Provider profile · Global
Synthetic coding plans
Synthetic is a Global-based provider tracking 3 fixed-price plans from $9 to $90/mo covering 8 models (kimi, deepseek, nvidia). Plans expose OpenAI-compatible endpoints usable by any agent. Compare every plan by requests per $1 in the calculator.
Privacy — Does not train on prompts/completions; works only with no-retention providers.
Plans tracked
3
Models served
8
Cheapest plan
$9/mo
Last verified
23 Oct 2026
In 30 seconds
Synthetic sells 3 plans from $9 to $90/mo — the cheapest entry is $9/mo. 8 models tracked, led by the Kimi K3 flagship. Plans expose OpenAI-compatible endpoints, so any agent can use them (BYOK).
Plans
Synthetic plans, verified 23 Oct 2026
Plan history
Cumulative value-changing events per plan since 2026-08-08 — one kind-colored dot per event, hover the charts for dates.
| Provider / planProvider and subscription tier. Badges and plan notes appear below. | PriceStandard monthly price in USD, before first-month promotions. | Top modelsFlagship models included in the plan. The list is approximate; '+N more' opens the full catalog. | Coding toolCoding tool included with the plan. 'only' means locked to the vendor's own tools — the supported set is listed next to the badge; '+others' means it also works elsewhere. | SubscribeOpen provider pricing. Referral links may support TokenPlans at no extra cost. | ||
|---|---|---|---|---|---|---|
| GoCredits regenerate over the week and are spent at subscription-discounted model rates; more tokens can be bought at usage-based pricesWeekly credit quota, 2% regenerated every ~3.4h · no 5h or monthly caps · 1 usage reset/month · extra tokens at API pricing | $9.00 | Kimi K3DeepSeek V4.1 FlashNemotron 3 Super 120B+5 more ↗ | Any tool | Weekly credit quota, 2% regenerated every ~3.4h · no 5h or monthly caps · 1 usage reset/month · extra tokens at API pricing | 23 Oct | Subscribe↗ |
| StandardCredits regenerate over the week and are spent at subscription-discounted model rates; more tokens can be bought at usage-based pricesWeekly credit quota, 2% regenerated every ~3.4h · no 5h or monthly caps · 1 usage reset/month · extra tokens at API pricing | $30.00 | Kimi K3DeepSeek V4.1 FlashNemotron 3 Super 120B+5 more ↗ | Any tool | Weekly credit quota, 2% regenerated every ~3.4h · no 5h or monthly caps · 1 usage reset/month · extra tokens at API pricing | 23 Oct | Subscribe↗ |
| BigCredits regenerate over the week and are spent at subscription-discounted model rates; more tokens can be bought at usage-based prices. Fast mode (2× speed; each request draws 2× the rate limit) and Infinite mode (Beta — no rate-limit draw, runs slower, DeepSeek V4.1 Flash only) are enabled from the Big planWeekly credit quota, 2% regenerated every ~3.4h · no 5h or monthly caps · 1 usage reset/month · extra tokens at API pricing · higher priority access | $90.00 | Kimi K3DeepSeek V4.1 FlashNemotron 3 Super 120B+5 more ↗ | Any tool | Weekly credit quota, 2% regenerated every ~3.4h · no 5h or monthly caps · 1 usage reset/month · extra tokens at API pricing · higher priority access | 23 Oct | Subscribe↗ |
Best for
Model coverage
Every model on Synthetic plans
“exclusive” = the only tracked plan with this model — a unique long-tail query target.
Recent changes
What changed for Synthetic subscribers
5 events in the last 90 days — 0 worse, 4 better.
- Price23 Oct 2026
synthetic.new/pricing now lists three subscription plans instead of one: Go $9, Standard $30 and Big $90, all serving the same model roster (Kimi K3, DeepSeek V4.1 Flash, Nemotron 3 Super 120B, Qwen3.8-27B, GPT-OSS 120B, GLM-4.7-Flash, GLM-5.3, GLM-5.3-Flash). The single $30 “Subscription” record becomes the Standard tier so existing plan links keep resolving; Go and Big join it. Big adds higher priority access plus Fast mode (2× speed, each request drawing 2× the rate limit) and Infinite mode (Beta — no rate-limit draw, runs slower, DeepSeek V4.1 Flash only). Usage-based per-token prices are unchanged.
Verified 2026-10-23 · source
- Ceiling23 Oct 2026
Synthetic replaced the request-pack limits with a single weekly credit limit that regenerates incrementally. The rate-limits page states the plans “only use weekly limits”, with no additional five-hour or monthly limits, 2% of the weekly quota returning every ~202 minutes and no lockout after a burst; each plan also carries 1 usage reset/month. The pricing page publishes a per-model token allowance per plan together with its API-rate dollar value, so the calculator now carries that published equivalent as each plan’s per-model monthly budget (Standard: $251/mo DeepSeek V4.1 Flash, $204/mo GPT-OSS 120B) where it previously showed n/a — Req/$1 reads as a value comparison (confidence proxy).
Verified 2026-10-23 · source
- Models11 Oct 2026
A new Standard-models row joined the Subscription roster: zai-org/GLM-5.3, marked Beta with 512k context and “Included”, published at $1.40 input / $4.40 output / $0.26 cached input per 1M. Every existing row on the page and every published rate is unchanged — plan price ($30/mo, “$1/day”), the 5h request quota (500 per $30 pack, max 5) and the concurrency throttle all read identically to the previous check.
Verified 2026-10-11 · source
- Models23 Sept 2026
The synthetic.new/pricing Standard-models table dropped the zai-org/GLM-5.2 row and gained deepseek-ai/DeepSeek-V4.1-Flash (Beta, 512k context) — every other row and every published rate is unchanged.
Verified 2026-09-23 · source
- Models02 Sept 2026
Synthetic.new Subscription ($30/mo) swaps Qwen3.6-27B for Qwen3.8-27B at unchanged rates and adds GLM-5.3-Flash (Beta).
Verified 2026-09-02 · source
Alternatives
Providers with overlapping model catalogs
Flagship rank · Kimi K3: #23 (Max config) on the Agent Arena agent leaderboard — 1.93% net improvement (board fetched 2026-10-19).
Common questions
Which Synthetic plan is cheapest?
Synthetic Go at $9/mo. The cheapest plan is not always the best value — compare Req/$1 in the calculator.
How many plans does Synthetic offer?
3 tiers tracked, 3 currently active. Every tier is in the plans table below with its price, models and usage ceiling.
Newsletter
The weekly brief — plan churn, dated.
A plain weekly digest of every tracked price move, ceiling change and model-list update — pulled straight from the dated changelog ledger, with a one-line “worth switching?” note on each. Free. No spam, unsubscribe anytime.