Every AI model API you want. Up to 90 % cheaper.

claude-opus-5-51M context

Claude Opus 5.5

$1.40 / $7.00 per 1M tokens

Claude Opus 5.5 is Anthropic's current Opus model, built for long-running agentic coding and knowledge work. The Zurelay Claude Opus 5.5 API serves it through an OpenAI-compatible or Anthropic-compatible endpoint at 65% below Anthropic's list price, for teams that want Opus-level results without Opus-level bills.

61%off

Claude Sonnet 5.5

$0.79 / $3.95 per 1M tokens

Claude Sonnet 5.5 is Anthropic's current Sonnet model, which Anthropic calls its best combination of speed and intelligence. The Zurelay Claude Sonnet 5.5 API serves it through an OpenAI-compatible or Anthropic-compatible endpoint at 61% below list price, for teams running coding, agent and document work at volume.

claude-sonnet-5-51M context

claude-haiku-5-51M context

Claude Haiku 5.5

$0.04 / $0.20 per 1M tokens

Claude Haiku 5.5 is Anthropic's current Haiku, which Anthropic calls the cheapest, fastest and most capable small model it has released. The Zurelay Claude Haiku 5.5 API serves it through OpenAI-compatible and Anthropic-compatible endpoints at 60% below Anthropic's list price, for classification, extraction, routing, sub-agents and other high-volume work.

claude-fable-5-21M context

Claude Fable 5.2

$3.20 / $16.00 per 1M tokens

Claude Fable 5.2 is Anthropic's newest Fable model, from the tier above Opus, built for demanding reasoning and long-horizon agentic work. The Zurelay Claude Fable 5.2 API serves it through OpenAI-compatible and Anthropic-compatible endpoints at 60% below Anthropic's list price, so your hardest coding, research and analysis jobs run for less.

claude-fable-5-11M context

Claude Fable 5.1

$3.50 / $17.50 per 1M tokens

Claude Fable 5.1 is a Fable model from Anthropic's tier above Opus, built for demanding reasoning and long-horizon agentic work. Claude Fable 5.2 has since succeeded it, and Fable 5.1 stays available. The Zurelay Claude Fable 5.1 API serves it through OpenAI-compatible and Anthropic-compatible endpoints at 65% below Anthropic's list price, for teams that tuned prompts and evals on it and want to keep them running for less.

Claude Fable 5

$3.50 / $17.50 per 1M tokens

Claude Fable 5 is Anthropic's first Fable model, part of the Mythos-class tier that Anthropic places above Opus in capability. The Zurelay Claude Fable 5 API serves it through OpenAI-compatible and Anthropic-compatible endpoints at 65% below Anthropic's list price. It suits teams that tuned prompts and evals on Fable 5 and want to keep them running for less.

claude-fable-51M context

Claude Opus 5

$1.75 / $8.75 per 1M tokens

Claude Opus 5 is Anthropic's July 2026 Opus model for complex agentic coding and enterprise work. The Zurelay Claude Opus 5 API serves the same model through OpenAI-compatible and Anthropic-compatible endpoints at 65% below Anthropic's list price. It suits teams that built prompts and agent harnesses on Opus 5 and want to keep that behavior.

claude-opus-51M context

claude-opus-4-81M context

Claude Opus 4.8

$2.40 / $12.00 per 1M tokens

Claude Opus 4.8 is the final Opus 4 model, released by Anthropic in May 2026 for agentic coding and knowledge work. The Zurelay Claude Opus 4.8 API serves the same model through OpenAI-compatible and Anthropic-compatible endpoints at 52% below Anthropic's list price. Teams keep it for its pinned behavior, its Opus 4.7 request shape and thinking that stays off until you ask for it.

64%off

Claude Opus 4.7

$1.78 / $8.93 per 1M tokens

Claude Opus 4.7 is the April 2026 Opus model that introduced xhigh effort, high-resolution vision and a new tokenizer. The Zurelay Claude Opus 4.7 API serves the same model through OpenAI-compatible and Anthropic-compatible endpoints, priced at 64% below Anthropic's list price. It suits teams whose prompts, evals or agents are tuned to Opus 4.7 and should not move yet.

claude-opus-4-71M context

claude-opus-4-61M context

Claude Opus 4.6

$2.40 / $12.00 per 1M tokens

Claude Opus 4.6 is the February 2026 Opus model that brought adaptive thinking and the max effort level to the Opus line. The Zurelay Claude Opus 4.6 API serves the same model through OpenAI-compatible and Anthropic-compatible endpoints at 52% below Anthropic's list price. It is the newest Opus that still accepts temperature and budget_tokens, and it uses the tokenizer from before Opus 4.7.

