# API Stock > One API, one key and one prepaid balance for many third-party AI generation models — video, image, music and chat (LLM). Each request is priced, charged from the prepaid balance, dispatched to a provider and returned by polling or webhook, with automatic failover to a reserve provider on failure. ## Key pages - [Model catalog](https://api-stock.com/models): every model with live pricing. - [Pricing](https://api-stock.com/pricing): prepaid, pay-per-use pricing. - [Machine-readable pricing](https://api-stock.com/pricing.md): the same prices as Markdown. - [Agent tools](https://api-stock.com/agent-tools): MCP setup for coding agents, the OpenClaw skill, media examples and the built-in agent. - [Documentation](https://docs.api-stock.com/): API reference, quick start and guides. - [Documentation llms.txt](https://docs.api-stock.com/llms.txt): machine-readable docs index. - [MCP server](https://docs.api-stock.com/docs/mcp): remote MCP endpoint for AI agents (Codex, Claude Code and other MCP clients) — list models, estimate cost, create generations and fetch results; OAuth sign-in in the browser, no API key. Add it with: Codex: `codex mcp add api-stock --url https://api.api-stock.com/mcp`, `codex mcp login api-stock`; Claude Code: `claude mcp add --transport http api-stock https://api.api-stock.com/mcp` - [Blog](https://api-stock.com/blog): pricing breakdowns, model comparisons and walkthroughs, newest first (RSS: /rss.xml). - [Full text](https://api-stock.com/llms-full.txt): every guide and blog post in one Markdown file. append .md to any /guides or /blog URL for plain Markdown. ## Guides - [Give your coding agent image, video and music tools](https://api-stock.com/guides/agent-media): Connect Claude Code, Codex, OpenCode or OpenClaw to API Stock and use generated media in a page, app or content draft. - [Generate images in Claude Code with API Stock](https://api-stock.com/guides/claude-code): Add API Stock media tools to Claude Code, check access and create a landing-page illustration with a request spending ceiling. - [Generate image assets from Codex with API Stock](https://api-stock.com/guides/codex): Connect Codex to API Stock over MCP and add a generated image to your app with an estimate, spending ceiling and resumable task. - [Add image and video generation to OpenCode](https://api-stock.com/guides/opencode): Configure API Stock as a remote MCP server in OpenCode, authenticate and create media alongside your selected coding model. - [Connect Cursor to API Stock](https://api-stock.com/guides/cursor): Add image, video and music generation to Cursor through MCP, or configure a chat model with your API key. - [Connect OpenClaw to API Stock](https://api-stock.com/guides/openclaw): Configure a model provider, check your connection and add image, video and music tools to an OpenClaw agent. - [Generate images and video with an OpenClaw agent](https://api-stock.com/guides/openclaw-media): Give an agent a media task with a quoted price, a server-enforced ceiling and a durable task id it can resume. - [Choose a model for an agent task](https://api-stock.com/guides/agent-model-selection): Compare models on completed tool-using tasks, repeated attempts and observed cost before setting an agent's default. - [Text to video](https://api-stock.com/guides/text-to-video): Which text-to-video model fits the shot you have in mind, prompts that actually work, and the full API run from create to finished file. - [Image to video](https://api-stock.com/guides/image-to-video): Turning a still into a shot — which model to animate it with, first and last frame control, motion transfer, and the prompts that keep the subject intact. - [Image generation](https://api-stock.com/guides/image-generation): Which image model to use for the picture you need, prompts that produce it, batching for variants, and the API run from prompt to file URL. - [Image editing](https://api-stock.com/guides/image-editing): Editing photos with references instead of prompts — background swaps, product composites, style matching, and the Midjourney action chain from imagine to inpaint. - [GPT Image 