OpenCode

Price/mo (USD)

$0

source · verified 2026-10-18

Homepage FAQ: OpenCode is 100% free to use and includes free models. Additional cost if you connect another provider.

Usage limits

Free models include Big Pickle plus promotional models available at the time. Daily request quota: Unverified

source · verified 2026-10-28

The 200 requests/day figure no longer appears on https://opencode.ai/go or the Console docs as of 2026-10-28, so the quota is marked Unverified rather than guessed.

Overflow / pay-as-you-go

Not published

source · verified 2026-10-28

not published by vendor. FAQ does not say what happens after. Homepage FAQ says other providers can add cost.

Models

Big Pickle, Iceman Free, Inkling 2 Small Free, GLM-5.3-Flash Free, DeepSeek V4.1 Flash Free, MiniMax M3.1 Flash Free, Beam Free, Flint 40B Free, LongCat 2.5 Free, MiMo-V2.6-Flash Free, Nemotron 3 Ultra Free, Nemotron 3.5 Lightning Free, Nemotron 3.5 Super VL Free, Jev 1.13 Free

source · verified 2026-11-12

Priced Free per 1M tokens on the Console models page. Several are free for a limited time. LongCat 2.5 Free has a limit of 100 requests per day and is hosted in China. Bring-your-own providers are separate. Pulse Alpha Free (deprecated November 6, 2026) and Crouton Alpha Free (deprecated November 9, 2026) remain in the page's Deprecated models table and are not on the active free list.

Price/mo (USD)

Not published

source · verified 2026-10-18

Not a monthly subscription. Add a $20 pay-as-you-go balance (+$1.23 card processing fee) and pay per request with zero markups. Auto-top up adds $20 when the balance reaches $5.

Usage limits

No fixed request, token, 5-hour, or weekly allowance. Pay-as-you-go per 1M tokens. You can set a monthly spend limit for the workspace and each member; the docs example is a $20 monthly usage limit.

source · verified 2026-10-18

If auto-reload is on, a balance under $5 can still trigger a charge above that monthly limit. Per-model token rates are on the same page.

Overflow / pay-as-you-go

Paid requests fail with HTTP 402 once the balance reaches zero. The balance never goes negative. Auto-recharge can buy more credits when the balance runs low. Credit purchases add a processing fee of 4.6% + $0.31.

source · verified 2026-10-18

Models docs: below $5, Console reloads $20 unless you change or disable it. Preset credit amounts are $10, $50, or $100, or another amount.

Models

GPT 6 Astra, GPT 6 Sol, GPT 6.1 Sol, GPT 6 Luna, GPT 5.6 Sol, GPT 5.6 Terra, GPT 5.6 Luna, GPT 5.5, GPT 5.5 Pro, GPT 5.4, GPT 5.4 Pro, GPT 5.4 Mini, GPT 5.4 Nano, GPT 5.3 Codex, GPT 5.3 Codex Spark, GPT 5.2, GPT 5.2 Codex, GPT 5.1, GPT 5.1 Codex, GPT 5.1 Codex Max, GPT 5.1 Codex Mini, GPT 5, GPT 5 Codex, GPT 5 Nano, Claude Fable 5.2, Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Opus 4.5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, Claude Haiku 5.5, Claude Haiku 4.5, Gemini 4 Argon, Gemini 4 Carbon, Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash, Gemini 3.5 Flash Lite, Gemini 3.1 Pro, Gemini 3 Flash, Grok 4.7, Grok 4.6, Grok 4.5, Grok Build 0.1, Muse Ember 1.0, Muse Wonder 1.0, Muse Spark 1.3, Muse Spark 1.2, Qwen3.8 Max, Qwen3.8 Flash, Qwen3.6 Plus, Qwen3.5 Plus, DeepSeek V4.1 Flash, DeepSeek V4 Pro, MiniMax M3, MiniMax M2.7, MiniMax M2.5, GLM 5.3 Flash, GLM 5.3, GLM 5.2, GLM 5.1, GLM 5, Kimi K2.5, Kimi K2.6, Kimi K2.7 Code, Kimi K3, Mistral Large 4, Jev 1.13, Jev 1.13 Free, Big Pickle, GLM-5.3-Flash Free, DeepSeek V4.1 Flash Free, Beam Free, Flint 40B Free, MiMo-V2.6-Flash Free, Nemotron 3 Ultra Free, Nemotron 3.5 Lightning Free, Nemotron 3.5 Super VL Free, Iceman Free, Inkling 2 Small Free, MiniMax M3.1 Flash Free, LongCat 2.5 Free

