5 Pro MiniMax M3 MiniMax M2.7 MiniMax M2.5 Qwen3.6-Plus Qwen3.7-Max Qwen3.7-Plus DeepSeek V4 Pro DeepSeek V4 Flash DeepSeek V4.1 Flash Hy3
Ceiling $110 credits/mo · $50 rollover
Reachability OAuth (Hermes) or NOUS key
Pricing notes —
Cost rule ~proxy estimate · floor: cached reads bill at the input rate · inference-api.nousresearch.com/v1/models — deepseek/deepseek-v4-pro row (2026-09-08) + Plus $22 credits/mo · $10 rollover $20.00 $0.0527 — — 379 ~≥19 ~≥19 Subscribe ↗ Models
Claude Opus 5.5 Claude Opus 5 GPT-6 Sol GPT-6 Luna GPT-5.6 Sol Gemini 3.7 Flash Claude Opus 4.7 GPT-5.5 Gemini 3.1 Pro Grok 4.5 Grok 4.6 Grok 4.7 GPT-5.6 Luna GPT-5.6 Terra GPT-6 Astra GLM-5-Turbo GLM-5.1 GLM-5.3-Flash GLM-4.7 Kimi K2.6 Kimi K2.7 Code MiMo V2.6 Pro MiMo V2.6 Flash MiMo V2.6 Pro UltraSpeed MiMo V2.5 MiMo V2.5 Pro MiniMax M3 MiniMax M2.7 MiniMax M2.5 Qwen3.6-Plus Qwen3.7-Max Qwen3.7-Plus DeepSeek V4 Pro DeepSeek V4 Flash DeepSeek V4.1 Flash Hy3
Ceiling $22 credits/mo · $10 rollover
Reachability OAuth (Hermes) or NOUS key
Pricing notes —
Cost rule ~proxy estimate · floor: cached reads bill at the input rate · inference-api.nousresearch.com/v1/models — deepseek/deepseek-v4-pro row (2026-09-08) + Taster Free 1st mo First month free ~18M Flash tokens/mo · first month free $3.99 n/a — — n/a n/a n/a Subscribe ↗ Models
DeepSeek V4 Flash GLM-5.3-Flash
Ceiling ~18M Flash tokens/mo · first month free
Reachability Any agent · OpenAI-compatible key
Pricing notes Bills $3.99/mo after the free month · cancel anytime · entry tier (Flash-tier models) · one free trial month per person, duplicate trial accounts will be canceled
Cost rule n/a + Plus 2× limits · 400 GB storage $4.99 n/a — — n/a n/a n/a Subscribe ↗ Models
Gemini 3.1 Pro Gemini Omni Flash
Ceiling 2× limits · 400 GB storage
Reachability —
Pricing notes —
Cost rule n/a + Everyday Usage 10–50 prompts / 5h (incl. image & video uploads) $5.00 n/a — — n/a n/a n/a Subscribe ↗
Ceiling 10–50 prompts / 5h (incl. image & video uploads)
Reachability Muse Code CLI only
Pricing notes Price confirmed on the provider product page 2026-09-25 (dev.meta.ai/products/muse-code) · Everyday Usage: 10–50 prompts/5h incl. image & video uploads
Cost rule n/a + Stream Unlimited tokens · 1 concurrent generation per stream (extra requests queue — queue waits unbounded, waits can be capped/dropped; 1–50 streams) · 260K context guaranteed $5.00 n/a — — n/a n/a n/a Subscribe ↗ Models
GPT-5.6 Luna Muse Spark 1.3 GLM-5.3-Flash DeepSeek V4.1 Flash
Ceiling Unlimited tokens · 1 concurrent generation per stream (extra requests queue — queue waits unbounded, waits can be capped/dropped; 1–50 streams) · 260K context guaranteed
Reachability Any agent · OpenAI/Anthropic-compatible key
Pricing notes Meterless: no per-token rates are published, so there is no cost-rule basis. Model ID is "auto" — the model cannot be picked; the fleet rotates (live fleet listed here, the docs page is the authoritative list). The flat price is subsidized by a training/advertising licence over prompts and outputs (no opt-out).
