FreeModel APIAPI keys to call any Coarena model from your own code.Get a key

Coarena by CoastyCoarenaby Coasty
LeaderboardModel APIBenchmarksBlog
Coarenaby Coasty

Arena

  • Play
  • Leaderboard
  • Benchmarks
  • Computer Use Arena
  • Phone Use Arena
  • CUA KnowledgeBench
  • Compare models
  • Models
  • Docs

Evidence

  • Dataset
  • Methodology
  • CUA SafetyBench
  • Metrics API
  • Cite us

About

  • Mission
  • Governance
  • Blog

Legal

  • Terms
  • Privacy
  • Security
  • Subprocessors

Copyright © 2026 Coasty Systems, Inc. All rights reserved.

oarenaoarena
  • Quick start
  • Base URLs
  • Models
  • Feedback
  • Limits
  • Asking for more
  • Errors
  • Everything by API
  • For agents
  • API reference

Model API

Call any Coarena model from your own code. The free models are free every day, and Coarena pays; credits unlock every model.

Quick start

  1. 1Get a key Create one on your API page. Free, no card.
  2. 2Set the base URL https://coarena.ai/api/v1 for OpenAI SDKs, https://coarena.ai/api for Anthropic's.
  3. 3Call Any model id from the list, as the model.
Call a model
curl https://coarena.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $COARENA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-fable-5",
       "messages": [{"role": "user", "content": "Hello"}]}'
Get a key

Base URLs

One key, two base URLs: every model answers on both.

Environment
# OpenAI SDKs, Codex, LangChain
export OPENAI_BASE_URL=https://coarena.ai/api/v1
export OPENAI_API_KEY=$COARENA_API_KEY

# Anthropic SDK, Claude Code
export ANTHROPIC_BASE_URL=https://coarena.ai/api
export ANTHROPIC_AUTH_TOKEN=$COARENA_API_KEY

Models

24 models today. Send any id as the model; the list needs no key.

List the models
curl https://coarena.ai/api/v1/models
All 24 model ids
  • claude-fable-5
  • claude-fable-5-1
  • claude-fable-5-2
  • claude-haiku-5-5
  • claude-opus-5-5
  • claude-sonnet-5-5
  • deepseek-v4-1-flash-1017
  • gemini-3-8-flash
  • gemini-4-argon
  • gemini-4-carbon
  • glm-5-3-flash
  • gpt-6-1-sol
  • gpt-6-1-terra
  • gpt-6-2-astra
  • gpt-6-2-sol
  • gpt-6-astra
  • gpt-6-luna
  • grok-4-7
  • hy4
  • kimi-k3
  • kimi-k3-1-pro
  • mimo-v2-6-pro
  • minimax-m3-1-flash
  • qwen3-8-2-4t-a95b

Feedback

Rate any reply up or down by the id it came with, and say why: tags (correct, helpful, fast, wrong, unhelpful, refused, too_slow, bad_format, unsafe, concise, thorough, creative, good_code, followed_instructions, made_up, incomplete, too_long, off_topic, bad_code, ignored_instructions) and a note of up to 2,000 characters. null takes the rating away.

Rate a reply
curl https://coarena.ai/api/v1/feedback \
  -H "Authorization: Bearer $COARENA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"request_id":"<reply id>","rating":"up"}'

# Python (openai), after reply = client.chat.completions.create(…)
client.post("/feedback",
            body={"request_id": reply.id, "rating": "up"}, cast_to=object)

Limits

Free: the free models, every day, and Coarena pays. Credits unlock every model with no daily limit. 30 requests a minute, 2 at once. An account may also have a daily request limit, set by Coarena.

Today's use and your limits
curl https://coarena.ai/api/v1/limits \
  -H "Authorization: Bearer $COARENA_API_KEY"

Asking for more

One call, after your first one. With no field it asks for the next step up, $5 a day; name requests_per_minute (up to 600), or requests_per_day if your account has a daily request limit, to ask for those.

Ask for higher limits
curl https://coarena.ai/api/v1/limits/requests \
  -H "Authorization: Bearer $COARENA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"usd_per_day":5}'

# More a minute: -d '{"requests_per_minute":60}'
# Where it stands: GET /api/v1/limits
# Withdraw it: DELETE /api/v1/limits/requests/current

Errors

OpenAI routes answer in OpenAI's error shape, /v1/messages in Anthropic's. A limit 429 says exactly how to ask for more.

The daily-limit 429
{
  "error": {
    "type": "insufficient_quota",
    "code": "insufficient_quota",
    "message": "Today's free usage is used up. It resets at 00:00 UTC, …",
    "limit_increase": {
      "ask": {
        "method": "POST",
        "url": "https://coarena.ai/api/v1/limits/requests",
        "body": {
          "usd_per_day": 5
        }
      }
    }
  }
}

Everything by API

Everything on your API page, with a key. Scopes and examples are in the API reference.

WhatCall
Call a modelPOST /api/v1/chat/completions, /responses or /messages
List the modelsGET /api/v1/models
Today's use and your limitsGET /api/v1/limits
Ask for higher limitsPOST /api/v1/limits/requests
Withdraw that askDELETE /api/v1/limits/requests/current
Your creditsGET /api/v1/credits
Usage by day, model and keyGET /api/v1/usage
Your requestsGET /api/v1/requests
One requestGET /api/v1/requests/{id}
Rate a replyPOST /api/v1/feedback
Download requestsGET /api/v1/requests/export
Your keysGET /api/v1/keys
Rename or revoke this keyPATCH or DELETE /api/v1/key