source · verified 2026-11-12

Console pay-as-you-go catalog linked from the Zen page. Claude Fable 5.2 added ($8 input / $40 output per 1M tokens). Pulse Alpha Free (Nov 6, 2026) and Crouton Alpha Free (Nov 9, 2026) are listed as deprecated. The list may include deprecated models still shown on the page. Catalog adds Gemini 4 Carbon, Muse Ember 1.0, Iceman Free, Inkling 2 Small Free, MiniMax M3.1 Flash Free, and LongCat 2.5 Free.

Price/mo (USD)

$10

source · verified 2026-10-18

Docs: $10/month, lower-cost access to the Go models.

Usage limits

Monthly dollar allowance per model. Each model: 5-hour = 20% of the monthly limit, weekly = 50%, monthly = 100%. Token rates per 1M tokens match Go Plus. Go monthly limit and estimated requests (5h / week / month): GLM-5.3-Flash $60, 6,320 / 15,790 / 31,580; GLM-5.3 $15, 220 / 540 / 1,080; GLM-5.2 $60, 880 / 2,150 / 4,300; Kimi K3.1 Pro $15, 147 / 368 / 735; Kimi K3 $15, 110 / 250 / 490; Kimi K2.7 Code $60, 1,350 / 3,380 / 6,750; LongCat-2.0 $60, 11,400 / 28,600 / 57,200; Step 5 Preview $15, 430 / 1,070 / 2,130; Beam Free unlimited (limited time); Iceman Contributor Free unlimited (limited time); MiMo-V2.6-Flash $60, 30,100 / 75,200 / 150,400; MiMo-V2.6-Pro $15, 3,250 / 8,150 / 16,300; MiMo-V2.5 $60, 30,100 / 75,200 / 150,400; MiMo-V2.5-Pro $15, 3,250 / 8,150 / 16,300; MiniMax M3.1 Flash $20, 3,880 / 9,690 / 19,380; MiniMax M3 $60, 3,200 / 8,000 / 16,000; Muse Spark 1.3 Contributor $60, 45,300 / 113,300 / 226,600; Muse Spark 1.2 Contributor $60, 45,300 / 113,300 / 226,600; Qwen3.8 Max $15, 160 / 400 / 810; Qwen3.8 Flash $30, 5,400 / 13,500 / 27,000; Qwen3.7 Plus $60 for both ≤256K and >256K, 4,300 / 10,800 / 21,600; DeepSeek V4.1 Flash $100 off-peak and peak, 43,330 / 108,330 / 216,670; DeepSeek V4 Pro $15 off-peak and peak, 1,050 / 2,600 / 5,200; Hy4 $60, 2,710 / 6,770 / 13,500; Hy4 preview $30, 1,350 / 3,380 / 6,770; Hy3 $60, 4,300 / 10,750 / 21,500; Grok 4.7 $15 for both ≤200K and >200K, 169 / 423 / 845; GPT 6 Luna $15 for both ≤272K and >272K, 4,230 / 10,560 / 21,130; GPT 5.6 Luna $15 for both ≤272K and >272K, 2,050 / 5,100 / 10,250; Claude Haiku 5.5 $15 for both ≤100K and >100K, 3,850 / 9,620 / 19,230; Gemini 4 Argon $30 (token prices 50% off through November 30, 2026), 440 / 1,080 / 2,120. Request counts are estimates; actual usage varies. Limits may change.

source · verified 2026-11-05

Hy4 (token rates $0.834 input / $2.501 output / $0.042 cached per 1M) added per https://opencode.ai/v2/docs/console/go/ verified 2026-11-05.

Overflow / pay-as-you-go

Without extra credits, requests stop at the usage limits. If Console credits are available, enable Extra Usage and Go falls back to the pay-as-you-go balance instead of blocking.

source · verified 2026-10-28

Billing docs: turn on Extra usage to pay from credits once a Go limit is reached. Go page: top up credit if needed.