46%off

Claude Haiku 4.5

$0.54 / $2.70 per 1M tokens

Claude Haiku 4.5 is the Haiku Anthropic released in October 2025, which it described as its fastest model with near-frontier intelligence. The Zurelay Claude Haiku 4.5 API serves it through OpenAI-compatible and Anthropic-compatible endpoints at 46% below Anthropic's list price. It still fits pipelines built on it, especially ones that set temperature or a thinking budget; Claude Haiku 5.5 is the newer, lower-priced Haiku.

claude-haiku-4-5200K context

GPT, GPT Image and Text APIs (OpenAI)

GPT pricing

GPT-6 Astra

$2.50 / $12.50 per 1M tokens

GPT-6 Astra is the top model in OpenAI's GPT-6 family, built for complex reasoning, coding, research and document work. The GPT-6 Astra API on Zurelay runs the same model through one OpenAI-compatible endpoint, below OpenAI's list price. It is for teams whose hardest tasks justify the most capable model.

gpt-6-astra1.05M context

GPT-6.1 Sol

$0.50 / $2.50 per 1M tokens

GPT-6.1 Sol is OpenAI's newest Sol model, released on September 29, 2026. OpenAI says it nearly matches GPT-6 Astra on agentic coding, computer use and professional work at one-fifth of Astra's list price per token. The GPT-6.1 Sol API on Zurelay serves it through one OpenAI-compatible endpoint, below OpenAI's list price.

gpt-6.1-sol1.05M context

gpt-6.1-terra1.05M context

GPT-6.1 Terra

$0.25 / $1.25 per 1M tokens

GPT-6.1 Terra is OpenAI's mid-tier GPT-6.1 model, released on October 26, 2026, for computer use, visual reasoning, coding and everyday work. OpenAI says it performs on par with GPT-6 Astra at one-tenth of Astra's list price per token. The GPT-6.1 Terra API on Zurelay serves it through one OpenAI-compatible endpoint, below OpenAI's list price.

GPT-6 Sol

$0.50 / $2.50 per 1M tokens

GPT-6 Sol is the middle model in OpenAI's GPT-6 family, built for complex coding and agentic workflows. The GPT-6 Sol API on Zurelay runs the same model through one OpenAI-compatible endpoint, below OpenAI's list price. It suits teams that want Sol's full reasoning range, from none to max.

gpt-6-sol1.05M context

gpt-5.6-terra1.05M context

GPT-6 Luna

$0.025 / $0.125 per 1M tokens

GPT-6 Luna is the fastest and lowest-cost model in OpenAI's GPT-6 family, built for focused, high-volume tasks like summaries, extraction and quick answers. The GPT-6 Luna API on Zurelay runs the same model through one OpenAI-compatible endpoint, below OpenAI's list price.

gpt-6-luna1.05M context

72%off

GPT-5.6 Sol

$1.14 / $5.70 per 1M tokens

GPT-5.6 Sol is the flagship of OpenAI's GPT-5.6 family, built for frontier reasoning and long-horizon agentic work. The GPT-5.6 Sol API on Zurelay runs the same model through one OpenAI-compatible endpoint, below OpenAI's list price. You pay one flat rate per token, even on prompts over 272K tokens.

gpt-5.6-sol1.05M context

73%off

GPT-5.6 Terra

$0.54 / $3.26 per 1M tokens

GPT-5.6 Terra is the middle tier of OpenAI's GPT-5.6 family, built to balance intelligence and cost. The GPT-5.6 Terra API on Zurelay runs the same model through one OpenAI-compatible endpoint, below OpenAI's list price. It fits production traffic that needs solid reasoning without paying for Sol.

