Chat Compare | Mesh API Docs

curl -X POST https://api.meshapi.ai/v1/chat/compare \
     -H "Authorization: Bearer <token>" \
     -H "Content-Type: application/json" \
     -d '{
  "models": [
    "openai/gpt-4o-mini",
    "anthropic/claude-haiku-4.5"
  ],
  "messages": [
    {
      "role": "user",
      "content": "Explain TCP vs UDP in two sentences."
    }
  ],
  "comparison_model": "openai/gpt-4o-mini"
}'

{
  "comparison_id": "cmp_01ARZ3NDEKTSV4RRFFQ6",
  "created": 1748331628,
  "models": [
    "openai/gpt-4o-mini",
    "anthropic/claude-haiku-4.5",
    "google/gemini-3-flash-preview"
  ],
  "results": [
    {
      "model": "openai/gpt-4o-mini",
      "latency_ms": 812,
      "request_id": "req_01ARZ3NDEKTSV4RRFFQ69G5FAV::openai/gpt-4o-mini",
      "response_body": {
        "id": "chatcmpl-DrTNOwFsT3v79HmQwOwMgEM2IbWJl",
        "object": "chat.completion",
        "created": 1748331628,
        "model": "gpt-4o-mini-2024-07-18",
        "choices": [
          {
            "index": 0,
            "message": {
              "role": "assistant",
              "content": "TCP is a connection-oriented protocol that guarantees ordered, reliable delivery; UDP is connectionless and sends datagrams without delivery or ordering guarantees."
            },
            "finish_reason": "stop"
          }
        ],
        "usage": {
          "prompt_tokens": 24,
          "completion_tokens": 47,
          "total_tokens": 71
        }
      },
      "content": "TCP is a connection-oriented protocol that guarantees ordered, reliable delivery; UDP is connectionless and sends datagrams without delivery or ordering guarantees.",
      "usage": {
        "prompt_tokens": 24,
        "completion_tokens": 47,
        "total_tokens": 71
      }
    },
    {
      "model": "anthropic/claude-haiku-4.5",
      "latency_ms": 650,
      "request_id": "req_01ARZ3NDEKTSV4RRFFQ69G5FAV::anthropic/claude-haiku-4.5",
      "response_body": {
        "id": "chatcmpl-019ed1d24b0371a390ab",
        "object": "chat.completion",
        "model": "anthropic/claude-haiku-4.5",
        "choices": [
          {
            "index": 0,
            "message": {
              "role": "assistant",
              "content": "TCP establishes a connection and guarantees ordered, intact delivery. UDP fires packets without a connection, trading reliability for lower latency."
            },
            "finish_reason": "stop"
          }
        ],
        "usage": {
          "prompt_tokens": 24,
          "completion_tokens": 52,
          "total_tokens": 76
        }
      },
      "content": "TCP establishes a connection and guarantees ordered, intact delivery. UDP fires packets without a connection, trading reliability for lower latency.",
      "usage": {
        "prompt_tokens": 24,
        "completion_tokens": 52,
        "total_tokens": 76
      }
    },
    {
      "model": "google/gemini-3-flash-preview",
      "latency_ms": 0,
      "request_id": "req_01ARZ3NDEKTSV4RRFFQ69G5FAV::google/gemini-3-flash-preview",
      "error": "Upstream provider returned an error.",
      "error_code": "upstream_error"
    }
  ],
  "total_latency_ms": 1340,
  "object": "compare.completion",
  "comparison": "Both answers are correct. Claude's phrasing is slightly clearer on the latency trade-off; GPT-4o-mini is more precise on ordering guarantees.",
  "comparison_model": "openai/gpt-4o-mini",
  "comparison_usage": {
    "prompt_tokens": 180,
    "completion_tokens": 60,
    "total_tokens": 240
  },
  "comparison_fallback_used": false,
  "partial": true,
  "skip_comparison": false
}

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

This endpoint expects an object.

modelslist of stringsRequired

messageslist of objectsRequired

model_overrideslist of objects or nullOptional

comparison_modelstring or nullOptional

comparison_instructionsstring or nullOptional

temperaturedouble or nullOptional0-2

max_tokensinteger or nullOptional>=1

streambooleanOptionalDefaults to false

templatestring or nullOptional

variablesmap from strings to strings or nullOptional

skip_comparisonbooleanOptionalDefaults to false

cacheboolean or nullOptional

Response

Per-model results plus an optional synthesized comparison (JSON), or an SSE stream when stream=true

comparison_idstring

Unique ID for this comparison (cmp_...).

createdinteger

Unix timestamp (seconds) when the response was produced.

modelslist of strings

Models that were compared, in request order (deduped).

resultslist of objects

Per-model results, in models order.

total_latency_msinteger

End-to-end latency for the whole compare request, in milliseconds.

object"compare.completion"

comparisonstring or null

Synthesized evaluation of all responses from the comparison LLM. Null when skip_comparison is true or fewer than two models succeeded.

comparison_modelstring or null

Model that produced comparison. Null when no synthesis ran.

comparison_usageobject or null

Token usage for the comparison LLM call.

comparison_fallback_usedbooleanDefaults to false

True if the primary comparison model failed and a fallback produced the synthesis.

partialbooleanDefaults to false

True if at least one model in results returned an error.

skip_comparisonbooleanDefaults to false

Echoes whether the comparison LLM step was skipped.

Errors

401

Unauthorized Error

402

Payment Required Error

403

Forbidden Error

422

Unprocessable Entity Error

429

Too Many Requests Error

500

Internal Server Error

502

Bad Gateway Error

503

Service Unavailable Error