# NinjaChat Developers

## Docs

- [NinjaChat Developers](https://docs.ninjachat.ai/index.md): Every model, two ways in — a REST API for your code, an MCP server for your agent.
- [Quickstart](https://docs.ninjachat.ai/quickstart.md): Get an API key and make your first request in under a minute.
- [Authentication](https://docs.ninjachat.ai/authentication.md): One header on every request.
- [OpenAI Compatibility](https://docs.ninjachat.ai/openai-compatibility.md): Use the official OpenAI SDKs with NinjaChat — just change the base URL and API key.
- [Chat](https://docs.ninjachat.ai/chat.md): Send messages to any model and get a response with its exact cost.
- [Streaming](https://docs.ninjachat.ai/streaming.md): Stream responses token-by-token over server-sent events.
- [Sessions](https://docs.ninjachat.ai/sessions.md): Server-side conversation memory. Send only the new message — history is automatic.
- [Smart Routing](https://docs.ninjachat.ai/smart-routing.md): Set model to auto and NinjaChat picks the best model for each prompt.
- [Fallback Chains](https://docs.ninjachat.ai/fallback-chains.md): Try models in sequence — if one fails or scores low, the next one runs.
- [Model Compare](https://docs.ninjachat.ai/compare.md): Race one prompt across up to 8 models and get ranked results with cost and latency.
- [Batch](https://docs.ninjachat.ai/batch.md): Up to 20 prompts in one call, all in parallel. Wall-clock = the slowest one, not the sum.
- [Ensemble](https://docs.ninjachat.ai/ensemble.md): Three models answer, a fourth synthesizes. For answers that must be right.
- [Budget Routing](https://docs.ninjachat.ai/budget-routing.md): Name a price, get the best model that fits it.
- [Quality Scoring](https://docs.ninjachat.ai/quality-scoring.md): A confidence score with every response — and auto-retry when it's too low.
- [Image Generation](https://docs.ninjachat.ai/image-generation.md): 14 models behind one endpoint, from $0.03 per image.
- [Video Generation](https://docs.ninjachat.ai/video-generation.md): Veo, Kling, and Seedance behind one endpoint. Submit, poll, get an MP4.
- [Web Search](https://docs.ninjachat.ai/search.md): Search the web and get AI-synthesized answers with cited sources.
- [Models](https://docs.ninjachat.ai/models.md): Quick guide to picking the right model for your use case.
- [Pricing](https://docs.ninjachat.ai/pricing.md): Flat per-request prices. No token math. The cost is in every response.
- [Cost Estimation](https://docs.ninjachat.ai/estimate.md): Know the exact price before you run anything. Always free, no key required.
- [Error Handling](https://docs.ninjachat.ai/error-handling.md): Every error code, what it means, and what to do about it.
- [Rate Limits](https://docs.ninjachat.ai/rate-limits.md): Limits per endpoint, response headers, and retry patterns.
- [NinjaChat MCP](https://docs.ninjachat.ai/mcp/overview.md): Your agent can make images and video. Connect once, then just ask.
- [MCP Quickstart](https://docs.ninjachat.ai/mcp/quickstart.md): Connect an agent and make your first image in under a minute.
- [Client Setup](https://docs.ninjachat.ai/mcp/clients.md): One endpoint, eight clients. Pick yours.
- [Tool Reference](https://docs.ninjachat.ai/mcp/tools.md): One front-door tool does almost everything. Sixteen specialists for fine control.
- [Recipes](https://docs.ninjachat.ai/mcp/recipes.md): Real workflows, no special tools — generate once, then edit and reference.
- [Billing & Limits](https://docs.ninjachat.ai/mcp/billing.md): Flat prices, hard budgets, automatic refunds.
- [Models](https://docs.ninjachat.ai/models-overview.md): Explore all available models on the NinjaChat API.
- [GPT-5.4](https://docs.ninjachat.ai/api-reference/models/chat/gpt-5-4.md): gpt-5.4 — OpenAI's latest flagship. $0.015/request.
- [GPT-5.4 Pro](https://docs.ninjachat.ai/api-reference/models/chat/gpt-5-4-pro.md): gpt-5.4-pro — OpenAI's highest-effort model. $0.030/request.
