A Unified API for Chat, Image and Video
Building on a unified API for chat, image and video: sync vs async calls, billing units, retries, timeouts and storage, with three calls and a launch checklist.
Integration tutorials, parameters, quick starts, tool integrations and prompt templates.
Latest Building on a unified API for chat, image and video: sync vs async calls, billing units, retries, timeouts and storage, with three calls and a launch checklist.A Unified API for Chat, Image and Video
More articles
Use the Kimi K3 API internationally: sign up with email, pay by card, create one key and call moonshotai/kimi-k3 with an OpenAI SDK. Steps, code and checks.
Call Tencent Hy3 with the OpenAI SDK outside China: base URL, model id, streaming, tool calls, reasoning_effort values, Hy3 vs Hy3 preview, and token billing.
How to call the Hailuo 3 Max API with an API key: the request, polling and download, the Max-only limits, what sets the cost of one video, and Max vs Hailuo 3.
Call the GTE-Large embedding API with the OpenAI SDK: batch inputs, the 512-token limit, 1024-dim vectors, cosine search, per-token billing, and when to switch.
A Kling CapCut Premiere editing workflow: read frame rate with ffprobe, name and conform clips, hide joins, layer audio and text, grade, export 9:16 or 16:9.
A Hailuo ComfyUI workflow: the MiniMax H3 partner nodes, their limits, a small custom node that calls your own API key, and handing clips to CapCut or Premiere.
Make a Hailuo product video set for each SKU: hero, detail and in-use prompts, which Hailuo id fits listing ratios, keeping labels intact, and a checklist.
Kling lip sync has two routes: native audio that speaks with the picture, or a post-sync pass on existing video. How to choose, write dialogue and check mouths.
Nano Banana edit image prompts that keep the rest intact: one change per turn, say what stays fixed, when to restart, and how to chain edits by API.
Seedance batch generation in Python: a CSV manifest, a small worker pool, idempotent submits, retries by error code, a per-key spend cap and an ffmpeg stitch.
A Seedance n8n workflow that turns sheet rows into video jobs: submit, wait, poll with a cap, download, and error branches keyed to the API's failure codes.
Extend a Seedance video from its last frame: chain clips with first_frame, use the extend task when identity matters, and know when a hard cut works better.
How to write a Veo 3.1 audio prompt: dialogue, sound effects and ambience as three layers, Google's own format, the generate_audio flag, and caption fixes.
Veo camera movement prompts that steer Veo 3.1: dolly, pan, tracking, crane, angle and lens terms from Google's own guides, plus one-move-per-shot prompt order.
Move a Google AI Studio prompt to the Gemini 3.8 Flash API: which settings map to which parameters, thinking and output limits, 429 retries, launch checklist.
GPT image edit mask rules from OpenAI's docs, a keep-everything-else preserve list, and a composite step that keeps untouched pixels identical after the edit.
No-code Hailuo video generation in n8n or Make: a shot-list sheet, create and poll steps, per-model checks for H3 and Hailuo 2.3, and which platform fits whom.
A Kling API Python batch pipeline: CSV in, capped concurrency, retries keyed to error codes, a crash-safe manifest, immediate downloads and an ffmpeg stitch.
How to run Kling in ComfyUI: the Kling 3.0 Video partner node and its inputs, a start-frame workflow, multi-shot storyboards, and when to use a script.
Kling O1 video editing prompts that change one thing and keep the rest: the change, keep, look pattern, Kling's input limits, and what to check on the API.
Limit LLM API spend with a prepaid balance plus four more guardrails: per-key credit limits, caps in code, cost checks before video jobs, and a daily review.
OpenAI compatible API differences between models: token caps, thinking switches, reasoning history, dropped parameters and tool calls, checked against docs.
Run Qwen Image in ComfyUI: exact model files and folders, the nodes in the official workflow, VRAM and speed from the ComfyUI tutorial, Edit versions, fixes.
How to frame Seedance 9:16 vertical video: set the ratio, keep faces and captions out of app UI zones, and avoid the first-frame trap that forces landscape.
Seedance image to video on the API: how to send a first frame, the input limits that fail jobs, why the frame sets the aspect ratio, and motion prompts.
How to write a Seedance lip sync prompt: labeled dialogue lines, language marking, one speaker per shot, voice references, and fixes when mouths drift.
Can Seedance render readable on-screen text and subtitles? What ByteDance says, a six-field text spec, how to stop stray captions, and when to add text in post.
A Wan video API, Make and CapCut workflow for 15-second ads: a five-shot list, two Make scenarios that survive failed jobs, the Wan 3.0 fields, and edit steps.
What is Kimi K3? Moonshot's 2.8T-parameter open-weight model: release date, 1M context window, what changed from Kimi K2, and the API traps to plan around.
What is MiniMax M3? MiniMax's open-weight multimodal model: June 2026 release, 1M context, thinking modes, what changed from M2, and the limits to plan around.
Aider Claude setup: use an Anthropic API key or an OpenAI-compatible base URL, pass full model ids instead of stale aliases, and pair architect and editor.
Claude prompt caching in Python with the Anthropic SDK: where cache_control goes, model minimums, reading usage fields, and the mistakes that cause misses.
Use the Gemini OpenAI compatible API from the OpenAI SDK: change base URL and model id, then retest thinking, max_tokens, dropped parameters and tools.
Gemini thinking level explained: defaults per model, how thinking tokens bill as output, thinking budget on 2.5, and how to set the level per route.
GLM function calling in Python: define tools, run the tool_calls loop, return reasoning with results, and handle tool_choice auto-only and silent drops.