59%off

GPT-5.6 Luna

$0.08 / $0.49 per 1M tokens

GPT-5.6 Luna is the fastest and lowest-cost tier of OpenAI's GPT-5.6 family, built for cost-sensitive, high-volume workloads. The GPT-5.6 Luna API on Zurelay runs the same model through one OpenAI-compatible endpoint, below OpenAI's list price. It suits classification, routing, extraction and short summaries at scale.

gpt-5.6-luna1.05M context

GPT Image 2.6 Flare

from $0.008 per image

GPT Image 2.6 Flare is OpenAI's image model for fast iteration, released on November 4, 2026. The GPT Image 2.6 Flare API on Zurelay makes and edits images from a text prompt and up to 16 reference images, through OpenAI-compatible endpoints. Every image is made at high quality, from $0.008 at 1K to $0.035 at 4K.

gpt-image-2.6-flareImage

gpt-image-2.6-sunburstImage

GPT Image 2.6 Sunburst

from $0.008 per image

GPT Image 2.6 Sunburst is OpenAI's image model for detailed visual work, released on November 4, 2026. The GPT Image 2.6 Sunburst API on Zurelay makes and edits detailed images from a text prompt and up to 16 reference images, through OpenAI-compatible endpoints. Every image is made at high quality, from $0.008 at 1K to $0.035 at 4K.

GPT Image 2.5 Flare

from $0.008 per image

GPT Image 2.5 Flare is OpenAI's fastest model for high-quality, everyday image generation, released on September 8, 2026. The GPT Image 2.5 Flare API on Zurelay makes and edits images from a text prompt and up to 16 reference images, through OpenAI-compatible endpoints. Every image is made at high quality, from $0.008 at 1K to $0.035 at 4K.

gpt-image-2.5-flareImage

gpt-image-2.5-sunburstImage

GPT Image 2.5 Sunburst

from $0.008 per image

GPT Image 2.5 Sunburst is OpenAI's most capable image model, tuned for quality and precision and released on September 8, 2026. The GPT Image 2.5 Sunburst API on Zurelay makes and edits detailed images from a text prompt and up to 16 reference images, through OpenAI-compatible endpoints. Every image is made at high quality, from $0.008 at 1K to $0.035 at 4K.

62%off

GPT Image 2

$0.02 per image

GPT Image 2 is OpenAI's image generation and editing model for production visuals such as infographics, posters and text-heavy layouts, released on April 21, 2026. The GPT Image 2 API on Zurelay makes and edits images from a text prompt and up to 16 reference images, through OpenAI-compatible endpoints. Every image is made at high quality, at one flat price for any size up to 3840 pixels.

gpt-image-2Image

25%off

GPT-6 Luna Decisions

$0.075 per 1M input tokens

GPT-6 Luna Decisions is the model behind OpenAI's Decisions API: it answers classification or scoring questions about some input, many questions in one request, and returns a typed answer with probabilities for each one instead of writing text. The Zurelay API serves it on OpenAI's own endpoint and request shape, so OpenAI's SDKs work with Zurelay's base URL, at 25% below OpenAI's list price.

gpt-6-luna-decisions1.05M context

50%off

Text Embedding 3 Small

$0.01 per 1M input tokens

Text Embedding 3 Small (text-embedding-3-small) is OpenAI's small, low-cost embedding model. It turns text into a vector of 1,536 numbers, placed so that texts with similar meanings sit close together, for semantic search, retrieval (RAG), clustering and recommendations. Zurelay serves it on OpenAI's embeddings endpoint with the same model ID, request and response, at 50% below OpenAI's list price, and the vectors match OpenAI's own.

text-embedding-3-small1,536 dimensions

50%off

Text Embedding 3 Large

$0.065 per 1M input tokens

Text Embedding 3 Large (text-embedding-3-large) is OpenAI's larger embedding model, for when retrieval quality matters most. It turns text into a vector of 3,072 numbers, placed so that texts with similar meanings sit close together, for semantic search, retrieval (RAG), clustering and recommendations. Zurelay serves it on OpenAI's embeddings endpoint with the same model ID, request and response, at 50% below OpenAI's list price, and the vectors match OpenAI's own.

text-embedding-3-large3,072 dimensions

Gemini, Nano Banana, Veo and Gemma APIs (Google)

Gemini pricing

11%off

Nano Banana 2.1

from $0.03 per image

Nano Banana 2.1 is Google's update to Nano Banana 2, released on October 6, 2026, with better visual quality, prompt adherence, text in images and character consistency across edits. The Zurelay Nano Banana 2.1 API turns a text prompt and up to 14 reference images into 1K, 2K or 4K images through an OpenAI-style images endpoint, below Google's price at every resolution, and checks every image against Google's official size.