2.5 — Sunburst, Flare, prompts and real examples](https://api-stock.com/guides/gpt-image-2-5): Choose a GPT Image model, compare Sunburst and Flare, copy four practical prompts, inspect six real renders, and generate or edit images through API Stock. - [Seedream 5.0 Pro prompts — miniature worlds, glass and watercolor](https://api-stock.com/guides/seedream-5-0-pro): Run three sourced creative prompts in 1K, inspect our Seedream Pro results and compare the same tasks with Nano Banana 2.1. - [Seedream 5.0 Pro vs Nano Banana 2.1 — three creative briefs in 1K](https://api-stock.com/guides/seedream-5-0-pro-vs-nano-banana-2-1): Six new results from sourced prompts: a Hollywood diorama, a glass willow and a shared-source watercolor edit, with exact inputs and matched 1K prices. - [Music generation](https://api-stock.com/guides/music-generation): Writing songs, jingles and sound effects with Suno — simple versus custom mode, style prompts that work, extending and covering tracks, stems and voice personas. - [LLM API pricing: GPT, Claude, Gemini, DeepSeek compared](https://api-stock.com/guides/llm-api-pricing): Compare LLM API pricing for GPT, Claude, Gemini, DeepSeek, Grok and Kimi per 1M tokens, with worked monthly cost examples and practical ways to cut the bill. - [Going to production](https://api-stock.com/guides/production-checklist): Key handling, webhooks over polling, idempotency, terminal states, retry policy by error code, balance monitoring, rate limits and media storage. ## Blog - [Seedream 5.5 transparent PNG: settings, alpha checks and cost](https://api-stock.com/blog/seedream-5-5-transparent-png) (2026-11-17): Create a transparent PNG with Seedream 5.5, check its alpha channel before compositing, and budget reference images and rejected attempts with live prices. - [Gemini Omni 1.2 Flash API: video edits, duration and cost](https://api-stock.com/blog/gemini-omni-1-2-flash-api) (2026-11-10): Create, edit or extend video with Gemini Omni 1.2 Flash: compare 1.1 prices, calculate billable seconds, and follow one API task through to a saved file. - [FLUX 3 Image vs Klein: API edits and cost per banner](https://api-stock.com/blog/flux-3-image-vs-klein) (2026-11-09): Build a reference-based banner with FLUX 3 Image from $0.06 at 1K, compare Klein's separate API, and budget drafts, final renders and rejected attempts. - [GPT-6.1 Sol vs Claude Opus 5.5: benchmarks and cost](https://api-stock.com/blog/gpt-6-1-sol-vs-claude-opus-5-5) (2026-11-05): Compare GPT-6.1 Sol and Claude Opus 5.5 using published coding benchmarks, Agent Arena results, current API tariffs and a fixed token budget. - [GPT-6.1 Sol vs Claude Sonnet 5.5: benchmarks and cost](https://api-stock.com/blog/gpt-6-1-sol-vs-claude-sonnet-5-5) (2026-11-05): Compare GPT-6.1 Sol and Claude Sonnet 5.5 using Artificial Analysis benchmarks, Agent Arena intervals, API protocols and a fixed token budget. - [GPT-6 Astra vs Claude Fable 5.1: benchmarks and cost](https://api-stock.com/blog/gpt-6-astra-vs-claude-fable-5-1) (2026-11-05): Compare GPT-6 Astra and Claude Fable 5.1 with published benchmarks, Agent Arena confidence intervals, API prices and two explicit cache scenarios. - [GPT Image 2.6 review: Flare, Sunburst, pricing and examples](https://api-stock.com/blog/gpt-image-2-6-review) (2026-11-13): GPT Image 2.6 now has separate Flare and Sunburst IDs and output up to 4K: check live prices, a poster budget, historical samples and the updated API request. - [Kling 4.0 vs Seedance 2.5: audio, references and cost](https://api-stock.com/blog/kling-4-0-vs-seedance-2-5) (2026-11-05): Compare Kling 4.0 and Seedance 2.5 for ten-second videos: current 720p and 1080p costs, audio, reference inputs and a realistic candidate budget. - [Nano Banana 2.1 vs GPT Image 2.5: prices and image size](https://api-stock.com/blog/nano-banana-2-1-vs-gpt-image-2-5) (2026-11-05): Choose between Nano Banana 2.1 and GPT Image 2.5 Sunburst using current 1K, 2K and 4K prices, editing limits and a budget for image candidates. - [Animate an illustration with AI: prompts and a $0.09 first clip](https://api-stock.com/blog/animate-illustration-ai) (2026-10-24): Turn