TokenMonopoly
Live leaderboard of AI API deals — pricing, subscriptions, and SWE-bench scores for Claude, GPT, Gemini, Kimi, DeepSeek, Llama and more. Compare 28 benchmarked models across 98 hosts by price-per-performance, refreshed daily.
| # | Provider | Model | Context | SWE-bench | Input $/MTok | Output $/MTok | Type |
|---|---|---|---|---|---|---|---|
| 1 | AT | 197k | 74.8% | $0.29 – $0.35 | $0.95 – $1.50 | Closed | |
| 2 | AZ | GPT-5.4 Nano2 hosts | 400k | 69.8% | $0.20 | $1.25 | Closed |
| 3 | AT | MiniMax M2.74 hosts | 197k | 73.8% | $0.30 | $1.20 | Closed |
| 4 | 1.0M | 62.8% | $0.25 | $1.50 | Closed | ||
| 5 | AL | 1M | 73.4% | $0.33 | $1.95 | Open | |
| 6 | CH | 262k | 70.0% | $0.38 – $0.60 | $1.72 – $3.50 | Open | |
| 7 | CH | 203k | 69.4% | $0.39 – $2.25 | $1.75 – $2.80 | Closed | |
| 8 | GPT-5 Mini2 hosts | 400k | 60.8% | $0.25 | $2.00 | Closed | |
| 9 | MI | 262k | 62.8% | $0.40 | $2.00 | Open | |
| 10 | GO | Gemini 3 Flash Preview2 hosts | 1.0M | 75.0% | $0.50 | $3.00 | Closed |
| 11 | AM | 80k | 71.4% | $0.72 – $1.20 | $2.30 – $3.50 | Closed | |
| 12 | NO | 131k | 60.2% | $0.57 – $0.60 | $2.30 – $2.50 | Open | |
| 13 | CH | 203k | 76.4% | $0.95 – $1.75 | $3.15 – $5.50 | Closed | |
| 14 | AZ | GPT-5.4 Mini2 hosts | 400k | 73.0% | $0.75 | $4.50 | Closed |
| 15 | AM | Claude Haiku 4.53 hosts | 200k | 66.6% | $1.00 | $5.00 | Closed |
| 16 | AZ | GPT-5.12 hosts | 400k | 69.8% | $1.25 | $10.00 | Closed |
| 17 | AZ | GPT-52 hosts | 400k | 69.0% | $1.25 | $10.00 | Closed |
| 18 | GO | Gemini 3.1 Pro Preview2 hosts | 1.0M | 78.8% | $2.00 | $12.00 | Closed |
| 19 | GPT-5.3-Codex2 hosts | 400k | 78.0% | $1.75 | $14.00 | Closed | |
| 20 | Gemini 2.5 Pro2 hosts | 1.0M | 54.4% | $1.25 | $10.00 | Closed | |
| 21 | AZ | GPT-5.22 hosts | 400k | 75.8% | $1.75 | $14.00 | Closed |
| 22 | AZ | GPT-5.2-Codex2 hosts | 400k | 72.4% | $1.75 | $14.00 | Closed |
| 23 | AZ | GPT-5.42 hosts | 1.1M | 78.2% | $2.50 | $15.00 | Closed |
| 24 | Claude Sonnet 4.64 hosts | 1M | 77.4% | $3.00 | $15.00 | Closed | |
| 25 | Claude Sonnet 4.53 hosts | 1M | 70.0% | $3.00 | $15.00 | Closed |
Subscription value comparison
Price vs estimated monthly requests · hover for models, click to pin
Click a dot above to pin the plan's full details — price, exact usage cap, models with their SWE-bench scores, and harness compatibility.
6 plans with PAYG or unpublished caps not plotted
- MiniMax Token Plan — Starter · $10/mo · Starter tier — fraction of Plus window
- OpenCode Zen · PAYG ~$20 topup · PAYG — provider cost passthrough
- Windsurf Max · $200/mo · Unlisted rolling cap
- Cline · Free (indie) · Unlimited — you pay API
- OpenCode · Free · Unlimited — you pay API
- Continue · Free · Unlimited — you pay API
All subscription deals
Hand-curated catalog of every subscription, flat-rate, and free-harness plan worth knowing about for coding use in 2026. Grouped by how they connect to harnesses.
Flat-rate API subscriptions
API key from a monthly subscription. Best value for power users of external harnesses — no per-token metering.
Flat weekly rate for high-volume Kimi K2.5 Turbo access. API key works in any OpenAI-compatible harness.