nano-banana-2.1Image

74%off

Nano Banana Pro

from $0.035 per image

Nano Banana Pro is Google DeepMind's image generation model, built on Gemini 3 Pro and served in the Gemini API as Gemini 3 Pro Image. The Zurelay Nano Banana Pro API turns a text prompt and up to 14 reference images into 1K, 2K or 4K images through an OpenAI-style images endpoint, for developers who need legible text, diagrams and production assets at a lower price per image.

nano-banana-proImage

63%off

Nano Banana 2

from $0.025 per image

Nano Banana 2 is Google's fast, general-purpose image model, served in the Gemini API as Gemini 3.1 Flash Image. The Zurelay Nano Banana 2 API turns a text prompt and up to 14 reference images into 1K, 2K or 4K images through an OpenAI-style images endpoint, at 63% below Google's price per image, and checks every image against Google's official size.

nano-banana-2Image

Nano Banana 2 Lite

$0.016 per image

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's efficiency model in the Nano Banana family, built for low latency and low cost at 1K. The Zurelay Nano Banana 2 Lite API makes and edits 1K images from a prompt and up to 14 reference images for $0.016 an image, 52% below Google's $0.0336, and checks every image against Google's official size.

nano-banana-2-liteImage

gemini-4-hydrogen1M context

Gemini 4 Hydrogen

$0.60 / $3.00 per 1M tokens

Gemini 4 Hydrogen is Google's fast, efficient Gemini 4 model for everyday coding and agentic workflows, released on November 12, 2026. The Zurelay Gemini 4 Hydrogen API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 60% below Google's list price.

gemini-3.8-flash1M context

Gemini 4 Argon

$0.80 / $4.00 per 1M tokens

Gemini 4 Argon is Google's frontier model for software engineering, professional knowledge work and defensive cybersecurity, announced on September 30, 2026 and opened to developers on October 13, 2026. The Zurelay Gemini 4 Argon API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 60% below Google's list price.

gemini-4-argon1M context

71%off

Gemini 3.1 Pro

$0.50 / $3.45 per 1M tokens

Gemini 3.1 Pro is Google's Pro model for complex problem-solving and agentic coding, released as a preview on February 19, 2026 and still in preview at Google. The Zurelay Gemini 3.1 Pro API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 71% below Google's list price and one rate at every prompt length.

gemini-3.1-pro1M context

71%off

Gemini 3.8 Flash

$0.22 / $1.10 per 1M tokens

Gemini 3.8 Flash is Google's most intelligent Flash model, built for long-horizon software engineering, autonomous agents and complex enterprise workflows, and released on September 2, 2026. The Zurelay Gemini 3.8 Flash API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 71% below Google's list price.

58%off

Gemini 3.7 Flash

$0.32 / $1.59 per 1M tokens

Gemini 3.7 Flash is Google's Flash model for coding, agentic tool use and multi-step work, released on August 13, 2026. The Zurelay Gemini 3.7 Flash API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 58% below Google's list price.

gemini-3.7-flash1M context

58%off

Gemini 3.5 Flash-Lite

$0.12 / $1.04 per 1M tokens

Gemini 3.5 Flash-Lite is the fastest and most cost-effective model in Google's Gemini 3.5 series, released on July 21, 2026. The Zurelay Gemini 3.5 Flash-Lite API serves it through one OpenAI-compatible endpoint for high-volume agent steps, search and document processing, at 58% below Google's list price.

gemini-3.5-flash-lite1M context

61%off

Gemini 3.1 Flash-Lite

$0.10 / $0.59 per 1M tokens

Gemini 3.1 Flash-Lite is Google's low-latency, low-cost Gemini 3 model for high-volume work such as translation, moderation, extraction and model routing. The Zurelay Gemini 3.1 Flash-Lite API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 61% below Google's list price.

gemini-3.1-flash-lite1M context

gemini-omni-1.2-flash4K video

Gemini Omni 1.2 Flash

from $0.042 per second

Gemini Omni 1.2 Flash is Google's newest video generation and editing model, generally available since November 5, 2026. On Zurelay it makes 720p, 1080p and 4K clips of 4 to 15 seconds with sound, from a prompt, a start frame, a start and end frame, up to 6 reference images, or up to 3 reference videos to edit or borrow from. The Zurelay Gemini Omni 1.2 Flash API costs from $0.042 per second of video, and a video is charged only once it's delivered.