a finished illustration into a six-second teaser with Grok Video: a motion prompt, a $0.09 first attempt, and checks for changes to your artwork. - [AI product description translation: a prompt and a real example](https://api-stock.com/blog/ai-product-description-translation) (2026-10-22): Translate a product listing with Gemini 3.8 Flash using a glossary and fact checks, with a real English-to-French example and its measured token cost. - [AI storyboard: plan three video shots with prompts and cost](https://api-stock.com/blog/ai-storyboard-three-shots) (2026-10-20): Plan a three-shot video with Seedream Pro stills from $0.042 each, using a lighthouse script, reference prompts and continuity checks before motion. - [AI girlfriend chat: personality, photos and video](https://api-stock.com/blog/obshchenie-s-virtualnoj-devushkoj) (2026-10-19): Start an AI girlfriend chat in agent mode: shape her personality, build a continuing story, generate photos and video, and control your spending. - [Grok image editing: photo URLs, model choice and cost](https://api-stock.com/blog/grok-image-editing-photo-url) (2026-10-18): Edit a photo with Grok Imagine 1.5 using a public image URL, not an image ID: copy a request, retrieve the result and budget $0.022 per generation. - [AI agent: turn a brief into text and images](https://api-stock.com/blog/ai-agent-guide) (2026-10-16): Use the new agent to turn a brief and reference files into text and images, choose models, set a spending limit and keep results in projects. - [AI YouTube thumbnails: prompts, real screenshots and cost](https://api-stock.com/blog/ai-youtube-thumbnail-backgrounds) (2026-10-16): Make an AI YouTube thumbnail backdrop for $0.014, add your real video still and editable title, then check the crop with practical tutorial prompts. - [Seedance 2.5 Spicy: less moderation, more creative freedom](https://api-stock.com/blog/seedance-spicy-creative-freedom) (2026-10-15): Seedance 2.5 Spicy brings relaxed content moderation to video generation: explore bolder ideas with audio, references and clips up to 30 seconds. - [AI wall paint color preview: your room, three shades and cost](https://api-stock.com/blog/ai-wall-paint-color-preview) (2026-10-14): Preview wall paint colors in your own room photo with Seedream Pro from $0.042 per image, using paint-only prompts and checks before buying real samples. - [Create AI images, video and music in our Telegram bot](https://api-stock.com/blog/telegram-ai-bot) (2026-10-14): Open the Telegram bot, choose a model and confirm the price to create images, video and music, with the same account and balance you use on the website. - [AI background music for voiceovers: prompts and cost](https://api-stock.com/blog/ai-background-music-for-voiceovers) (2026-10-12): Make instrumental background music for a voiceover with Suno from $0.075 per request, then test it under speech, trim it and budget for alternate takes. - [Wan 3.0 Pro: more creative freedom, video up to 4K](https://api-stock.com/blog/wan-3-0-pro-creative-freedom) (2026-10-12): Wan 3.0 Pro brings relaxed moderation, video up to 4K and audio to API Stock. Explore bolder scenes, reference inputs and prices from $0.086 per second. - [AI support ticket summaries: a MiniMax M3 handoff tutorial](https://api-stock.com/blog/ai-support-ticket-handoff-minimax-m3) (2026-10-10): Turn a support thread into a source-backed agent handoff with MiniMax M3: a reusable prompt, an API example and a $1.08-per-1,000 token-cost scenario. - [AI avatar from a photo: prompts, likeness checks and cost](https://api-stock.com/blog/ai-avatar-from-photo) (2026-10-08): Make a square AI avatar from your photo with Seedream Pro, starting at $0.042 per image; use portrait prompts and check likeness before the circular crop. - [Nano Banana 2.1 review: 4K images at one flat price](https://api-stock.com/blog/nano-banana-2-1-review) (2026-10-07): Nano Banana 2.1 brings 1K, 2K and 4K image generation and reference editing at a price of $0.014 per image. See its limits, use cases and API request. - [AI images for presentations: prompts