model parameter.
Smart routing variants
These are virtual models that route to real models at runtime. Use them when you don’t want to hard-code a specific model.| ID | Optimizes for | Billed at | Guide |
|---|---|---|---|
auto | Best model per task type (balanced) | Resolved model’s rate | Smart Routing → |
auto-fast | Lowest latency | Resolved model’s rate | Smart Routing → |
auto-cheap | Lowest cost | Resolved model’s rate | Smart Routing → |
auto-quality | Highest quality | Resolved model’s rate | Smart Routing → |
ensemble | 3-model consensus (GPT-5 + Claude Sonnet + Gemini Pro) | $0.040/req flat | Chat → |
ensemble-quality | 3-model consensus (GPT-5 + Claude Opus + Gemini Pro) | $0.050/req flat | Chat → |
"claude-opus-4.6>gpt-5>gemini-3.1-pro" — tries each model in order if the previous fails or scores below your quality threshold. See chat docs →
Pick a model
| I want to… | Model | Cost | ID |
|---|---|---|---|
| Let NinjaChat decide | Auto (Balanced) | resolved rate | auto |
| Build a production chatbot | GPT-5 | $0.006 | gpt-5 |
| Generate high-quality code | Claude Sonnet 4.6 | $0.015 | claude-sonnet-4.6 |
| Do math and logical reasoning | o3-mini | $0.006 | o3-mini |
| Get the best possible answer | Claude Opus 4.6 | $0.030 | claude-opus-4.6 |
| Classify / extract text (budget) | DeepSeek V3 | $0.003 | deepseek-v3 |
| Fast real-time chat | Gemini 3 Flash | $0.003 | gemini-3-flash |
| Analyze long documents | Gemini 2.5 Pro | $0.006 | gemini-2.5-pro |
| Highest quality (any task) | Ensemble Quality | $0.050 | ensemble-quality |
| Generate images | Nano Banana 2 | $0.05/img | nano-banana-2 |
| Generate images (budget) | FLUX.2 Klein | $0.03/img | flux-2-klein |
| Best image quality | FLUX Kontext Max | $0.10/img | flux-kontext-max |
| Generate video | Veo 3.1 Fast | $3.00/video | veo-3.1-fast |
| Best video quality | Veo 3.1 | $5.00/video | veo-3.1 |
| Search the web | Web Search | $0.05/query | — |
Chat models — 24 models
Full guide with examples: Chat → $0.030/req — Ultra:claude-opus-4.6
$0.015/req — Premium: claude-sonnet-4.6
$0.006/req — Standard: gpt-5 o3-mini claude-sonnet-4.5 claude-haiku-4.5 gemini-2.5-pro gemini-3-pro gemini-3.1-pro grok-4 kimi-k2 mistral-large llama-4-maverick kimi-k2.5
$0.003/req — Free tier: gpt-5-mini gemini-2.5-flash gemini-3-flash llama-4-scout deepseek-v3 qwq-32b glm-5 minimax-m2.5 ninja-1 uncensored-ai
Image models — 13 models
Full guide with examples: Images →| Model | ID | Cost |
|---|---|---|
| FLUX Kontext Max | flux-kontext-max | $0.10/img |
| FLUX.2 Flex | flux-2-flex | $0.08/img |
| FLUX.1 Pro Ultra | flux-1-pro-ultra | $0.08/img |
| Recraft V3 | recraft-v3 | $0.08/img |
| Google Imagen 4 | google-imagen-4 | $0.08/img |
| Nano Banana Pro | nano-banana-pro | $0.08/img |
| Seedream | seedream | $0.08/img |
| FLUX.2 Pro | flux-2-pro | $0.05/img |
| FLUX Kontext Pro | flux-kontext-pro | $0.05/img |
| Nano Banana 2 | nano-banana-2 | $0.05/img |
| FLUX.1 Fill | flux-1-fill | $0.05/img |
| FLUX.2 Klein | flux-2-klein | $0.03/img |
| Nano Banana | nano-banana | $0.03/img |
Video models — 8 models
Full guide with examples: Video →| Model | ID | Cost |
|---|---|---|
| Runway Gen-4.5 | runway-gen4.5 | $5.00/video |
| Veo 3.1 | veo-3.1 | $5.00/video |
| Runway Gen-4 Turbo | runway-gen4-turbo | $3.00/video |
| Seedance 2 | seedance-2 | $3.00/video |
| Kling Video | kling-video | $3.00/video |
| Google Veo 2 | google-veo-2 | $3.00/video |
| Veo 3.1 Fast | veo-3.1-fast | $3.00/video |
| Veo 3 Fast | google-veo-3-fast | $3.00/video |
Search — $0.05/query
Full guide with examples: Search →Live model catalog via API
Get the full model list programmatically — including capabilities, context window, speed, and recommendations:capabilities, context_window, max_output_tokens, speed, recommended_for. Estimate costs →