Skip to main content
Routeway provides access to 200+ models from leading providers — OpenAI, Anthropic, Google, Meta, DeepSeek, MoonshotAI, and more — through a single unified endpoint.

Models Catalog

Browse all models with live pricing, context lengths, and capability filters.

GET /v1/models

Fetch the full model list programmatically with pricing and metadata.

​
Model Tiers

Free models are identified by a :free suffix in their ID (e.g. deepseek-r1:free).
Cost$0.00 — all tokens are free
Rate limit20 requests / minute · 200 requests / day
Best forDevelopment, testing, low-volume prototyping
Exceeding the rate limit returns a 429. See Rate Limits.

​
Listing Models Programmatically

Fetch the live catalog — including pricing, capabilities, and availability — with a single request: 
curl https://api.routeway.ai/v1/models

​
Response shape

{
  "object": "list",
  "data": [
    {
      "id": "kimi-k2.7-code",
      "name": "MoonshotAI: Kimi K2.7 Code",
      "short_name": "Kimi K2.7 Code",
      "description": "Kimi K2.7 Code is Moonshot AI's coding-focused agentic model...",
      "context_length": 262144,
      "created": 1781222400,
      "owned_by": "moonshot-ai",
      "available": true,
      "endpoints": ["/v1/chat/completions", "/v1/responses", "/v1/messages"],
      "pricing": {
        "input":  { "unit": "1M tokens", "price_per_million_t": 0.95 },
        "output": { "unit": "1M tokens", "price_per_million_t": 4.0 },
        "caching": {
          "read": { "unit": "1M tokens", "price_per_million_t": 0.2 }
        }
      },
      "capabilities": {
        "vision": true,
        "function_call": true,
        "reasoning": true
      },
      "supported_parameters": ["temperature", "top_p", "tools", "tool_choice", "..."],
      "benchmarks": {
        "gpqa": 0.866,
        "lcr": 0.733,
        "tau2": 0.942
      }
    }
  ]
}

​
Model Schema

​
Core fields

FieldTypeDescription
idstringThe model ID to use in API requests (e.g. "kimi-k2.7-code").
namestringFull display name including provider (e.g. "MoonshotAI: Kimi K2.7 Code").
short_namestringAbbreviated name without the provider prefix.
descriptionstringDescription of the model’s capabilities and intended use.
context_lengthintegerMaximum context window in tokens.
createdintegerUnix timestamp of when the model became available on Routeway.
owned_bystringOriginating provider (e.g. "openai", "anthropic", "moonshot-ai").
availablebooleantrue if the model is currently routable. false means it is temporarily unavailable.
endpointsstring[]API paths this model can be called on (see Endpoints below).

​
Pricing fields

FieldTypeDescription
pricing.inputobjectRate for standard input tokens (prompt + context).
pricing.outputobjectRate for generated output tokens.
pricing.cachingobjectPresent only on models that support prompt caching.
pricing.caching.readobjectRate for tokens served from cache (always cheaper than fresh input).
pricing.caching.write.5mobjectRate to write a prompt into cache with a 5-minute TTL.
pricing.caching.write.1hobjectRate to write a prompt into cache with a 1-hour TTL.
All rates use price_per_million_t (USD per 1M tokens). See How Billing Works for caching cost examples.

​
Capabilities

FieldTypeDescription
capabilities.visionbooleanAccepts image inputs.
capabilities.function_callbooleanSupports tool / function calling.
capabilities.reasoningbooleanExposes a chain-of-thought reasoning mode (e.g. via reasoning_effort).

​
Benchmarks

Common benchmark scores included where available. Fields are null when a score has not been published.
FieldWhat it measures
gpqaGraduate-level science reasoning (GPQA Diamond)
hleHumanity’s Last Exam
lcrLiveCodeBench — competitive coding
tau2Tool-use & agent task completion (TAU2)
ifbenchInstruction following
terminalbench_hardTerminal / shell task completion
scicodeScientific coding
artificial_analysis_intelligence_indexComposite intelligence score (Artificial Analysis)
artificial_analysis_coding_indexCoding-specific composite (Artificial Analysis)

​
Endpoints

Each model advertises which API paths it supports in the endpoints array. Not all models are available on every path.
EndpointCompatible withUsed for
/v1/chat/completionsOpenAI SDK, any OpenAI-compatible clientText generation (broadest model coverage)
/v1/responsesOpenAI Responses APIText generation
/v1/messagesAnthropic SDKText generation
/v1/images/generationsOpenAI SDK (images.generate)Image generation from a text prompt
/v1/images/editsOpenAI SDK (images.edit)Image editing with a mask and prompt
Use /v1/chat/completions as your default for text models. It has the broadest model coverage and is compatible with any OpenAI-compatible library. Image models are only available on their respective /v1/images/* paths.

​
Filtering by Capability

You can filter the response client-side to find models that match your requirements: 
import requests

data = requests.get("https://api.routeway.ai/v1/models").json()

vision_models = [
    m
    for m in data["data"]
    if m.get("available") and m.get("capabilities", {}).get("vision")
]

for m in vision_models:
    print(m["id"], "— input $", m["pricing"]["input"]["price_per_million_t"], "/ 1M")