POST /v1/gto/preflop · 200 OK

Build with solver-grade GTO strategy over HTTP.

Use MelaSolver GPU through one self-serve API. Preflop and presolved flop spots use published strategy data; custom flop, turn, and river spots run through our real-time solver pool. One key, stateless requests, a free tier.

pip install pokerai-bet / npm install @pokerai/client / npx @pokerai/mcp

Real API responsepokerai.bet
Hero 9♥9♠ · MP · facing UTG raise · 6-max 100bb
raise 64%
call
fold 25%
{
  "situation": "Raise",
  "strategy": [
    { "action":"fold",  "frequency":0.254 },
    { "action":"call",  "frequency":0.106 },
    { "action":"raise", "frequency":0.64, "amount_bb":9 }
  ]
}
5.8M+presolved solutions
66Kisomorphic flop spots
4streets covered
2API families
$0free tier
M4 flop benchmark · July 25, 2026

MelaSolver GPU finished this documented M4 flop benchmark in 27.75s.

MelaSolver GPU finished in 27.75s, versus 56.47s for MelaSolver CPU and 67.22s for TexasSolver.

SpotTypical 3-bet pot · 19.5 bb pot · 91 bb behind · 2h 5s Td flop
SizingsFlop 50% / 100% · turn 67% / 120% · river 75% / 100%
Raise capraise_limit 3 · one bet plus up to two re-raises per street
BranchesCustom OOP/IP ranges · donk sizes · all-in enabled on every street

Scope: one M4 flop benchmark, not a global solver ranking. MacBook Pro · Apple M4 · 10-core CPU · 10-core GPU · 16 GB unified memory · 15 threads · 100 iterations · accuracy 0.5 · isomorphism on.

MelaSolver GPUMeasured
27.75s

FullEngine V2 · 1.00x reference

MelaSolver CPUMeasured
56.47s

2.03x slower than MelaSolver GPU

TexasSolverMeasured
67.22s

2.42x slower than MelaSolver GPU

GitHub repository
PioSolverEstimated
~94.58s

3.41x slower than MelaSolver GPU · directional estimate

TexasSolver source claim
Range explorer

Change the spot. Keep the API mental model.

Choose stack depth, position, and action line; the complete 13×13 range and request payload update from the same data the API serves.

Browse all 40 range pages →
Stack
Open
Defend
Loading…
Raise Call Fold split cell = mixed frequency
The same spot, via the APIstateless

        
      
Coverage

One key. Four streets. Zero solver infrastructure.

Preflop and presolved flop spots are fast lookups, while custom flop, turn, and river spots can be submitted as queued real-time solves.

01 / cached

Preflop

RFI, vs-raise, 3-bet and 4-bet lines across supported stack depths.

Presolved lookup
02 / cached + queued

Flop lookup or solve

Use 5.8M+ presolved flop solutions, or submit a custom flop spot to the solver pool.

milliseconds or real-time solve
03 / queued

Turn solve

Continue from any supported spot and poll until the solver pool has a result.

real-time solve
04 / queued

River solve

Resolve final-street frequencies without shipping your own solver stack.

real-time solve
Why an API

Strategy belongs in your product, not trapped behind another UI.

GTO Wizard and RangeConverter are excellent apps to study inside. Pokerai is the strategy layer itself, exposed over HTTP for trainers, bots, chart tools, review flows, and AI agents.

What developers should remember

Serious solver infrastructure you can plug into your own product today.

One API key · four streets · a free tier
Featured case

Counterplay is one product built on Pokerai API.

A real-time GTO trainer for iOS: every hand, one thin client, no cached strategy. User action is graded against returned GTO frequencies and explained by an LLM coach.

270lines of API client
0cached strategy
1thin API client
app/gto/client.pythe whole strategy layer
strategy = pokerai.preflop(
  hole_cards="AhKh",
  hero="MP",
  actions=[("UTG","raise",3)],
)
grade(hero_action, strategy)  # vs GTO freq
Trainer

Real-time drills

Generate spots, grade each action, and explain frequencies after the hand.

Charts

Range browser

Turn supported stack depths and positions into product-native charts.

Review

Hand history audit

Compare played lines against solver strategy without storing your own tree.

Agent

AI poker coach

Let an LLM request exact strategies, then translate them into user feedback.

Pricing

Start free. Scale when real solves matter.

Presolved lookups and real-time solves are metered separately. Alipay, WeChat Pay, and crypto checkout are supported.

Free

$0
  • 1,000 presolved lookups
  • 25 real-time solves
  • no card required

Builder

Recommended
$29/mo
  • 20,000 presolved lookups
  • 500 real solves
  • for indie devs

Pro

$99/mo
  • 100,000 presolved lookups
  • 3,000 real solves
  • production apps

Scale

Custom
  • from $299/mo
  • dedicated solver pool
  • contact us
Contact sales →

Builder and Pro are available with Alipay, WeChat Pay, and crypto checkout. Choose a paid plan.

FAQ

Answers before the first request.

Is there a free tier?

Yes — 1,000 presolved lookups and 25 real-time solves per month, no credit card. Enough to build a full trainer and run every tutorial.

What formats do you cover?

6-max No-Limit Hold'em, all four streets — done to solver depth, not a shallow multi-format menu. Preflop across multiple stack depths (100bb + 40bb), flop from 5.8M+ presolved solutions, turn/river solved on demand. PLO and ICM aren't covered yet.

Is Pokerai API a desktop solver download?

No. Pokerai API is a hosted HTTP API for documented 6-max NLHE strategy data. Use desktop solver software for local tree construction or research control; use benchmark or gameplay APIs to evaluate agents or simulate games, not as GTO strategy output.

Do requests carry session state?

No. Every request is self-contained — send the spot, get the strategy. Nothing about your hands is stored.

Can I use it for real-time assistance (RTA)?

No. Real-time assistance at real-money tables is prohibited. Pokerai API is for training, coaching, hand review, study, and research.