and cost per slide](https://api-stock.com/blog/ai-images-for-presentations) (2026-10-06): Create wide slide illustrations with Seedream 5.0 Pro from $0.042 per image, keep text editable, and budget for revisions with practical prompts. - [Claude API pricing after Sonnet 5.5 and Opus 5.5: cost per task](https://api-stock.com/blog/claude-api-models-and-pricing) (2026-10-04): Anthropic released Claude Opus 5.5 and Sonnet 5.5 in late September 2026. What changed, what each Claude model costs per task, and which one to pick. - [AI music video for your song: models, prompts and cost](https://api-stock.com/blog/ai-music-video-for-a-song) (2026-10-02): How to make an AI music video for a song: which model suits which shot, prompts that work, and what three minutes of footage cost, from $2.38. - [Seedance 2.5 API: release date, pricing and cost per clip](https://api-stock.com/blog/seedance-2-5-api) (2026-11-05): Seedance 2.5 costs $2.15 for ten seconds at 720p or $7.62 at 1080p; see reference-video billing and a three-shot budget with extra attempts. - [AI product photos for an online store: models, prompts, cost](https://api-stock.com/blog/ai-product-photos-online-store) (2026-10-30): Plan AI product photos from $0.014 per 2K request: compare models, adapt prompts, inspect product details and budget a store catalog before scaling. - [Sora 2 API is shut down: the alternatives and what they cost](https://api-stock.com/blog/sora-2-api-shutdown-alternatives) (2026-11-10): Replace the retired Sora 2 API by input type and duration. Compare current 720p costs, audio settings and a Veo migration request. ## Video models - [Agnes Video 2.5](https://api-stock.com/model/agnes-video-2.5) (Agnes AI): Generate 1–12 second videos from text, up to 9 reference images and 3 audio references. Supports 720p, 1080p and 2K output in six aspect ratios. — from $0.023 per second of output - [FLUX 3 Video](https://api-stock.com/model/flux-3-video) (Black Forest Labs, released 2026-07-23): Black Forest Labs' multimodal video model with native synchronized audio. Text-to-video, keyframes (1-10 images) and continuation of an existing clip, 5-20 seconds at 720p/1080p, with a low-cost draft mode. — from $0.069 per second of output - [Gemini Omni 1.1 Flash](https://api-stock.com/model/gemini-omni-1.1-flash) (Google, released 2026-08-27): Generate 4–10 second video with sound from text, first/last frames and image references, or transform a 3–10 second source video. Output from 360p to upscaled 4K. — from $0.279 per generation - [Gemini Omni 1.2 Flash](https://api-stock.com/model/gemini-omni-1.2-flash) (Google, released 2026-11-05): Generate 3–15 second videos with native audio from text, images and subject references. Interpolate first/last frames, edit a source video or extend it by up to 10 seconds. Output from 360p to upsampled 4K. — from $0.029 per second of output - [Grok Imagine 1.5 Video](https://api-stock.com/model/grok-imagine-1.5-video) (xAI, released 2026-06-16): Generate short video from text or animate a reference image. — from $0.014 per second of output - [Kling 3.0](https://api-stock.com/model/kling-3.0) (Kling, released 2026-02-05): Generate video from text or frames with native audio, up to 15 seconds and 4K. — from $0.091 per second of output - [Kling 3.0 Motion Control](https://api-stock.com/model/kling-3.0-motion-control) (Kling, released 2026-03-05): Transfer motion from a reference video to a character image. — from $0.065 per second of output - [Kling 4.0](https://api-stock.com/model/kling-4.0) (Kling, released 2026-10-15): Generate 3–30 second videos with stereo audio, references, keyframes and video editing at 720p or 1080p. — from $0.189 per second of output - [Kling 4.0 Flash](https://api-stock.com/model/kling-4.0-flash) (Kling, released 2026-11-12): Generate 3–20 second 720p videos with native audio from text, a first frame or image and video references. — from $0.132 per second of output - [MiniMax H3](https://api-stock.com/model/minimax-h3) (MiniMax, released 2026-07-31): Text, image and audio reference video generation at 480p, 768p or 1080p. 1–15 seconds (up to 10 