Skip to main content
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

​
Authorization
string
required
Your secret key as a bearer token: Bearer prysm_sk_...

​
Body

​
task
string
required
The coding task in natural language, e.g. “Write a thread-safe LRU cache in Python with tests”.
​
language
string
Target language (python, typescript, rust, …). Auto-detected from the task if omitted.
​
policy
string
default:"balanced"
The objective dial: efficiency (one cheap coder), depth (cross several diverse coders in parallel and keep the best), or balanced.
​
coder_model
string
Force the model that writes the code. Ignored if it isn’t a known catalog model.
​
reviewer_model
string
Force the critic model that reviews the code. Ignored if it isn’t a known catalog model.
​
max_iters
integer
default:"3"
Total iterations: the first generation plus up to max_iters - 1 repairs.
​
review
boolean
default:"true"
Set false for a single shot — one coder, one draft, no critic loop.
​
max_tokens
integer
default:"2048"
Maximum tokens per underlying model call.
​
temperature
number
default:"0.2"
Sampling temperature passed to the underlying models. Lower is steadier for code.
​
max_cost_usd
number
A soft budget hint, in USD. The repair loop stops early once the estimated spend approaches this cap.
​
include_trace
boolean
default:"true"
Include the per-stage execution trace in prysm.stages. Set false for a leaner response.

​
Response

​
id
string
Unique code-run id, e.g. prysm-a1b2c3d4.
​
object
string
Always code.
​
created
integer
Unix timestamp (seconds).
​
task
string
The task that was solved.
​
language
string
The target language (detected or forced).
​
policy
string
The policy that ran: efficiency, balanced, or depth.
​
reason
string
Plain-English explanation of how the run was carried out.
​
passed
boolean
Whether the final review passed.
​
iterations
integer
How many generate→review cycles ran.
​
files
array
The generated files.
​
review
object
The final critic verdict, or null when review was false.
​
usage
object
Aggregate token usage across every model call.
​
prysm
object
The Code Mode extension block.

​
Errors

StatuserrorMeaning
400no_tasktask was empty or whitespace.
401—Missing or invalid API key.
502no_code_producedKeys are configured but no model produced usable code.
502code_errorThe engine raised while generating or reviewing.
503no_provider_availableNo 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"])

{
  "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-r1"
  },
  "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-r1",
      "models_used": ["qwen-2.5-72b", "deepseek-r1"],
      "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-r1"],
      "confidence": 0.9,
      "verifiable": true
    },
    "stages": [
      {
        "name": "plan",
        "results": [],
        "detail": { "language": "python", "policy": "balanced", "coder_models": ["qwen-2.5-72b"], "reviewer_model": "deepseek-r1" }
      },
      {
        "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-r1", "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 }
      }
    ]
  }
}