Code

from prysm import Prysm

client = Prysm()
r = client.code(
    "Write a Python function to add two numbers",
    policy="balanced",
)
for f in r["files"]:
    print(f["path"]); print(f["content"])
print(r["passed"], r["prysm"]["proof"]["proof_hash"])

import { Prysm } from "@prysmai/sdk";

const client = new Prysm();
const r = await client.code(
  "Write a Python function to add two numbers",
  { policy: "balanced" },
);
for (const f of r.files) { console.log(f.path); console.log(f.content); }
console.log(r.passed, r.prysm.proof.proof_hash);

curl https://api.prysm1.com/v2/code \
  -H "Authorization: Bearer $PRYSM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "task": "Write a Python function to add two numbers",
    "policy": "balanced"
  }'

{
  "id": "prysm-a1b2c3d4",
  "object": "code",
  "created": 1767312000,
  "task": "Write a Python function to add two numbers",
  "language": "python",
  "policy": "balanced",
  "reason": "balanced policy: one mid-tier coder, reviewed and repaired by a reasoning critic.",
  "passed": true,
  "iterations": 1,
  "files": [
    {
      "path": "main.py",
      "language": "python",
      "content": "def add(a, b):\n    \"\"\"Return the sum of two numbers.\"\"\"\n    return a + b\n",
      "bytes": 71
    }
  ],
  "review": {
    "passed": true,
    "score": 0.92,
    "issues": [],
    "reviewer": "deepseek-v4-pro"
  },
  "usage": {
    "prompt_tokens": 86,
    "completion_tokens": 120,
    "total_tokens": 206
  },
  "prysm": {
    "code": {
      "policy": "balanced",
      "language": "python",
      "passed": true,
      "score": 0.92,
      "confidence": 0.9,
      "iterations": 1,
      "coder_models": ["qwen-2.5-72b"],
      "reviewer_model": "deepseek-v4-pro",
      "models_used": ["qwen-2.5-72b", "deepseek-v4-pro"],
      "latency_ms": 3180
    },
    "cost": { "total_usd": 0.000412, "estimated": true },
    "proof": {
      "request_id": "a1b2c3d4-...-...",
      "timestamp": "2026-06-03T00:00:00+00:00",
      "proof_hash": "sha256:7f3a9c2b1e4d8a06",
      "policy": "balanced",
      "language": "python",
      "passed": true,
      "models_used": ["qwen-2.5-72b", "deepseek-v4-pro"],
      "confidence": 0.9,
      "verifiable": true
    },
    "stages": [
      {
        "name": "plan",
        "results": [],
        "detail": { "language": "python", "policy": "balanced", "coder_models": ["qwen-2.5-72b"], "reviewer_model": "deepseek-v4-pro" }
      },
      {
        "name": "generate:0",
        "results": [
          { "model": "qwen-2.5-72b", "ok": true, "in_tokens": 42, "out_tokens": 78, "latency_ms": 1620, "cost_usd": 0.00021, "confidence": 0.8, "role": "coder" }
        ],
        "detail": { "iteration": 0 }
      },
      {
        "name": "review:0",
        "results": [
          { "model": "deepseek-v4-pro", "ok": true, "in_tokens": 44, "out_tokens": 42, "latency_ms": 1560, "cost_usd": 0.0002, "confidence": 0.92, "role": "reviewer" }
        ],
        "detail": { "passed": true, "score": 0.92 }
      }
    ]
  }
}

POST https://api.prysm1.com/v2/code · Requires authentication

Code Mode writes code, reviews it with a separate critic model, and repairs against that feedback until the review passes or a budget/iteration cap is hit (Reflexion-style). In depth policy several diverse coders run in parallel and the best candidate is kept. The response carries the files, the final review verdict, and a PrysmProof v2 that binds the task to the code it produced. You pick the objective with a policy; PRYSM picks the coder and the critic (or you force them). See How Code Mode works for the full model.

This endpoint lives under /v2, not /v1. The SDKs target it automatically with client.code(...). PRYSM never executes the generated code — the default critic is a pure LLM reviewer.

Authorization

string

required

Your secret key as a bearer token: Bearer prysm_sk_...

Body

string

required

The coding task in natural language, e.g. “Write a thread-safe LRU cache in Python with tests”.

string

Target language (python, typescript, rust, …). Auto-detected from the task if omitted.

string

default:"balanced"

The objective dial: efficiency (one cheap coder), depth (cross several diverse coders in parallel and keep the best), or balanced.

string

Force the model that writes the code. Ignored if it isn’t a known catalog model.

string

Force the critic model that reviews the code. Ignored if it isn’t a known catalog model.

integer

default:"3"

Total iterations: the first generation plus up to max_iters - 1 repairs.

boolean

default:"true"

Set false for a single shot — one coder, one draft, no critic loop.

integer

default:"2048"

Maximum tokens per underlying model call.

number

default:"0.2"

Sampling temperature passed to the underlying models. Lower is steadier for code.

number

A soft budget hint, in USD. The repair loop stops early once the estimated spend approaches this cap.

boolean

default:"true"

Include the per-stage execution trace in prysm.stages. Set false for a leaner response.

Response

string

Unique code-run id, e.g. prysm-a1b2c3d4.

string

Always code.

integer

Unix timestamp (seconds).

string

The task that was solved.

string

The target language (detected or forced).

string

The policy that ran: efficiency, balanced, or depth.

string

Plain-English explanation of how the run was carried out.

boolean

Whether the final review passed.

integer

How many generate→review cycles ran.

array

The generated files.

Show files[]

string

Relative file path, e.g. main.py.

string

The file’s language.

string

The full file contents.

integer

Length of content in bytes.

object

The final critic verdict, or null when review was false.