at 1080p), up to 9 images and 3 audio references. First 5 images and all audio references are free; extra images are billed separately per request. — from $0.016 per second of output - [PixVerse V6](https://api-stock.com/model/pixverse-v6) (PixVerse, released 2026-03-30): Generate video from text or frames with motion, audio, and continuation controls. — from $0.024 per generation - [Seedance 1.5 Pro](https://api-stock.com/model/seedance-1-5-pro) (ByteDance, released 2025-12-16): Generate cinematic video from text or first/last frame images with optional generated audio. — from $0.065 per generation - [Seedance 2.0](https://api-stock.com/model/seedance-2.0) (ByteDance, released 2026-02-12): Generate 4-15 second video from text, first/last frames, and multimodal image, video, or audio references at up to 4K resolution. — from $0.09 per second of output - [Seedance 2.0 Fast](https://api-stock.com/model/seedance-2.0-fast) (ByteDance, released 2026-04-14): Generate 4-15 second video faster from text, first/last frames, and multimodal image, video, or audio references at 480p or 720p. — from $0.057 per second of output - [Seedance 2.0 Mini](https://api-stock.com/model/seedance-2.0-mini) (ByteDance, released 2026-06-15): Generate lightweight 4-15 second video from text, first/last frames, and multimodal image, video, or audio references at 480p or 720p. — from $0.025 per second of output - [Seedance 2.5](https://api-stock.com/model/seedance-2.5) (ByteDance, released 2026-07-31): Generate 4-30 second video from text, first/last frames, and multimodal image, video, or audio references at 480p, 720p, or 1080p. — from $0.137 per second of output - [Seedance 2.5 Flash](https://api-stock.com/model/seedance-2.5-flash) (ByteDance, released 2026-11-15): Generate 4–30 second videos with audio from text, first/last frames, and image, video or audio references at 480p or 720p. — from $0.063 per second of output - [Seedance 2.5 Flash Spicy](https://api-stock.com/model/seedance-2.5-flash-spicy) (ByteDance): Generate, edit and extend 480p or 720p videos with native audio and image, video or audio references through APIPod’s relaxed-moderation Seedance 2.5 Flash route. — from $0.1 per second of output - [Seedance 2.5 Spicy](https://api-stock.com/model/seedance-2.5-spicy) (ByteDance): Generate 4-30 second videos with native audio and image, video or audio references at up to 1080p through APIPod’s relaxed-moderation Seedance 2.5 route. — from $0.142 per second of output - [Veo 3.1 Fast](https://api-stock.com/model/veo3.1-fast) (Google, released 2025-10-15): Generate video quickly from text or reference images with resolution controls. — from $0.2 per generation - [Veo 3.1 Lite](https://api-stock.com/model/veo3.1-lite) (Google, released 2026-03-31): Cheapest Veo 3.1 tier for high-volume text-to-video. 8-second clips with audio at 720p, 1080p or 4k. Text prompt only — no reference images. — from $0.1 per generation - [Veo 3.1 Quality](https://api-stock.com/model/veo3.1-quality) (Google, released 2025-10-15): Quality-focused video generation from text or reference images. — from $1.43 per generation - [Wan 2.7 Video](https://api-stock.com/model/wan2.7-video) (Alibaba, released 2026-04-07): Generate, edit, reference, or continue video through one flexible model. — from $0.086 per second of output - [Wan 3.0 Pro](https://api-stock.com/model/wan3.0-video-pro) (Alibaba, released 2026-10-11): Wan 3.0 Pro video generation from text, first and last frames, or multimodal references. 2–30 seconds with native audio at 480p, 720p, 1080p, 2K or 4K. — from $0.085 per second of output - [Wan 3.0 Video](https://api-stock.com/model/wan3.0-video) (Alibaba, released 2026-08-24): Alibaba Wanxiang 3.0 all-in-one reference video model. Text, first frame, first + last frame, multi-modal reference (images, video, audio) and document or web page references, 2-30 seconds at 480p/720p/1080p. — from $0.047 per second of output - [Wan 3.0 Video Prime](https://api-stock.com/model/wan3.0-video-prime) (Alibaba, released 2026-08-24): Faster Wan 3.0 video generation from text, first and last frames, or multimodal image, video, audio, document and web references. 