Switch from OpenRouter in two lines.

Your OpenRouter models still have names.

GPT-5.4Claude OpusGemini 3.1Grok 4DeepSeek

What joining NinjaChat actually adds.

FLUX 2Imagen 4Nano BananaRecraft V3

Veo 3.1

Seedance 2

Kling 2.6

Then these.

1. 01

   Create a key and add credits

   Get an nj_sk_ key at /developers and add a credit pack. Balances are prepaid, and failed generations are refunded.

   verify your key workscopy

   # Sanity check: list every model your key can call (no auth needed)
   curl https://www.ninjachat.ai/api/v1/models
   
   # First authenticated request
   curl https://www.ninjachat.ai/api/v1/chat/completions \
     -H "Authorization: Bearer nj_sk_YOUR_KEY" \
     -H "Content-Type: application/json" \
     -d '{"model": "gpt-5", "messages": [{"role": "user", "content": "Say hi"}]}'

2. 02

   Drop the provider prefixes

   OpenRouter namespaces models as vendor/model. NinjaChat uses canonical catalog IDs. Routing preferences live in the routing object and ordered fallbacks live in the models array.

   routing + fallbackscopy

   # NinjaChat routing + ordered fallbacks
   client.chat.completions.create(
       models=["claude-opus-4.6", "gpt-5", "gemini-3.1-pro"],
       routing={"strategy": "cost", "allow_fallbacks": True},
       messages=[{"role": "user", "content": "Hello"}],
   )

3. 03

   Verify streaming and tool calling

   Same SDK code. Streaming arrives as SSE deltas, and tool_calls round-trip with role: "tool" messages.

   streaming + tools, unchanged sdkPythonNode.jscopy

   # Streaming
   stream = client.chat.completions.create(
       model="claude-sonnet-4.6",
       messages=[{"role": "user", "content": "Write a haiku about ninjas"}],
       stream=True,
   )
   for chunk in stream:
       if chunk.choices and chunk.choices[0].delta.content:
           print(chunk.choices[0].delta.content, end="", flush=True)
   
   # Tool calling
   resp = client.chat.completions.create(
       model="gpt-5",
       messages=[{"role": "user", "content": "Weather in Tokyo?"}],
       tools=[{
           "type": "function",
           "function": {
               "name": "get_weather",
               "parameters": {
                   "type": "object",
                   "properties": {"city": {"type": "string"}},
                   "required": ["city"],
               },
           },
       }],
   )
   call = resp.choices[0].message.tool_calls[0]
   # ...run your function, then send the result back:
   followup = client.chat.completions.create(
       model="gpt-5",
       messages=[
           {"role": "user", "content": "Weather in Tokyo?"},
           resp.choices[0].message,
           {"role": "tool", "tool_call_id": call.id, "content": "22°C, clear"},
       ],
   )

Model mapping — OpenRouter ids to NinjaChat slugs

Metered per token — prices shown are typical-request estimates at the live rates on GET /v1/models. Actual requests settle from measured token usage.

OpenRouter idNinjaChat slugPrice / request

openai/gpt-5gpt-5$0.023

anthropic/claude-opus-4.6claude-opus-4.6$0.050

anthropic/claude-sonnet-4.6claude-sonnet-4.6$0.030

google/gemini-3.1-progemini-3.1-pro$0.022

google/gemini-3-flashgemini-3-flash$0.0055

deepseek/deepseek-v3.2.2deepseek-v3.2.2$0.004

x-ai/grok-4grok-4$0.009

moonshotai/kimi-k2.5 (any K2)kimi-k2.6$0.009

openrouter/autoninja/autobilled at resolved model's rate

What doesn't come along.

FAQ