GLM-5.3-Flash image input in Python: send image URLs or base64 with the OpenAI SDK, stay inside size and image limits, and know where its vision is weak.
GPT structured outputs with a JSON schema: strict-mode rules, size limits, refusal and truncation checks, a Pydantic example, and JSON mode compared.
Use Hailuo first and last frame control for cuts, morphs and loops: which models accept it, image and size rules, the crop pitfall, and a Python example.
Hailuo H3 audio and dialogue: what MiniMax documents about native stereo sound, reference audio limits, writing spoken lines, and checks before you ship.
Hailuo prompt length limits by model (2,000 characters on 2.3, 7,000 on H3), MiniMax's camera commands, words worth testing, and words to cut from prompts.
Keep one character consistent with Hailuo subject reference: S2V-01's one-image rules, H3's up to nine reference images, picking the image, and where it slips.
Write Kling action scene prompts as short beats: the 3-15 s and six-shot limits, physics words, camera by action type, contact and multi-person fixes.
Kling camera control is in the prompt: push-in, pan, tilt, track, orbit, crane, dolly zoom. One move per shot, speed, end point, and what the API lacks.
Kling character consistency across shots: reusable references, image-to-video from fixed stills, a locked identity line, and motion control, with trade-offs.
How Kling Elements work: building one from a frontal image plus 1 to 3 references, the Omni reference limits, @ prompt names, and sending images on OceanToken.
Kling image to video done right: pick a sharp first frame at the output ratio, prompt only the motion, keep start and end frames close, and know the API limits.
Kling Motion Brush paints which part of an image moves and along what path. How to use it, why we found no API field for it, and what to use in code instead.
OpenAI SDK video generation for Kling in Python and Node: create_and_poll vs a manual poll loop, Kling parameters, error codes, idempotent retries, downloads.
Set the LangChain OpenAI base_url and a LlamaIndex custom endpoint for GPT: env-var order, stream usage, structured output, OpenAILike and its defaults.
Set an n8n OpenAI custom base URL on the credential, type prefixed GPT ids by ID, and avoid the agent traps: hidden reasoning effort, timeouts, loops.
Use Qwen enable_thinking per request: which tasks need it, sizing thinking_budget, streaming reasoning_content, multi-turn preserve_thinking, and sampling.
Connect Qwen to Dify, LobeChat and Cherry Studio with an OpenAI-compatible base URL: where each tool wants the URL, the /v1 trap, model ids, and fixes.
Get valid Qwen JSON output: json_object vs json_schema, which Qwen models enforce a schema, keywords that return 400, max_tokens and thinking pitfalls, retries.
How to send images to the Qwen vision API: URL vs base64, Alibaba's size and count limits, the 32x32 token formula, and what high-res mode costs.
Set up Qwen3 Coder Next behind a coding agent: base URL, model id, sampling, context limits, a capped tool loop, and what an 80B-A3B non-thinking coder suits.
Seedance camera movement prompts that read: push-in, dolly, orbit, tracking, tilt, locked-off. One move per shot, speed words, and when to use a reference.
Seedance character consistency in practice: a headshot plus full-body reference, a locked description block, an anchor shot, last-frame chaining and seeds.
How to write a Seedance music video prompt: split the song into sections, give the audio reference a job, mix performance and b-roll, and sync in the edit.
A Seedance product demo prompt that keeps the product right: lock the design to one reference image, one camera move per shot, and keep labels short and clean.
Six Seedance prompt templates by genre (horror, romance, action, documentary, sci-fi, comedy): one copyable structure per genre with camera, light and sound.
The best chat UI for GLM depends on who uses it. Open WebUI setup steps, where Cherry Studio takes a base URL, which GLM ids to add, and fixes.
Gemini structured output and function calling pitfalls: JSON schema limits, tools plus JSON on Gemini 3 only, MALFORMED_FUNCTION_CALL, dropped params, fixes.
Run the Hailuo API in Python: create a task, poll its status, fetch the file before the 1-hour link expires, and handle MiniMax error codes and callbacks.
Kling API tutorial from Kuaishou's docs: create a Kling 3.0 task, poll or use callback_url, every setting, error 1303, and how the flow maps to OceanToken.
How Kling multi-shot works in Kling 3.0: the official shot syntax inside the prompt, six-shot and 15-second limits, and how to write a shot list that holds.
Build a Kling n8n workflow, or the same in Make: create the video job, poll status every 10-20 s, download within 24 hours, and retry safely with idempotency.
Qwen function calling in Python with the OpenAI SDK: a complete tool loop, tool_choice values Qwen rejects, parallel calls, streaming arguments and fixes.
Qwen Image API guide: models, size and n limits, prompt_extend, editing inputs and 24-hour image URLs from Alibaba's docs, plus one OceanToken key for it all.
Seedance API parameters explained: which model id to pick, resolution and duration limits, Native vs Upscaled, safe create requests and output file handling.
A Seedance API Python quickstart: one POST to create a video job, a GET loop to poll it, one GET to download the MP4, plus the status and URL pitfalls to catch.
How to run Seedance 2.0 in ComfyUI with partner nodes: templates, login and credit rules, real-person checks, Comfy's limits, and when to use the API.
How to write a Seedance multi shot prompt for 2.0: shot labels, one camera move per shot, cut markers, stable character labels, and a five-shot template to run.
Four Seedance UGC ad prompts to copy (review, unboxing, 3am moment, hands-only), how to write the hook, and why real-person reference photos get refused.
Developers now run Claude Code and Codex side by side. How to put both on one Claude Code API key setup, cap what each agent can spend, and add video, image and voice tools.
RSS feed
Every new article, in your feed reader.
oceantoken.ai/blog/rss.xml