- [GPT-5](https://docs.ninjachat.ai/api-reference/models/chat/gpt-5.md): gpt-5 — OpenAI's general-purpose model. $0.006/request.
- [GPT-5 Mini](https://docs.ninjachat.ai/api-reference/models/chat/gpt-5-mini.md): gpt-5-mini — OpenAI's fast, lightweight model. $0.003/request.
- [Claude Opus 4.6](https://docs.ninjachat.ai/api-reference/models/chat/claude-opus-4-6.md): claude-opus-4.6 — Anthropic's most capable model. $0.030/request.
- [Claude Sonnet 4.6](https://docs.ninjachat.ai/api-reference/models/chat/claude-sonnet-4-6.md): claude-sonnet-4.6 — Anthropic's best for code and complex tasks. $0.015/request.
- [Claude Sonnet 4.5](https://docs.ninjachat.ai/api-reference/models/chat/claude-sonnet-4-5.md): claude-sonnet-4.5 — Anthropic's balanced coding model. $0.006/request.
- [Claude Haiku 4.5](https://docs.ninjachat.ai/api-reference/models/chat/claude-haiku-4-5.md): claude-haiku-4.5 — Anthropic's fastest model. $0.006/request.
- [o3-mini](https://docs.ninjachat.ai/api-reference/models/chat/o3-mini.md): o3-mini — OpenAI's reasoning and math specialist. $0.006/request.
- [Gemini 2.5 Pro](https://docs.ninjachat.ai/api-reference/models/chat/gemini-2-5-pro.md): gemini-2.5-pro — Google's structured data analysis model. $0.006/request.
- [Gemini 2.5 Flash](https://docs.ninjachat.ai/api-reference/models/chat/gemini-2-5-flash.md): gemini-2.5-flash — Google's ultra-fast model. $0.003/request.
- [Gemini 3 Pro](https://docs.ninjachat.ai/api-reference/models/chat/gemini-3-pro.md): gemini-3-pro — Google's multi-modal reasoning model. $0.006/request.
- [Gemini 3.1 Pro](https://docs.ninjachat.ai/api-reference/models/chat/gemini-3-1-pro.md): gemini-3.1-pro — Google's latest reasoning model. $0.006/request.
- [Gemini 3 Flash](https://docs.ninjachat.ai/api-reference/models/chat/gemini-3-flash.md): gemini-3-flash — Google's fast and affordable model. $0.003/request.
- [Grok 4](https://docs.ninjachat.ai/api-reference/models/chat/grok-4.md): grok-4 — xAI's model with real-time knowledge. $0.006/request.
- [DeepSeek V3](https://docs.ninjachat.ai/api-reference/models/chat/deepseek-v3.md): deepseek-v3 — DeepSeek's coding and math model. $0.003/request.
- [Kimi K2](https://docs.ninjachat.ai/api-reference/models/chat/kimi-k2.md): kimi-k2 — Moonshot's instruction-following model. $0.006/request.
- [Kimi K2.5](https://docs.ninjachat.ai/api-reference/models/chat/kimi-k2-5.md): kimi-k2.5 — Moonshot's advanced reasoning model. $0.006/request.
- [Mistral Large](https://docs.ninjachat.ai/api-reference/models/chat/mistral-large.md): mistral-large — Mistral's multilingual model. $0.006/request.
- [Llama 4 Maverick](https://docs.ninjachat.ai/api-reference/models/chat/llama-4-maverick.md): llama-4-maverick — Meta's multi-modal open-source model. $0.006/request.
- [Llama 4 Scout](https://docs.ninjachat.ai/api-reference/models/chat/llama-4-scout.md): llama-4-scout — Meta's multilingual open-source model. $0.003/request.
- [QwQ 32B](https://docs.ninjachat.ai/api-reference/models/chat/qwq-32b.md): qwq-32b — Qwen's math and logic specialist. $0.003/request.
- [GLM 5](https://docs.ninjachat.ai/api-reference/models/chat/glm-5.md): glm-5 — Zhipu's bilingual Chinese/English model. $0.003/request.