Models

Grok 4.7, GLM-5.3-Flash, GLM-5.3, GLM-5.2, GPT 6 Luna, GPT 5.6 Luna, Claude Haiku 5.5, Gemini 4 Argon, Kimi K3.1 Pro, Kimi K3, Kimi K2.7 Code, LongCat-2.0, Step 5 Preview, Beam Free, Iceman Contributor Free, LongCat 2.5 Free, MiMo-V2.6-Flash, MiMo-V2.6-Pro, MiMo-V2.5, MiMo-V2.5-Pro, MiniMax M3.1 Flash, MiniMax M3, Muse Spark 1.3 Contributor, Muse Spark 1.2 Contributor, Qwen3.8 Max, Qwen3.8 Flash, Qwen3.7 Plus, DeepSeek V4.1 Flash, DeepSeek V4 Pro, Hy4, Hy4 preview, Hy3

source · verified 2026-11-10

Same 31 models on Go Plus and Go Teams. The list may change. Beam Free, Iceman Contributor Free and LongCat 2.5 Free are free for a limited time (unlimited); Beam Free and Muse Spark Contributor have region limits; LongCat 2.5 Free is hosted in China and needs Global regions in workspace privacy settings.

Price/mo (USD)

$40

source · verified 2026-10-18

Docs: $40/month, higher usage limits across the same models. Everything included in Go.

Usage limits

Same cap rule as Go: 5-hour = 20% of the monthly dollar limit, weekly = 50%, monthly = 100%. Token rates per 1M tokens match Go. Go Plus monthly limit and estimated requests (5h / week / month): GLM-5.3-Flash $180, 18,960 / 47,370 / 94,740; GLM-5.3 $120, 1,760 / 4,320 / 8,640; GLM-5.2 $180, 2,640 / 6,450 / 12,900; Kimi K3.1 Pro $60, 588 / 1,471 / 2,941; Kimi K3 $60, 440 / 1,000 / 1,960; Kimi K2.7 Code $180, 4,050 / 10,140 / 20,250; LongCat-2.0 $240, 45,600 / 114,400 / 228,800; Step 5 Preview $60, 1,720 / 4,280 / 8,520; Beam Free unlimited (limited time); Iceman Contributor Free unlimited (limited time); MiMo-V2.6-Flash $120, 60,200 / 150,400 / 300,800; MiMo-V2.6-Pro $60, 13,000 / 32,600 / 65,200; MiMo-V2.5 $120, 60,200 / 150,400 / 300,800; MiMo-V2.5-Pro $60, 13,000 / 32,600 / 65,200; MiniMax M3.1 Flash $80, 15,500 / 38,760 / 77,520; MiniMax M3 $180, 9,600 / 24,000 / 48,000; Muse Spark 1.3 Contributor $120, 90,600 / 226,600 / 453,200; Muse Spark 1.2 Contributor $120, 90,600 / 226,600 / 453,200; Qwen3.8 Max $60, 640 / 1,600 / 3,240; Qwen3.8 Flash $90, 16,200 / 40,500 / 81,000; Qwen3.7 Plus $180 for both context tiers, 12,900 / 32,400 / 64,800; DeepSeek V4.1 Flash $200 off-peak and peak, 86,670 / 216,670 / 433,330; DeepSeek V4 Pro $60 off-peak and peak, 4,200 / 10,400 / 20,800; Hy4 $240, 10,840 / 27,080 / 54,000; Hy4 preview $120, 5,400 / 13,520 / 27,080; Hy3 $240, 17,200 / 43,000 / 86,000; Grok 4.7 $60 for both context tiers, 676 / 1,692 / 3,380; GPT 6 Luna $60 for both context tiers, 16,920 / 42,240 / 84,520; GPT 5.6 Luna $60 for both context tiers, 8,200 / 20,400 / 41,000; Claude Haiku 5.5 $60 for both context tiers, 15,380 / 38,460 / 76,920; Gemini 4 Argon $120 (token prices 50% off through November 30, 2026), 1,760 / 4,320 / 8,480. Request counts are estimates. Limits may change.

source · verified 2026-11-05

Hy4 (token rates $0.834 input / $2.501 output / $0.042 cached per 1M) added per https://opencode.ai/v2/docs/console/go/ verified 2026-11-05.