2–30 seconds at 480p, 720p or 1080p. — from $0.074 per second of output ## Image models - [FLUX 3 Image](https://api-stock.com/model/flux-3-image) (Black Forest Labs, released 2026-10-08): Generate and edit images with up to 10 references, flexible framing, web search and resolution tiers up to 4K. — from $0.055 per generation - [GPT Image 2](https://api-stock.com/model/gpt-image-2) (OpenAI, released 2026-04-21): Generate and edit images with flexible aspect ratios, resolution, and quality controls. — from $0.013 per generation - [GPT Image 2.5 Flare](https://api-stock.com/model/gpt-image-2.5-flare) (OpenAI, released 2026-09-08): Generate and edit images with the Flare variant of GPT Image 2.5, with output up to 4K. — from $0.01 per generation - [GPT Image 2.5 Sunburst](https://api-stock.com/model/gpt-image-2.5-sunburst) (OpenAI, released 2026-09-08): Generate and edit images with the Sunburst variant of GPT Image 2.5, with output up to 4K. — from $0.01 per generation - [GPT Image 2.6 Flare](https://api-stock.com/model/gpt-image-2.6-flare) (OpenAI, released 2026-11-06): Generate and edit images up to 4K with GPT Image 2.6 Flare. Both variants share the base 2.6 engine at 1K; 2K/4K select the named engine. Image quality is configurable and defaults to high. — from $0.013 per generation - [GPT Image 2.6 Sunburst](https://api-stock.com/model/gpt-image-2.6-sunburst) (OpenAI, released 2026-11-06): Generate and edit images up to 4K with GPT Image 2.6 Sunburst. Both variants share the base 2.6 engine at 1K; 2K/4K select the named engine. Image quality is configurable and defaults to high. — from $0.013 per generation - [Grok Imagine 1.5 Image](https://api-stock.com/model/grok-imagine-1.5-image) (xAI): Generate or transform images from a prompt and optional reference image. — from $0.021 per generation - [Grok Imagine 2.0 Image](https://api-stock.com/model/grok-imagine-2.0-image) (xAI, released 2026-08-07): Generate batches of images from a text prompt in common aspect ratios. — from $0.021 per generation - [Nano Banana](https://api-stock.com/model/nano-banana) (Google, released 2025-08-26): Create and edit images from a prompt and optional reference images. — from $0.012 per generation - [Nano Banana 2](https://api-stock.com/model/nano-banana-2) (Google, released 2026-02-26): Generate and edit images from prompts and reference images at multiple resolutions. — from $0.018 per generation - [Nano Banana 2 Lite](https://api-stock.com/model/nano-banana-2-lite) (Google, released 2026-06-30): Fast 1K image generation and editing from text and reference images. — from $0.005 per generation - [Nano Banana 2.1](https://api-stock.com/model/nano-banana-2.1) (Google, released 2026-10-07): Generate and edit images from prompts and reference images at multiple resolutions. — from $0.014 per generation - [Nano Banana Pro](https://api-stock.com/model/nano-banana-pro) (Google, released 2025-11-20): Quality-focused image generation and editing with reference-image support. — from $0.029 per generation - [Seedream 4.5](https://api-stock.com/model/seedream-4-5) (ByteDance, released 2025-12-03): Generate and edit detailed images from prompts and reference images. — from $0.036 per generation - [Seedream 5.0 Flash](https://api-stock.com/model/seedream-5-0-flash) (ByteDance, released 2026-09-15): Fast image generation and editing at 1K, 1.5K or 2K, with up to 10 reference images. — from $0.021 per generation - [Seedream 5.0 Lite](https://api-stock.com/model/seedream-5-0-lite) (ByteDance, released 2026-02-13): Fast image generation and editing from text and reference images. — from $0.033 per generation - [Seedream 5.0 Pro](https://api-stock.com/model/seedream-5-0-pro) (ByteDance, released 2026-07-08): Quality-focused image generation and editing with up to 2K output. — from $0.052 per generation - [Seedream 5.5](https://api-stock.com/model/seedream-5-5) (ByteDance): Image generation and editing at 1K, 1.5K or 2K, with transparent PNG backgrounds and up to 10 references. — from $0.028 per generation - [Wan 2.7 