- Models
- Kimi K2.5 Turbo
- Limit
- Unlimited tokens (RPM throttled)
- Harness
- OpenCode, Cline, Roo, any OpenAI-compat
Flat monthly rate giving API access to Claude-class frontier models. Drop the key into any agent framework.
- Models
- Claude-class frontier
- Limit
- Unlimited tokens, 135 concurrent requests
- Harness
- Cline, Roo, OpenCode, any framework
Entry tier of MiniMax's flat-rate API bundle. Uses standard API keys so any harness works.
- Models
- MiniMax M2.7
- Limit
- Starter tier — fraction of Plus window
- Harness
- OpenCode Zen, Cline, Roo, OpenClaw
Mid-tier MiniMax subscription with 4,500 requests per 5-hour window. Best price/volume ratio in the flat-rate bucket.
- Models
- MiniMax M2.7 + speech/image
- Limit
- 4,500 req / 5hr
- Harness
- OpenCode Zen, Cline, Roo, OpenClaw
Top MiniMax tier, 15,000 requests per 5-hour window plus all modalities. For continuous agent workflows.
- Models
- MiniMax M2.7 + all modalities
- Limit
- 15,000 req / 5hr
- Harness
- OpenCode Zen, Cline, Roo, OpenClaw
Pay-as-you-go gateway to multiple frontier models at zero markup. No monthly fee — just top up and use.
- Models
- Kimi K2.5, GPT-5-Codex, Gemini, Claude
- Limit
- PAYG — provider cost passthrough
- Harness
- OpenCode native, any via key
Consumer subscriptions (harness-compatible)
Standard chatbot plans that can be unlocked for harness use via subscription auth plugins. You keep the chat app, you also get the CLI.
Standard Claude chat subscription. Claude Code subscription auth is reusable by OpenCode, Cline, and other harnesses. Some third-party restrictions apply on Max tokens.
- Models
- Claude Sonnet 4.6
- Limit
- ~45 Sonnet msgs / 5hr
- Harness
- Claude Code, OpenCode, Cline (sub auth)
- Own agent
- Claude Code
~225 Sonnet messages per 5-hour window (5× Claude Pro). Claude Code subscription auth reusable by OpenCode, Cline, and other harnesses — though Anthropic restricts some third-party consumers of Max tokens.
- Models
- Claude Sonnet 4.6, Opus 4.6
- Limit
- ~225 Sonnet msgs / 5hr
- Harness
- Claude Code, OpenCode, Cline (sub auth)
- Own agent
- Claude Code
~900 Sonnet messages per 5-hour window (20× Claude Pro). Heaviest Claude Code tier for full-day Opus runs. Subscription auth reusable by OpenCode / Cline with some third-party restrictions.
- Models
- Claude Sonnet 4.6, Opus 4.6
- Limit
- ~900 Sonnet msgs / 5hr
- Harness
- Claude Code, OpenCode, Cline (sub auth)
- Own agent
- Claude Code
Baseline Codex tier. Token-based 5-hour windows (since Apr 2 2026). Codex OAuth works in OpenCode, ForgeCode, Cline and other OpenAI-compatible harnesses.
- Models
- GPT-5, o3, o4-mini, GPT-5 Codex
- Limit
- 600–3,000 Codex local msgs / 5hr
- Harness
- Codex CLI, OpenCode, ForgeCode, Cline (Codex OAuth)
- Own agent
- Codex CLI
New $100 Pro tier (Apr 9 2026). 5× Codex of Plus — built for heavy agentic coding sessions. Same model access as $200 Pro. 10× boost through May 31 promo.
- Models
- GPT-5, o3, o4-mini, GPT-5 Codex
- Limit
- 3,000–15,000 Codex local msgs / 5hr (5× Plus)
- Harness
- Codex CLI, OpenCode, ForgeCode, Cline (Codex OAuth)
- Own agent
- Codex CLI
Maximum Codex throughput — 20× Plus limits. Unlimited GPT-5 Instant/Thinking, 250 Deep Research runs/mo. Same harness OAuth as other tiers.
- Models
- GPT-5, o3, o4-mini, GPT-5 Codex
- Limit
- 12,000–60,000 Codex local msgs / 5hr (20× Plus)
- Harness
- Codex CLI, OpenCode, ForgeCode, Cline (Codex OAuth)
- Own agent
- Codex CLI
Gemini 2.5 Pro consumer tier. Jules and Code Assist ship native; OpenCode authenticates via the gemini-auth plugin for harness use.
