Keep Together AI. Add every other lab.

Your Together AI models still have names.

FLUX

DeepSeekKimiQwen

What joining NinjaChat actually adds.

Imagen 4Nano Banana

Veo 3.1

Seedance 2

GPT-5.4Claude OpusGemini 3.1Kling 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

   Shorten the model ids

   Together uses full Hugging Face-style repo paths. NinjaChat slugs are short and stable — deepseek-ai/DeepSeek-V3.2 becomes deepseek-v3.2, and the slug keeps pointing at the current serving of that model, so a provider-side redeploy never breaks your code. Full table below.

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"},
       ],
   )

4. 04

   Move FLUX image calls to /v1/images/generations

   Together's images.generate endpoint maps to POST /v1/images/generations. Same FLUX family, synchronous response with hosted URLs.

   before· together aicopy

   # Before — Together images
   img = client.images.generate(
       model="black-forest-labs/FLUX.1-pro",
       prompt="a ninja cat, studio lighting",
   )

   →becomes

   after· ninjachatPythonNode.jscURLcopy

   # pip install ninjachat
   import os
   from ninjachat import NinjaChat
   
   client = NinjaChat(api_key=os.environ["NINJACHAT_API_KEY"])
   image = client.images.generate(
       model="flux-2-pro",
       prompt="a ninja cat, studio lighting",
       n=1,
   )
   print(image["data"][0]["url"])

Model mapping — Together ids to NinjaChat slugs

Together AI idNinjaChat slugPrice / request

deepseek-ai/DeepSeek-V3.2deepseek-v3.2$0.004

Qwen/QwQ-32Bqwq-32b$0.002

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

zai-org/GLM (4.x/5 family)glm-5$0.008

mistralai/Mistral-Large…mistral-large$0.016

black-forest-labs/FLUX.1-proflux-2-pro (POST /v1/images/generations)$0.03 / image

— (closed models Together can't serve)gpt-5, claude-opus-4.6, gemini-3.1-pro…$0.022–$0.05

What doesn't come along.

FAQ