Models

The best AI coding plans per dollar in 2026, and the free models that almost beat them

Every top AI coding plan ranked by the value it gets you per dollar, with the models worth paying for and the free ones that come close. If you are choosing where to spend, start here. Every figure dated and sourced.

The value ranking

Every row is ranked on one number: capability per dollar. It is the model's coding score (Artificial Analysis Coding Index, 0–100) divided by how much a million tokens of it costs. Higher is better: more coding ability for every dollar of tokens. Best route is the cheapest credible place to actually buy the model.

DeepSeek V4 Flash is the best value at about 4,934 capability points per dollar via OpenCode Go, then GLM-5.2, GPT-5.6 Luna, Kimi K3 and Grok 4.5. The Gemini and Claude models, valued from API prices, sit lower.

Bars use a log scale: each gridline above is 10× the last, so equal bar-length gaps mean equal multiples, not equal differences. DeepSeek's real advantage over Claude Fable 5 is about 700×; a linear axis couldn't show both ends at once.

The * rows (Claude, Gemini, GPT-5.5) are quota plans: the vendor publishes no solid data on how much you actually get on the plan, so we fall back to the API price. The real plan value could be better or worse than this estimate. The unstarred rows use published plan economics.

Free models worth running

The best-value model is one that costs nothing. Several routers and plans carry genuinely free frontier and open-weight models, the kind of thing the pricing pages bury. All rotate, so treat these as current, not stable.

Ranked by coding capability, the strongest free coding models you can run today:

ModelScoreFree whereNotes
MiniMax M3
80.5%
SWE-bench Verified; not free on OpenRouter
DeepSeek V4 Flash
79%
SWE-bench Verified; not free on OpenRouter
Nemotron 3 Ultra
71%
leaderboards put it at 70–72%
Laguna S 2.1
70.2%
Terminal-bench 70.2%; free on OpenRouter
North Mini Code
68%
vendor claims 80.2% pass@10; independent boards say 68
GPT-OSS 20B
62%
free on OpenRouter; the 120B model is paid

Where to get them free

OpenRouter

Free models: Laguna S 2.1, North Mini Code, Nemotron 3 Ultra, GPT-OSS 20B, Laguna XS 2.1, Ling 3.0 Flash, Gemma 4, Nemotron Nano

Limits: ~20 req/min, ~50–200 req/day (no card needed); the :free router picks the best free model automatically

Lineup rotates; several free models were pulled in 2026 (Qwen3 Coder, DeepSeek R1). Good for prototyping, not a stable dependency. Scores are on each model page, from Artificial Analysis.

OpenCode Zen

Free models: DeepSeek V4 Flash, MiMo-V2.5, Laguna S 2.1, North Mini Code, Nemotron 3 Ultra, Big Pickle (stealth)

Limits: Free while in the rotation; no card needed to try them

Rotates monthly and is explicitly not permanent. Some free endpoints log data for model improvement, so don't send client code you care about.

Freebuff

Free models: DeepSeek V4 Flash, MiniMax M3, Kimi, open models

Limits: ~5 free hours of DeepSeek V4 Flash per day; ad-funded, no subscription, no API key

The daily figure is the founder's stated quota, not a contract. Ad-supported.

GitHub Copilot

Free models: Claude, GPT-5.6, Gemini, Grok 4.5 (multi-model)

Limits: Unlimited completions free; agentic coding burns AI credits

New Pro/Pro+/Max signups paused since 1 Jun 2026; still valid for existing subscribers.

Kiro (AWS)

Free models: Auto + model multipliers

Limits: Free 50 credits on signup

Credits run out fast; it is a spec-driven agent, not raw model access.

Cursor

Free models: Claude, GPT-5.6, Gemini, GLM-5.2, Kimi K3

Limits: Hobby tier free

Free tier is usage-quota; you pay for real work.

Flat-rate plans worth checking

These sell a quota rather than a price per token, so they are not on the value chart (we will not invent a number for them). But several are the cheapest route to a strong open model. Each plan is listed individually with its real price.