Cost rule n/a + Go Expanded messages · may include ads $8.00 n/a — — n/a n/a n/a Subscribe ↗ Models
GPT-6 Luna GPT-5.6 Luna
Ceiling Expanded messages · may include ads
Reachability —
Pricing notes Codex: GPT-6 Luna at Standard speed in the desktop app (subject to rollout) — Go does not get GPT-6 Sol
Cost rule n/a + Plus $50/mo usage (5× price) · 2,000 req/day · $4.17/4h burst · 6% off PAYG beyond $10.00 n/a — — n/a n/a n/a Subscribe ↗ Models
GLM-5.2 Kimi K2.6 Qwen3.5 Mistral-Nemo-Instruct-2407 Qwen3-32B Gemma 4 31B Turbo MiniMax M2.5 Qwen3-235B-A22B-Thinking-2507 Qwen3.6-27B Kimi K2.5 DeepSeek V3.2 DeepSeek V4 Flash GLM-5 GLM-5.1
Ceiling $50/mo usage (5× price) · 2,000 req/day · $4.17/4h burst · 6% off PAYG beyond
Reachability Any agent · OpenAI-compatible key
Pricing notes —
Cost rule n/a + Pro $15/mo total AI credits · unlimited completions $10.00 n/a — — n/a n/a n/a Subscribe ↗ Models
Claude Sonnet 5 GPT-5.6 Terra Gemini 3.7 Flash Grok 4.6 Kimi K3 Claude Haiku 4.5 Claude Sonnet 4.6 GPT-5.4 GPT-5.4 Mini Gemini 3.6 Flash Gemini 3.5 Flash Grok 4.5 Kimi K2.7 Code
Ceiling $15/mo total AI credits · unlimited completions
Reachability —
Pricing notes —
Cost rule n/a + SuperGrok Lite $10.00 n/a — — n/a n/a n/a Subscribe ↗
Ceiling —
Reachability —
Pricing notes —
Cost rule n/a + Pro Fair usage · up to 6× Free · 150 Flash answers/day $14.99 n/a — — n/a n/a n/a Subscribe ↗ Models
Mistral Medium 3.5 Mistral Small 4 Mistral Large 3 Codestral Ministral 3 14B Ministral 3 8B Ministral 3 3B
Ceiling Fair usage · up to 6× Free · 150 Flash answers/day
Reachability Vibe web/CLI/IDE (own client) · API PAYG separate
Pricing notes —
Cost rule n/a + High Usage 5× Everyday (≈50–250 prompts/5h) $15.00 n/a — — n/a n/a n/a Subscribe ↗
Ceiling 5× Everyday (≈50–250 prompts/5h)
Reachability Muse Code CLI only
Pricing notes Price confirmed on the provider product page 2026-09-25 (dev.meta.ai/products/muse-code) · High Usage: 5× Everyday usage, more prompts with the latest Muse models
Cost rule n/a + Builder Flat-rate · ~3-4 coding agents · 128K context · best-effort capacity · fair use $19.00 n/a — — n/a n/a n/a Subscribe ↗
Ceiling Flat-rate · ~3-4 coding agents · 128K context · best-effort capacity · fair use
Reachability Any agent · OpenAI-compatible key
Pricing notes Flat-rate — no per-token meter; ~3-4 coding agents, 128K context
Cost rule n/a + Pro 4× limits · 5 TB storage $19.99 n/a — — n/a n/a n/a Subscribe ↗ Models
Gemini 3.1 Pro Gemini 3 Pro Gemini Omni Flash Gemini Spark
Ceiling 4× limits · 5 TB storage
Reachability —
Pricing notes —
Cost rule n/a + Pro ≥5× Free · 5h rolling window + weekly cap $20.00 n/a — — n/a n/a n/a Subscribe ↗ Models
Claude Fable 5.1 Claude Fable 5 Claude Sonnet 5 Claude Opus 5.5
Ceiling ≥5× Free · 5h rolling window + weekly cap
Reachability —
Pricing notes —
Cost rule n/a + Pro $100/mo usage (5× price) · 5,000 req/day · $8.33/4h burst · 10% off PAYG beyond $20.00 n/a — — n/a n/a n/a Subscribe ↗ Models