Overflow / pay-as-you-go

Same as Go: requests stop at the limits unless Extra Usage is enabled, in which case usage falls back to Console pay-as-you-go credits.

source · verified 2026-10-28

Billing docs call this Extra usage, paid from credits once a Go limit is reached.

Models

Grok 4.7, GLM-5.3-Flash, GLM-5.3, GLM-5.2, GPT 6 Luna, GPT 5.6 Luna, Claude Haiku 5.5, Gemini 4 Argon, Kimi K3.1 Pro, Kimi K3, Kimi K2.7 Code, LongCat-2.0, Step 5 Preview, Beam Free, Iceman Contributor Free, LongCat 2.5 Free, MiMo-V2.6-Flash, MiMo-V2.6-Pro, MiMo-V2.5, MiMo-V2.5-Pro, MiniMax M3.1 Flash, MiniMax M3, Muse Spark 1.3 Contributor, Muse Spark 1.2 Contributor, Qwen3.8 Max, Qwen3.8 Flash, Qwen3.7 Plus, DeepSeek V4.1 Flash, DeepSeek V4 Pro, Hy4, Hy4 preview, Hy3

source · verified 2026-11-10

Docs: both Go and Go Plus provide access to these 31 models. Beam Free, Iceman Contributor Free and LongCat 2.5 Free are free for a limited time.

Price/mo (USD)

$20

source · verified 2026-10-30

Per member per month. For workspaces with several members; covers every member. A member who joins mid-period is charged $20 and gets a full monthly allowance. Service accounts are not covered. Go and Go Plus (single-member workspaces) can upgrade to Go Teams at any time, with the unused part of the month's allowance credited.

Usage limits

Every member gets their own limits, $5/month higher than Go on every model. Same cap rule as Go: 5-hour = 20% of the monthly dollar limit, weekly = 50%, monthly = 100%. Token rates per 1M tokens match Go and Go Plus. Go Teams monthly limit per member and estimated requests (5h / week / month): GLM-5.3-Flash $65, 6,847 / 17,110 / 34,210; GLM-5.3 $20, 293 / 720 / 1,440; GLM-5.2 $65, 953 / 2,330 / 4,660; Kimi K3.1 Pro $20, 196 / 491 / 980; Kimi K3 $20, 147 / 333 / 653; Kimi K2.7 Code $65, 1,462 / 3,660 / 7,310; LongCat-2.0 $65, 12,350 / 30,980 / 61,970; Step 5 Preview $20, 573 / 1,430 / 2,840; Beam Free unlimited (limited time); Iceman Contributor Free unlimited (limited time); MiMo-V2.6-Flash $65, 32,608 / 81,470 / 162,930; MiMo-V2.6-Pro $20, 4,333 / 10,870 / 21,730; MiMo-V2.5 $65, 32,608 / 81,470 / 162,930; MiMo-V2.5-Pro $20, 4,333 / 10,870 / 21,730; MiniMax M3.1 Flash $25, 4,850 / 12,110 / 24,230; MiniMax M3 $65, 3,467 / 8,670 / 17,330; Muse Spark 1.3 Contributor $65, 49,075 / 122,740 / 245,480; Muse Spark 1.2 Contributor $65, 49,075 / 122,740 / 245,480; Qwen3.8 Max $20, 213 / 530 / 1,080; Qwen3.8 Flash $35, 6,300 / 15,750 / 31,500; Qwen3.7 Plus $65 for both context tiers, 4,658 / 11,700 / 23,400; DeepSeek V4.1 Flash $105 off-peak and peak, 45,500 / 113,750 / 227,500; DeepSeek V4 Pro $20 off-peak and peak, 1,400 / 3,470 / 6,930; Hy4 $65, 2,936 / 7,330 / 14,630; Hy4 preview $35, 1,575 / 3,940 / 7,900; Hy3 $65, 4,658 / 11,650 / 23,290; Grok 4.7 $20 for both context tiers, 225 / 564 / 1,130; GPT 6 Luna $20 for both context tiers, 5,640 / 14,080 / 28,170; GPT 5.6 Luna $20 for both context tiers, 2,733 / 6,800 / 13,670; Claude Haiku 5.5 $20 for both context tiers, 5,133 / 12,830 / 25,640; Gemini 4 Argon $35 (token prices 50% off through November 30, 2026), 513 / 1,260 / 2,470. Request counts are estimates. Limits may change.

source · verified 2026-11-12

Hy4 token rates remain $0.834 input / $2.501 output / $0.042 cached per 1M. The Go Teams Hy4 monthly limit is now $65 (previously listed at $120), which matches the $5-higher-than-Go rule. Hy4 preview stays $35.