Image](https://api-stock.com/model/wan2.7-image) (Alibaba, released 2026-04-01): Generate and edit images with aspect-ratio, pixel-size, and seed controls. — from $0.029 per generation - [Z-Image](https://api-stock.com/model/z-image) (Alibaba, released 2025-11-26): Generate and edit images from text with optional reference images and safety control. — from $0.01 per generation ## Music models - [Suno](https://api-stock.com/model/suno) (released 2026-09-09): Suno audio generation: create songs, lyrics and sound effects, and edit existing tracks (extend, cover, stems, fades, mashup, remaster, MV, persona and more) — one model selected by the `action` field. — from $0.075 per generation ## Chat / LLM models - [Claude Fable 5](https://api-stock.com/model/claude-fable-5) (Anthropic, released 2026-06-09): Anthropic model tuned for long-form writing and narrative work. — from $1.5 per 1M input tokens - [Claude Fable 5.1](https://api-stock.com/model/claude-fable-5.1) (Anthropic): Anthropic's Mythos-class model for autonomous knowledge work and coding, with a 1M-token context window and text, image and file input. — from $10 per 1M input tokens - [Claude Fable 5.2](https://api-stock.com/model/claude-fable-5.2) (Anthropic, released 2026-11-09): Anthropic model for demanding reasoning, coding and long-running agent workflows, with a 1M-token context window and always-on adaptive thinking. — from $3.6 per 1M input tokens - [Claude Opus 5](https://api-stock.com/model/claude-opus-5) (Anthropic, released 2026-07-24): Anthropic's most capable model for complex reasoning, coding and agentic work. — from $3 per 1M input tokens - [Claude Opus 5.5](https://api-stock.com/model/claude-opus-5-5) (Anthropic): Successor to Claude Opus 5 for demanding reasoning, coding and long-running agentic work. — from $4.8 per 1M input tokens - [Claude Sonnet 5](https://api-stock.com/model/claude-sonnet-5) (Anthropic, released 2026-06-30): Anthropic's balanced model for coding, agentic workflows and everyday reasoning. Text and image input, long context. — from $0.3 per 1M input tokens - [Claude Sonnet 5.5](https://api-stock.com/model/claude-sonnet-5-5) (Anthropic): Upgraded Sonnet-class model for agentic coding, tool use and everyday professional work — faster than Claude Sonnet 5. — from $0.9 per 1M input tokens - [DeepSeek V4 Flash](https://api-stock.com/model/deepseek-v4-flash) (DeepSeek, released 2026-04-24): Fast, very low cost DeepSeek tier for high-volume classification, extraction and chat. — from $0.168 per 1M input tokens - [DeepSeek V4 Pro](https://api-stock.com/model/deepseek-v4-pro) (DeepSeek, released 2026-04-24): DeepSeek's frontier reasoning model. Strong at maths, coding and long analytical chains at a fraction of Western frontier pricing. — from $0.522 per 1M input tokens - [Gemini 3.5 Flash](https://api-stock.com/model/gemini-3.5-flash) (Google, released 2026-05-19): Fast general-purpose chat and structured generation through the OpenAI protocol. — from $0.9 per 1M input tokens - [Gemini 3.6 Flash](https://api-stock.com/model/gemini-3.6-flash) (Google, released 2026-07-21): High-efficiency Google model for coding, agentic workflows and web/app development. 1M-token context, text/image/audio/video/file input. — from $0.9 per 1M input tokens - [Gemini 3.7 Flash](https://api-stock.com/model/gemini-3.7-flash) (Google, released 2026-08-13): Latest Gemini Flash tier — fast multimodal reasoning at a low token price. — from $0.9 per 1M input tokens - [Gemini 3.8 Flash](https://api-stock.com/model/gemini-3.8-flash) (Google): Latest Gemini Flash tier — fast multimodal reasoning at a low token price. — from $0.9 per 1M input tokens - [Gemini 4 Carbon](https://api-stock.com/model/gemini-4-carbon) (Google): Gemini 4 Carbon for text generation, coding, tool calling and image analysis through the OpenAI-compatible Chat Completions API. — from $2.4 per 1M input tokens - [Gemini 4 Hydrogen](https://api-stock.com/model/gemini-4-hydrogen) (Google): Gemini 4 Hydrogen for text generation, coding, tool calling and image analysis through the OpenAI-compatible Chat Completions API. — from $0.596 per 1M input tokens - [GLM 