GLM-5.2 Kimi K2.6 Qwen3.5 Mistral-Nemo-Instruct-2407 Qwen3-32B Gemma 4 31B Turbo MiniMax M2.5 Qwen3-235B-A22B-Thinking-2507 Qwen3.6-27B Kimi K2.5 DeepSeek V3.2 DeepSeek V4 Flash GLM-5 GLM-5.1
Ceiling $100/mo usage (5× price) · 5,000 req/day · $8.33/4h burst · 10% off PAYG beyond
Reachability Any agent · OpenAI-compatible key
Pricing notes —
Cost rule n/a + Pro $20/mo API pool + Cursor Models pool $20.00 n/a — — n/a n/a n/a Subscribe ↗ Models
Grok 4.5 Grok 4.6 Grok 4.7 Composer 2.5 Claude Opus 5.5 Claude Opus 5 Claude Sonnet 5 Claude Fable 5.1 Claude Fable 5 GPT-5.6 Luna GPT-5.6 Sol GPT-5.6 Terra Gemini 3.1 Pro Gemini 3.8 Flash Gemini 3.7 Flash Muse Spark 1.3
Ceiling $20/mo API pool + Cursor Models pool
Reachability Cursor IDE / CLI / cloud agents only
Pricing notes —
Cost rule n/a + Basic 2.35 kWh/mo energy incl. $20.00 n/a — — n/a n/a n/a Subscribe ↗ Models
DeepSeek V4 Flash GLM-5.2 Kimi K2.7 Code Gemma 4 31B Qwen3.6-35B GLM-5.3 Kimi K3 Qwen 3.8 27B
Ceiling 2.35 kWh/mo energy incl.
Reachability Any agent · OpenAI-compatible API key
Pricing notes Energy-based billing — kWh allocation incl.
Cost rule n/a + Plus Unlimited* messages (reasonable use) $20.00 n/a — — n/a n/a n/a Subscribe ↗ Models
GPT-6 Astra GPT-6 Sol GPT-6 Luna GPT-5.6 Sol GPT-5.5 GPT-5.6 Terra GPT-5.6 Luna
Ceiling Unlimited* messages (reasonable use)
Reachability —
Pricing notes Codex limits (messages): GPT-6 Luna 350–3,000 = highest · GPT-6 Sol 15–150 · GPT-5.6 Luna 250–2,000 · GPT-5.6 Sol 10–100 · Terra 25–200 · Astra 5–45 · weekly limits may also apply · Luna Reserve = extra Luna-only usage once the regular weekly cap is exhausted (selected Plus accounts, own limit)
Cost rule n/a + Subscription 500 requests/5h per pack · 1 concurrent request per model · +500 req/5h per $30 pack (max 5 packs) $30.00 n/a — — n/a n/a n/a Subscribe ↗ Models
Kimi K3 DeepSeek V4.1 Flash Nemotron 3 Super 120B Qwen3.8-27B GPT-OSS 120B GLM-4.7-Flash GLM-5.3-Flash
Ceiling 500 requests/5h per pack · 1 concurrent request per model · +500 req/5h per $30 pack (max 5 packs)
Reachability Any agent · OpenAI-compatible key
Pricing notes —
Cost rule n/a + SuperGrok $30.00 n/a — — n/a n/a n/a Subscribe ↗
Ceiling —
Reachability —
Pricing notes Grok Bot access is included (not on Lite): link the Grok or X account to grant weekly Grok Bot usage on a Cursor account — cursor.com/help/grok-bot/plans
Cost rule n/a + Pro+ $70/mo total AI credits · 4× Pro usage $39.00 n/a — — n/a n/a n/a Subscribe ↗ Models
Claude Opus 5 GPT-5.6 Sol Gemini 3.7 Flash Claude Sonnet 5 Claude Fable 5.1 Claude Fable 5 Grok 4.6 Kimi K3 GPT-5.6 Terra GPT-5.6 Luna GPT-5.5 GPT-5.4 Claude Opus 4.8 Claude Opus 4.7 Claude Haiku 4.5 Claude Sonnet 4.6 Kimi K2.7 Code Gemini 3.6 Flash Gemini 3.5 Flash Grok 4.5 GPT-5 Mini GPT-5.4 Mini
Ceiling $70/mo total AI credits · 4× Pro usage