- [MiniMax M2.5](https://docs.ninjachat.ai/api-reference/models/chat/minimax-m2-5.md): minimax-m2.5 — MiniMax's creative writing model. $0.003/request.
- [Ninja 1](https://docs.ninjachat.ai/api-reference/models/chat/ninja-1.md): ninja-1 — NinjaChat's general-purpose model. $0.003/request.
- [Uncensored AI](https://docs.ninjachat.ai/api-reference/models/chat/uncensored-ai.md): uncensored-ai — Unrestricted content generation. $0.003/request.
- [FLUX Kontext Max](https://docs.ninjachat.ai/api-reference/models/image/flux-kontext-max.md): flux-kontext-max — Premium context-aware editing, maximum fidelity. $0.10/image.
- [FLUX.2 Flex](https://docs.ninjachat.ai/api-reference/models/image/flux-2-flex.md): flux-2-flex — Premium quality with exceptional detail. $0.08/image.
- [FLUX.1 Pro Ultra](https://docs.ninjachat.ai/api-reference/models/image/flux-1-pro-ultra.md): flux-1-pro-ultra — Ultra-high resolution up to 4MP. $0.08/image.
- [Recraft V3](https://docs.ninjachat.ai/api-reference/models/image/recraft-v3.md): recraft-v3 — Design and illustration specialist. $0.08/image.
- [Google Imagen 4](https://docs.ninjachat.ai/api-reference/models/image/google-imagen-4.md): google-imagen-4 — Google's photorealistic image model. $0.08/image.
- [Nano Banana Pro](https://docs.ninjachat.ai/api-reference/models/image/nano-banana-pro.md): nano-banana-pro — Professional asset production. $0.08/image.
- [Seedream](https://docs.ninjachat.ai/api-reference/models/image/seedream.md): seedream — Realistic and artistic styles. $0.08/image.
- [FLUX.2 Pro](https://docs.ninjachat.ai/api-reference/models/image/flux-2-pro.md): flux-2-pro — Balanced quality, speed, and cost. $0.05/image.
- [FLUX Kontext Pro](https://docs.ninjachat.ai/api-reference/models/image/flux-kontext-pro.md): flux-kontext-pro — Context-aware image editing. $0.05/image.
- [Nano Banana 2](https://docs.ninjachat.ai/api-reference/models/image/nano-banana-2.md): nano-banana-2 — Best value image generation with text rendering. $0.05/image.
- [FLUX.1 Fill](https://docs.ninjachat.ai/api-reference/models/image/flux-1-fill.md): flux-1-fill — AI inpainting, outpainting, and image extension. $0.05/image.
- [FLUX.2 Klein](https://docs.ninjachat.ai/api-reference/models/image/flux-2-klein.md): flux-2-klein — Fastest FLUX model, optimized for speed. $0.03/image.
- [Nano Banana](https://docs.ninjachat.ai/api-reference/models/image/nano-banana.md): nano-banana — Fast image generation for high-volume tasks. $0.03/image.
- [Veo 3.1](https://docs.ninjachat.ai/api-reference/models/video/veo-3-1.md): veo-3.1 — Google's highest quality video generation. $5.00/video.
- [Veo 3.1 Fast](https://docs.ninjachat.ai/api-reference/models/video/veo-3-1-fast.md): veo-3.1-fast — Speed-optimized variant of Google's best model. $3.00/video.
- [Seedance 2](https://docs.ninjachat.ai/api-reference/models/video/seedance-2.md): seedance-2 — Longest clips up to 15s with unrestricted content. $3.00/video.
- [Kling Video](https://docs.ninjachat.ai/api-reference/models/video/kling-video.md): kling-video — Superior motion quality and scene coherence. $3.00/video.
- [Google Veo 2](https://docs.ninjachat.ai/api-reference/models/video/google-veo-2.md): google-veo-2 — Fastest generation with high visual quality. $3.00/video.
- [Google Veo 3 Fast](https://docs.ninjachat.ai/api-reference/models/video/google-veo-3-fast.md): google-veo-3-fast — Budget-friendly Veo with fast generation. $3.00/video.