Show review

boolean

Whether the critic passed the code.

number

The critic’s score, 0–1.

string[]

Concrete issues the critic raised (empty when clean).

string

The critic model that produced the verdict.

object

Aggregate token usage across every model call.

Show usage

integer

Total input tokens.

integer

Total output tokens.

integer

Sum of the two.

object

The Code Mode extension block.

Show prysm

object

Show code

string

The policy that ran.

string

The target language.

boolean

Whether the final review passed.

number

The final review score, 0–1.

number

Blended confidence across the loop, 0–1.

integer

How many generate→review cycles ran.

string[]

Every coder that wrote a candidate.

string

The critic model.

string[]

Every model that contributed (coders + critic).

integer

Wall-clock latency in milliseconds.

object

Show cost

number

Total cost across all model calls, USD.

boolean

Always true — v2 cost is estimated from text length (~4 chars/token).

object

A verifiable PrysmProof v2 binding the task to the code. Verify it later via GET /v1/proof/{request_id}.

Show proof

string

The id to verify against.

string

ISO-8601 UTC timestamp.

string

SHA-256 over the task, files, and stages, e.g. sha256:a1b2c3d4e5f6....

string

The policy that ran.

string

The target language.

boolean

Whether the final review passed.

string[]

Every model that contributed.

number

Blended confidence across the loop.

boolean

Always true.

array

Per-stage execution trace (present when include_trace is true). Stages run as plan → generate:0 → review:0 → generate:1 → review:1 … Each stage has a name, a results array with one entry per model call (model id, ok, token counts, latency, cost, confidence, role — the raw text is omitted), and a detail object. A skipped critic (review: false) leaves review:0 with an empty results array.

Errors

Status	`error`	Meaning
`400`	`no_task`	`task` was empty or whitespace.
`401`	—	Missing or invalid API key.
`502`	`no_code_produced`	Keys are configured but no model produced usable code.
`502`	`code_error`	The engine raised while generating or reviewing.
`503`	`no_provider_available`	No provider API keys are configured on the server.

from prysm import Prysm

client = Prysm()
r = client.code(
    "Write a Python function to add two numbers",
    policy="balanced",
)
for f in r["files"]:
    print(f["path"]); print(f["content"])
print(r["passed"], r["prysm"]["proof"]["proof_hash"])

import { Prysm } from "@prysmai/sdk";

const client = new Prysm();
const r = await client.code(
  "Write a Python function to add two numbers",
  { policy: "balanced" },
);
for (const f of r.files) { console.log(f.path); console.log(f.content); }
console.log(r.passed, r.prysm.proof.proof_hash);

curl https://api.prysm1.com/v2/code \
  -H "Authorization: Bearer $PRYSM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "task": "Write a Python function to add two numbers",
    "policy": "balanced"
  }'

{
  "id": "prysm-a1b2c3d4",
  "object": "code",
  "created": 1767312000,
  "task": "Write a Python function to add two numbers",
  "language": "python",
  "policy": "balanced",
  "reason": "balanced policy: one mid-tier coder, reviewed and repaired by a reasoning critic.",
  "passed": true,
  "iterations": 1,
  "files": [
    {
      "path": "main.py",
      "language": "python",
      "content": "def add(a, b):\n    \"\"\"Return the sum of two numbers.\"\"\"\n    return a + b\n",
      "bytes": 71
    }
  ],
  "review": {
    "passed": true,
    "score": 0.92,
    "issues": [],
    "reviewer": "deepseek-v4-pro"
  },
  "usage": {
    "prompt_tokens": 86,
    "completion_tokens": 120,
    "total_tokens": 206
  },
  "prysm": {
    "code": {
      "policy": "balanced",
      "language": "python",
      "passed": true,
      "score": 0.92,
      "confidence": 0.9,
      "iterations": 1,
      "coder_models": ["qwen-2.5-72b"],
      "reviewer_model": "deepseek-v4-pro",
      "models_used": ["qwen-2.5-72b", "deepseek-v4-pro"],
      "latency_ms": 3180
    },
    "cost": { "total_usd": 0.000412, "estimated": true },
    "proof": {
      "request_id": "a1b2c3d4-...-...",
      "timestamp": "2026-06-03T00:00:00+00:00",
      "proof_hash": "sha256:7f3a9c2b1e4d8a06",
      "policy": "balanced",
      "language": "python",
      "passed": true,
      "models_used": ["qwen-2.5-72b", "deepseek-v4-pro"],
      "confidence": 0.9,
      "verifiable": true
    },
    "stages": [
      {
        "name": "plan",
        "results": [],
        "detail": { "language": "python", "policy": "balanced", "coder_models": ["qwen-2.5-72b"], "reviewer_model": "deepseek-v4-pro" }
      },
      {
        "name": "generate:0",
        "results": [
          { "model": "qwen-2.5-72b", "ok": true, "in_tokens": 42, "out_tokens": 78, "latency_ms": 1620, "cost_usd": 0.00021, "confidence": 0.8, "role": "coder" }
        ],
        "detail": { "iteration": 0 }
      },
      {
        "name": "review:0",
        "results": [
          { "model": "deepseek-v4-pro", "ok": true, "in_tokens": 44, "out_tokens": 42, "latency_ms": 1560, "cost_usd": 0.0002, "confidence": 0.92, "role": "reviewer" }
        ],
        "detail": { "passed": true, "score": 0.92 }
      }
    ]
  }
}

Orchestrate Agents

Overview

Endpoints

Agentic Control Plane

Agentic Control Plane

Authorization

Body

Response

Errors

​Authorization

​Body

​Response

​Errors

Authorization

Body

Response

Errors