Reachability —
Pricing notes —
Cost rule n/a + Pro Flat-rate · ~5-6 coding agents · 256K context · best-effort capacity · fair use $39.00 n/a — — n/a n/a n/a Subscribe ↗
Ceiling Flat-rate · ~5-6 coding agents · 256K context · best-effort capacity · fair use
Reachability Any agent · OpenAI-compatible key
Pricing notes Flat-rate — no per-token meter; ~5-6 coding agents, 256K context
Cost rule n/a + Standard 6.25 kWh/mo energy incl. · priority $50.00 n/a — — n/a n/a n/a Subscribe ↗ Models
DeepSeek V4 Flash GLM-5.2 Kimi K2.7 Code Gemma 4 31B Qwen3.6-35B GLM-5.3 Kimi K3 Qwen 3.8 27B
Ceiling 6.25 kWh/mo energy incl. · priority
Reachability Any agent · OpenAI-compatible API key
Pricing notes Energy-based billing — kWh allocation incl.
Cost rule n/a + Power Usage 20× Everyday (≈200–1000 prompts/5h) $50.00 n/a — — n/a n/a n/a Subscribe ↗
Ceiling 20× Everyday (≈200–1000 prompts/5h)
Reachability Muse Code CLI only
Pricing notes Price confirmed on the provider product page 2026-09-25 (dev.meta.ai/products/muse-code) · Power Usage: 20× Everyday usage, early access to new features
Cost rule n/a + Pro+ $70/mo API pool + Cursor Models pool $60.00 n/a — — n/a n/a n/a Subscribe ↗ Models
Grok 4.5 Grok 4.6 Grok 4.7 Composer 2.5 Claude Opus 5.5 Claude Opus 5 Claude Sonnet 5 Claude Fable 5.1 Claude Fable 5 GPT-5.6 Luna GPT-5.6 Sol GPT-5.6 Terra Gemini 3.1 Pro Gemini 3.8 Flash Gemini 3.7 Flash Muse Spark 1.3
Ceiling $70/mo API pool + Cursor Models pool
Reachability Cursor IDE / CLI / cloud agents only
Pricing notes Grok Bot bundled since Aug 21 2026 — dedicated weekly usage pool, separate from Cursor model pools
Cost rule n/a + Ultra 5x 5× Pro · 20 TB storage $99.99 n/a — — n/a n/a n/a Subscribe ↗ Models
Gemini 3.1 Pro Gemini 3 Pro Deep Think Gemini Spark Gemini Omni Flash
Ceiling 5× Pro · 20 TB storage
Reachability —
Pricing notes —
Cost rule n/a + Max 5x 5× Pro $100.00 n/a — — n/a n/a n/a Subscribe ↗ Models
Claude Fable 5.1 Claude Fable 5 Claude Opus 5.5 Claude Opus 4.8
Ceiling 5× Pro
Reachability —
Pricing notes —
Cost rule n/a + Max $200/mo total AI credits · 2.9× Pro+ usage $100.00 n/a — — n/a n/a n/a Subscribe ↗ Models
Claude Opus 5 GPT-5.6 Sol Gemini 3.7 Flash Claude Sonnet 5 Claude Fable 5.1 Claude Fable 5 Grok 4.6 Kimi K3 GPT-5.6 Terra GPT-5.6 Luna GPT-5.5 GPT-5.4 Claude Opus 4.8 Claude Opus 4.7 Claude Haiku 4.5 Claude Sonnet 4.6 Kimi K2.7 Code Gemini 3.6 Flash Gemini 3.5 Flash Grok 4.5 GPT-5 Mini GPT-5.4 Mini
Ceiling $200/mo total AI credits · 2.9× Pro+ usage
Reachability —
Pricing notes —
Cost rule n/a + Pro 13.33 kWh/mo energy incl. · highest priority $100.00 n/a — — n/a n/a n/a Subscribe ↗ Models
DeepSeek V4 Flash GLM-5.2 Kimi K2.7 Code Gemma 4 31B Qwen3.6-35B GLM-5.3 Kimi K3 Qwen 3.8 27B
Ceiling 13.33 kWh/mo energy incl. · highest priority
Reachability Any agent · OpenAI-compatible API key
Pricing notes Energy-based billing — kWh allocation incl.