PlanPriceStrongest model it exposesCap.Notes
$10/mo ($5 first)
18 models: Grok 4.5, GLM-5.2, GPT-5.6 Luna, Kimi K3, DeepSeek V4 Flash/Pro, Qwen, MiniMax, MiMo
76.2
The best value route in this whole table, with published token economics and cheap. 6× usage multiplier for most models.
$10/mo ($5 first)
GLM-5.2, Kimi K2.6/K2.7 Code, MiniMax M3, Qwen3, GPT-OSS 120B
68.8
Four strong open models flat; no per-token rate published, so not ranked above.
$9.99/mo
Kimi K3 (~5× discount), GLM-5.2, Kimi K2.7, DeepSeek V4, Qwen3.7, MiniMax, MiMo
76.2
Kimi K3 is the strongest open model and this is its cheapest access; already on the value chart via the 5× estimate.
$72/mo ($50.40 promo)
GLM-5.2, GLM-5-Turbo
68.8
Publishes credit economics, so it is ranked above. Listed here as the flat-rate route to GLM-5.2.
$20 / $100
glm-5.2:cloud, cloud models
68.8
GPU-time based; a flat route to GLM-5.2, but allowance depends on compute.
$19–$199
Kimi K3, K2.7, K2.6
76.2
Shared token-metered pool; no credits↔tokens conversion published.
$20/mo
M3 (1M ctx) + M2.7 + image/speech/music
58.6
Published token quota (~1.7B/mo), the cheapest published quota in the set, but M3 is outside the top-15 roster.
$10/mo
Claude Fable 5, Opus 5, Sonnet 5; GPT-5.6 Sol/Terra/Luna; Gemini; Grok 4.5; Kimi K2.7
78.3
Usage-based credits since 1 Jun 2026; completions free. New signups paused.
$20/mo
Claude 4/5.x, GPT-5.x, Gemini 3.x, GLM-5.2, Kimi K3
78
Own pool + resold frontier models; quota per tier, on-demand beyond.
$10/mo
Claude Fable 5, Opus 4.5–5, Sonnet 5; GPT-5.6 Sol/Terra/Luna, 5.5; Gemini
78
$5 bundled tokens, then API + 10%.
$100 / $200 / $500
Claude Opus 4.7, GPT-5.6 Luna, Gemini 3.1 Flash Lite
73.6
Subscription or 1¢/credit PAYG.
$19 / $49 / $199
500+ hosted models / 60+ providers
78.3
Credit sub with up to 50% bonus.
$20/mo
Spec-driven agent; Opus 4.8 2.2×, GLM-5 0.5× multipliers
74.3
1,000 credits; overage $0.04. Only reseller with published per-model multipliers.
$3 / $10 / $30 / $100
Doubao + DeepSeek
69.1
ByteDance; trae.cn free.
$1 / $15 / $100 / $200
DeepSeek V4 Pro, Qwen 3.7 Max, MiniMax M3, MiMo; premium GPT-5.6/Grok/Claude
76.7
Credit pools.
$49.99 / $99.99 / $199.99
OpenAI, Claude, Gemini (auto-routed)
78.3
2,000/7,000/17,000 credits; 6-mo rollover.
$10 / $40 / $50
GPT, Claude, Gemini, Grok, Kimi, DeepSeek
78.3
Credits at cost, no markup; BYOK option.
$19 / $39 / $79 / $199
Multi-model GPT/Claude agents
78.3
Daily credits 2/5/10/30.
$20/mo
glm-5.2:cloud
68.8
GPU-time windows 5h + 7d.
$100/mo flat
own code models
n/a
Up to 50 seats; flat + usage.
~$6 / $16 / $50
MiMo-V2.5-Pro, V2.5, V2.5-TTS
n/a
Xiaomi; credit-based (¥39–45/99).

Method, sources, date

Capability: Artificial Analysis Coding Index (Terminal-Bench v2.1 + SciCode), best variant. Value = capability ÷ effective blended $/M, where blended $/M = 0.85 × (0.34×input + 0.66×cached) + 0.15×output, a coding-agent-typical profile. Unstarred rows use published plan economics; starred rows use the API price because no plan economics are published. All figures re-verified 2026-08-05.

Universe: models reachable through a subscription coding plan, or a free model tier on a router or plan. Where official sources disagree (OpenAI's Codex credit card, the Claude Max token window, Gemini Ultra prices) we show the corroborated figure and flag the conflict rather than average.

This page ranks price. It doesn't rank capability.

Value per dollar is the axis this page can measure honestly, because both halves of it are published. The question of which tool can actually see your project is a different one, and we've written it up separately: the questions worth asking instead of reading a ranking.

Which model you pick matters less than how you review it

The chart tells you what to rent. A fixed-price audit tells you whether the code it wrote is safe to ship.

Book a discovery call

[email protected] · replies within 1 business day