- [Chat Completions](https://docs.ninjachat.ai/api-reference/endpoints/chat-completions.md): Generate AI text completions using 26 LLM models. Supports both standard and streaming responses. Cost varies by model tier — see the `model` parameter for pricing details. Also available at the OpenAI-compatible path `/api/v1/chat/completions`.
- [Model Comparison (beta)](https://docs.ninjachat.ai/api-reference/endpoints/model-comparison-beta.md): Compare outputs from two different models on the same prompt. Returns both responses side-by-side with basic metadata. Pricing is based on the underlying models used.
- [Batch Requests](https://docs.ninjachat.ai/api-reference/endpoints/batch-requests.md): Send multiple requests in a single HTTP call. Each item is processed independently and billed as if it were a separate request to the corresponding endpoint.
- [Estimate Request Costs](https://docs.ninjachat.ai/api-reference/management/estimate-request-costs.md): Estimate the cost of one or more planned API requests before sending them. Useful for budgeting and showing users a price quote.
- [List Available Models](https://docs.ninjachat.ai/api-reference/management/list-available-models.md): List all available models, including capabilities, pricing tier, and recommended use cases. Supports filtering by tier, capability, and whether a model is virtual (auto/ensemble).
- [Create Session](https://docs.ninjachat.ai/api-reference/sessions/create-session.md): Create a persistent conversation session. Use the returned session_id with the chat endpoint to maintain context across messages.
- [Retrieve Session](https://docs.ninjachat.ai/api-reference/sessions/retrieve-session.md): Get the full message history and metadata for a session.
- [Delete Session](https://docs.ninjachat.ai/api-reference/sessions/delete-session.md): Permanently delete a session and its stored messages.
- [Export Session](https://docs.ninjachat.ai/api-reference/sessions/export-session.md): Export a session as JSON or Markdown.
- [Web Search](https://docs.ninjachat.ai/api-reference/endpoints/web-search.md): Search the web, academic papers, or news with an optional AI-generated answer that synthesizes the results. Cost: $0.05 per query.
- [Image Generation](https://docs.ninjachat.ai/api-reference/endpoints/image-generation.md): Generate images from text prompts using 6 different models. Supports text-to-image and image-to-image editing with a reference URL. Cost varies by model — from $0.03 to $0.10 per image.
- [Video Generation](https://docs.ninjachat.ai/api-reference/endpoints/video-generation.md): Start a video generation job. Supports 6 models. **$5.00/video:** `veo-3.1` (Google best quality). **$3.00/video:** `seedance-2` (default, uncensored, 5–15s), `kling-video` (motion quality, 5–10s), `google-veo-2` (fast cinematic, 5/6/8s), `veo-3.1-fast` (speed-optimized, 4/6/8s), `google-veo-3-fast`…
- [Video Generation Status](https://docs.ninjachat.ai/api-reference/endpoints/video-generation-status.md): Check the status of a video generation job created by `POST /api/v1/video`. Poll this endpoint until `status` is `completed` or `failed`. Recommended polling interval: every 10–30 seconds. No additional charge for polling. Works with all video models.
- [List API Keys](https://docs.ninjachat.ai/api-reference/management/list-api-keys.md): List all your API keys with usage stats and billing info.
- [Create API Key](https://docs.ninjachat.ai/api-reference/management/create-api-key.md): Create a new API key. You can have up to 5 active keys per account.
- [Revoke API Key](https://docs.ninjachat.ai/api-reference/management/revoke-api-key.md): Revoke an API key. Revoked keys stop working immediately but remain visible in your key list.
- [Credit Purchase History](https://docs.ninjachat.ai/api-reference/management/credit-purchase-history.md): List all credit purchases for the authenticated user, ordered by most recent first.
- [Per-Request Usage Logs](https://docs.ninjachat.ai/api-reference/management/per-request-usage-logs.md): Get granular per-request usage logs with filtering. Supports CSV export via format=csv.

## OpenAPI Specs

- [openapi](https://docs.ninjachat.ai/openapi.json)

## Optional

- [Dashboard](https://www.ninjachat.ai/developers)
- [Playground](https://www.ninjachat.ai/developers/playground)