Cost rule n/a + Pro 5x 5× Plus $100.00 n/a — — n/a n/a n/a Subscribe ↗ Models
GPT-6 Astra GPT-6 Sol GPT-6 Luna GPT-5.6 Sol Pro GPT-5.6 Sol GPT-5.6 Terra GPT-5.6 Luna
Ceiling 5× Plus
Reachability —
Pricing notes Codex limits (Pro 5×, messages): GPT-6 Luna 1,750–14,000 = highest · GPT-6 Sol 70–700 · GPT-5.6 Luna 1,250–10,000 · GPT-5.6 Sol 50–500 · Terra 125–1,000 · Astra 25–225 · weekly limits may also apply
Cost rule n/a + SuperGrok Plus $100.00 n/a — — n/a n/a n/a Subscribe ↗
Ceiling —
Reachability —
Pricing notes —
Cost rule n/a + Ultra 20x 20× Pro · 30 TB storage $199.99 n/a — — n/a n/a n/a Subscribe ↗ Models
Gemini 3.1 Pro Gemini 3 Pro Deep Think Gemini Spark Gemini Omni Flash
Ceiling 20× Pro · 30 TB storage
Reachability —
Pricing notes —
Cost rule n/a + Max 20x 20× Pro $200.00 n/a — — n/a n/a n/a Subscribe ↗ Models
Claude Fable 5.1 Claude Fable 5 Claude Opus 5.5 Claude Opus 4.8
Ceiling 20× Pro
Reachability —
Pricing notes —
Cost rule n/a + Ultra $400/mo API pool + Cursor Models pool $200.00 n/a — — n/a n/a n/a Subscribe ↗ Models
Grok 4.5 Grok 4.6 Grok 4.7 Composer 2.5 Claude Opus 5.5 Claude Opus 5 Claude Sonnet 5 Claude Fable 5.1 Claude Fable 5 GPT-5.6 Luna GPT-5.6 Sol GPT-5.6 Terra Gemini 3.1 Pro Gemini 3.8 Flash Gemini 3.7 Flash Muse Spark 1.3
Ceiling $400/mo API pool + Cursor Models pool
Reachability Cursor IDE / CLI / cloud agents only
Pricing notes —
Cost rule n/a + Pro 20x 20× Plus $200.00 n/a — — n/a n/a n/a Subscribe ↗ Models
GPT-6 Astra GPT-6 Sol GPT-6 Luna GPT-5.6 Sol Pro GPT-5.6 Sol GPT-5.6 Terra GPT-5.6 Luna
Ceiling 20× Plus
Reachability —
Pricing notes Codex limits (Pro 20×, messages): GPT-6 Luna 7,000–56,000 = highest · GPT-6 Sol 300–3,000 · GPT-5.6 Luna 5,000–40,000 · GPT-5.6 Sol 200–2,000 · Terra 500–4,000 · Astra 100–900 · weekly limits may also apply
Cost rule n/a + SuperGrok Heavy $300.00 n/a — — n/a n/a n/a Subscribe ↗
Ceiling —
Reachability —
Pricing notes Grok Bot access is included; linking SuperGrok Heavy grants the highest linked weekly Grok Bot usage on a Cursor account (cursor.com/help/grok-bot/supergrok) — a usage grant, not a Cursor plan, and no extra usage on top of one.
Cost rule n/a No plans match your filters.