- Models
- Gemini 2.5 Pro
- Limit
- 100 Gemini 2.5 Pro msgs / day
- Harness
- Jules, Code Assist, OpenCode (gemini-auth)
- Own agent
- Jules, Code Assist
Formerly ChatGPT Team. Per-seat pricing with admin console, SOC 2, SAML SSO. Standard seats include full Codex access with token-based credits.
- Models
- GPT-5, o3, o4-mini, GPT-5 Codex
- Limit
- ~600 Codex msgs / 5hr (per seat)
- Harness
- Codex CLI, OpenCode, ForgeCode, Cline (Codex OAuth)
- Own agent
- Codex CLI
IDE / terminal native agents
Ship their own harness in-editor. Most also allow BYOK so you can drive external tools with the same plan.
Intent agent for VS Code / JetBrains / CLI. 40k credits/mo, uses Augment's own models — no BYOK.
- Models
- Augment proprietary
- Limit
- 40,000 credits / mo
- Harness
- Intent CLI (internal)
- Own agent
- Intent
Team tier: 130k credits/mo, up to 20 users. Same locked-in Augment models.
- Models
- Augment proprietary
- Limit
- 130,000 credits / mo
- Harness
- Intent CLI (internal)
- Own agent
- Intent
Heavy-use tier: 450k credits/mo. Still locked to Augment's models.
- Models
- Augment proprietary
- Limit
- 450,000 credits / mo
- Harness
- Intent CLI (internal)
- Own agent
- Intent
Terminal AI agent with BYOK unlocked. 1,500 credits/mo.
- Models
- Multi (BYOK)
- Limit
- 1,500 credits / mo
- Harness
- Warp Agent + BYOK
- Own agent
- Warp Agent
10,000 credits/mo for Warp's terminal agent, with BYOK support.
- Models
- Multi (BYOK)
- Limit
- 10,000 credits / mo
- Harness
- Warp Agent + BYOK
- Own agent
- Warp Agent
Top Warp tier at 18,000 credits/mo. BYOK available.
- Models
- Multi (BYOK)
- Limit
- 18,000 credits / mo
- Harness
- Warp Agent + BYOK
- Own agent
- Warp Agent
Cursor IDE with Claude + GPT agent mode. BYOK supported for external API use.
- Models
- Claude + GPT (multi)
- Limit
- 500 premium req / mo
- Harness
- Cursor IDE + BYOK
- Own agent
- Cursor Agent
10,000 premium requests per month across all frontier models. Top tier for Cursor heavy users.
- Models
- All frontier (multi)
- Limit
- 10,000 premium req / mo
- Harness
- Cursor IDE + BYOK
- Own agent
- Cursor Agent
Windsurf IDE agent with 500 credits/mo and BYOK support.
- Models
- Multi (BYOK)
- Limit
- 500 credits / mo
- Harness
- Windsurf IDE + BYOK
- Own agent
- Windsurf Agent
Rolling-window power user tier for Windsurf. BYOK available.
- Models
- Multi (BYOK)
- Limit
- Unlisted rolling cap
- Harness
- Windsurf IDE + BYOK
- Own agent
- Windsurf Agent
Copilot with agent mode in VS Code + JetBrains. 300 advanced requests, MCP-compatible, BYOK supported.
- Models
- Multi (BYOK)
- Limit
- 300 advanced req / mo
- Harness
- VS Code + JetBrains + MCP + BYOK
- Own agent
- Copilot Agent
Higher Copilot tier with access to all frontier models and higher request limits.
- Models
- All frontier (multi)
- Limit
- 1,500 premium req / mo
- Harness
- VS Code + JetBrains + MCP + BYOK
- Own agent
- Copilot Agent
BYOK harnesses (free platform)
Free (or near-free) harness platforms. Pair these with any API key from the sections above.
Open-source VS Code + CLI agent. Free for individuals, $20/mo for teams. Drop in any provider key.
- Models
- Any (BYOK)
- Limit
- Unlimited — you pay API
- Harness
- VS Code + CLI, any provider key
- Own agent
- Cline Agent
Free terminal TUI agent. Plug in any provider or use Zen as an optional gateway.
- Models
- Any (BYOK)
- Limit
- Unlimited — you pay API
- Harness
- Any provider key, Zen optional
- Own agent
- OpenCode Agent
Free VS Code / JetBrains plugin. Works with any OpenAI-compatible provider.
- Models
- Any (OpenAI-compat)
- Limit
- Unlimited — you pay API
- Harness
- VS Code + JetBrains, any OpenAI-compat key
- Own agent
- Continue Agent