5.2](https://api-stock.com/model/glm-5.2) (Zhipu, released 2026-06-16): Zhipu's flagship general model with strong tool use and bilingual (EN/ZH) performance. — from $1.37 per 1M input tokens - [GLM 5.3](https://api-stock.com/model/glm-5.3) (Zhipu, released 2026-08-14): Zhipu's GLM-5.3 — successor to GLM-5.2 with stronger tool use and bilingual (EN/ZH) reasoning. — from $1.68 per 1M input tokens - [GPT 5.5](https://api-stock.com/model/gpt-5.5) (OpenAI, released 2026-04-24): Broadly capable GPT-5.5 model for everyday reasoning, coding and writing. — from $1.5 per 1M input tokens - [GPT 5.6 Luna](https://api-stock.com/model/gpt-5.6-luna) (OpenAI, released 2026-07-09): Fast, cost-efficient model of the GPT-5.6 series. Suited for high-volume, latency-sensitive chat, classification and lightweight agentic workflows. — from $0.18 per 1M input tokens - [GPT 5.6 Sol](https://api-stock.com/model/gpt-5.6-sol) (OpenAI, released 2026-07-09): Frontier model of the GPT-5.6 series for the hardest reasoning, coding and agentic tasks. Text, image and file input, 1M-token context. — from $3 per 1M input tokens - [GPT 5.6 Terra](https://api-stock.com/model/gpt-5.6-terra) (OpenAI, released 2026-07-09): High-capability GPT-5.6 model for long-context, tool-enabled workflows across writing, coding, analysis and multi-step problem solving. Text, image and file input. — from $1.2 per 1M input tokens - [GPT 6 Astra](https://api-stock.com/model/gpt-6-astra) (OpenAI, released 2026-09-03): Frontier GPT-6 model for the hardest reasoning, coding and agentic work. Text, image and file input. — from $8 per 1M input tokens - [GPT 6 Luna](https://api-stock.com/model/gpt-6-luna) (OpenAI): Fast, low-cost model of the GPT-6 series for chat, classification and high-volume tasks. Text, image and file input. — from $0.12 per 1M input tokens - [GPT 6 Sol](https://api-stock.com/model/gpt-6-sol) (OpenAI): High-capability model of the GPT-6 series for demanding reasoning, coding and agentic tasks. Text, image and file input. — from $2.4 per 1M input tokens - [GPT 6.1 Sol](https://api-stock.com/model/gpt-6.1-sol) (OpenAI): Refreshed Sol model of the GPT-6.1 series for demanding reasoning, coding and agentic tasks. Text, image and file input. — from $1.8 per 1M input tokens - [GPT 6.1 Terra](https://api-stock.com/model/gpt-6.1-terra) (OpenAI, released 2026-10-26): Fast GPT-6.1 model for visual reasoning, spatial tasks and natural writing. Text responses and agent tool calling through Responses API. — from $1.2 per 1M input tokens - [Grok 4.5](https://api-stock.com/model/grok-4.5) (xAI, released 2026-07-08): xAI frontier model for coding, agentic tasks and knowledge work. 500K-token context, text and image input. — from $2.1 per 1M input tokens - [Grok 4.6](https://api-stock.com/model/grok-4.6) (xAI, released 2026-08-12): xAI upgrade over Grok 4.5, built for long-running multi-step agent tasks and interactive visual project creation. 500K-token context, text and image input. — from $2.1 per 1M input tokens - [Grok 4.7](https://api-stock.com/model/grok-4.7) (xAI, released 2026-09-21): xAI model for coding, knowledge work and multi-step tool workflows. Available through the OpenAI-compatible Chat Completions API. Input contexts above 200K tokens use a separate tariff. — from $0.23 per 1M input tokens - [Kimi K2.7 Code](https://api-stock.com/model/kimi-k2.7-code) (Moonshot, released 2026-06-12): Coding-specialised Kimi tier tuned for repository-scale edits and agentic software tasks. — from $1.11 per 1M input tokens - [Kimi K3](https://api-stock.com/model/kimi-k3) (Moonshot, released 2026-07-16): Moonshot's frontier model — long-context reasoning and agentic tool use. — from $3.15 per 1M input tokens - [MiniMax M3](https://api-stock.com/model/minimax-m3) (MiniMax, released 2026-06-01): Efficient general-purpose model with a very low token price; good default for chat and summarisation. — from $0.36 per 1M input tokens - [Qwen3.7 Plus](https://api-stock.com/model/qwen3.7-plus) (Qwen, released 2026-06-01): Alibaba's balanced Qwen tier for multilingual chat, reasoning and tool use. — from $0.343 per 1M input tokens