Overflow / pay-as-you-go

Go Teams starts with Extra Usage on, so usage falls back to the Console pay-as-you-go balance after the limits instead of blocking. It can be turned off or on again on the Go page. With Extra Usage off, requests stop at the limits.

source · verified 2026-10-30

Models

Grok 4.7, GLM-5.3-Flash, GLM-5.3, GLM-5.2, GPT 6 Luna, GPT 5.6 Luna, Claude Haiku 5.5, Gemini 4 Argon, Kimi K3.1 Pro, Kimi K3, Kimi K2.7 Code, LongCat-2.0, Step 5 Preview, Beam Free, Iceman Contributor Free, LongCat 2.5 Free, MiMo-V2.6-Flash, MiMo-V2.6-Pro, MiMo-V2.5, MiMo-V2.5-Pro, MiniMax M3.1 Flash, MiniMax M3, Muse Spark 1.3 Contributor, Muse Spark 1.2 Contributor, Qwen3.8 Max, Qwen3.8 Flash, Qwen3.7 Plus, DeepSeek V4.1 Flash, DeepSeek V4 Pro, Hy4, Hy4 preview, Hy3

source · verified 2026-11-10

Docs: Go, Go Plus, and Go Teams all provide access to these models. LongCat 2.5 Free is free for a limited time.

Price/mo (USD)

Not published

source · verified 2026-10-28

https://opencode.ai/black now returns a 301 redirect to https://opencode.ai/go (checked 2026-10-28); no Black plan details are published.

Usage limits

Not published

source · verified 2026-10-28

https://opencode.ai/black now returns a 301 redirect to https://opencode.ai/go (checked 2026-10-28); no Black plan details are published.

Overflow / pay-as-you-go

Not published

source · verified 2026-10-28

https://opencode.ai/black now returns a 301 redirect to https://opencode.ai/go (checked 2026-10-28); no Black plan details are published.

Models

Unverified

source · verified 2026-10-28

https://opencode.ai/black now returns a 301 redirect to https://opencode.ai/go (checked 2026-10-28); no Black plan details are published.

Price/mo (USD)

$0

source · verified 2026-10-18

Console is free for any team size, with no seat fees. You pay only for usage from prepaid credits that cover the whole workspace.

Usage limits

No included usage allowance and no seat-based cap. The workspace pays for usage from shared prepaid credits. Owners and admins can set a monthly usage limit for the workspace and for each member.

source · verified 2026-10-18

The monthly-limit example ($20) is on https://opencode.ai/v2/docs/console/models/. Usage through your own providers is billed by that provider, not by Console.

Overflow / pay-as-you-go

Paid requests fail with HTTP 402 when the balance reaches zero. A credit agreement can switch the workspace to monthly invoicing; requests then fail with HTTP 402 when the credit limit is reached or an invoice is overdue. Go extra usage can be paid from the same credits.

source · verified 2026-10-18

Invoices for invoiced billing are issued on the 1st (UTC) and due 14 days later. Credit top-ups add a 4.6% + $0.31 processing fee.

Models

Not published

source · verified 2026-10-18

not published by vendor as a separate team list. Workspaces share the Console catalog and admins choose which models are enabled.

Price/mo (USD)

Not published

source · verified 2026-10-18

not published by vendor. Per-seat pricing; contact OpenCode for a custom quote. No USD amount is shown.

Usage limits

If you have your own LLM gateway, OpenCode does not charge for tokens used.

source · verified 2026-10-18

No request, token, 5-hour, or seat-count cap is published. Trial first, then contact for pricing and implementation.

Overflow / pay-as-you-go

Not published

source · verified 2026-10-18

not published by vendor

Models

Not published

source · verified 2026-10-18

not published by vendor. Configured to use your internal AI gateway; other providers can be disabled.