gemini-omni-flash4K video

Gemini Omni Flash

from $0.042 per second

Gemini Omni Flash is Google's video generation model, built to understand text, images, audio and video together and to make video with its sound in one pass. On Zurelay it makes 360p, 720p, 1080p and 4K clips of 4 to 10 seconds from a prompt, a start frame, a start and end frame, up to 10 reference images, or up to 3 reference videos to edit or borrow from. The Zurelay Gemini Omni Flash API costs from $0.042 per second of video, and a video is charged only once it's delivered.

gemini-3.8-flash-ttsText to speech

Veo 3.1 Fast

from $0.025 per second

Veo 3.1 Fast is the lower-cost version of Google's Veo 3.1 video model, released on October 15, 2025. It turns a text prompt or a first frame into an 8 second 720p video with sound. The Zurelay Veo 3.1 Fast API charges one flat price per clip, only once the video is delivered.

veo-3.1-fast720p video

40%off

Gemini 3.8 Flash TTS

$0.30 / $5.40 per 1M tokens

Gemini 3.8 Flash TTS is Google's flagship text-to-speech model, released in preview in September 2026 and built for creative direction and character voices. It reads text aloud in 30 voices and more than 130 languages, with vocal tags such as <laugh> or <short pause> written into the text. The Zurelay Gemini 3.8 Flash TTS API serves it through an OpenAI-compatible speech endpoint at 40% below Google's list price, about $0.008 a minute of speech.

40%off

Gemini 3.1 Flash TTS

$0.60 / $12.00 per 1M tokens

Gemini 3.1 Flash TTS is Google's expressive, steerable text-to-speech model, released in preview on April 15, 2026. It reads text aloud in 30 voices and more than 70 languages, and audio tags written into the text change the delivery mid-sentence. The Zurelay Gemini 3.1 Flash TTS API serves it through an OpenAI-compatible speech endpoint at 40% below Google's list price, about $0.023 a minute of speech.

gemini-3.1-flash-ttsText to speech

4%off

Gemma 4 Uncensored

$0.155 / $0.48 per 1M tokens

Gemma 4 Uncensored is a community uncensored fine-tune of Google's Gemma 4 26B, a mixture-of-experts model with about 4B parameters active per token, tuned for chat without content filtering. It isn't made or endorsed by Google. The Zurelay Gemma 4 Uncensored API serves it through one OpenAI-compatible endpoint with a 256K-token context window, image input and tool calling, at 4% below list price. Zurelay's Terms of Service still apply to everything you send it.

gemma-4-uncensored256K context

Grok Imagine and Grok APIs (xAI)

Grok pricing

grok-imagine-image-2.0Image

Grok 4.7

$0.70 / $2.10 per 1M tokens

Grok 4.7 is xAI's newest model for coding, agentic tasks and knowledge work, with a 500K-token context window and image input. The Zurelay Grok 4.7 API gives you the same model through one OpenAI-compatible endpoint, billed per token at 65% below xAI's list price.

grok-4.7500K context

25%off

Grok Imagine Image 2.0

from $0.045 per image

Grok Imagine Image 2.0 is xAI's general image model for text-to-image and image editing, up to 2K. The Zurelay Grok Imagine Image 2.0 API makes images at xAI's medium quality for $0.045 at 1K and $0.06 at 2K, 25% below xAI's own price, and edits or combines up to 3 images at the same price.

grok-imagine-video-1.5720p video

Grok Imagine Video 1.5

from $0.071 per second

Grok Imagine Video 1.5 is the video model xAI calls its best yet, with sound effects, ambience and dialogue generated in the same pass as the picture. On Zurelay it makes 480p and 720p clips from 1 to 15 seconds long, from text, a first frame or up to 3 reference images. The Zurelay Grok Imagine Video 1.5 API starts at $0.071 per second of video, and a video is charged only once it's delivered.

MiMo API (Xiaomi)

MiMo pricing

26%off

MiMo V2.6 Pro

$0.32 / $0.64 per 1M tokens

MiMo V2.6 Pro is Xiaomi's open-weight flagship, a 1.02-trillion-parameter model that reads text, images, audio and video and holds 1M tokens of context. The MiMo V2.6 Pro API on Zurelay takes text and images, and suits teams building agents, coding tools and multimodal apps who want Xiaomi's strongest model at 26% below its list price.

mimo-v2.6-pro1M context

46%off

MiMo V2.6 Flash

$0.075 / $0.15 per 1M tokens

MiMo V2.6 Flash is the efficient model in Xiaomi's MiMo-V2.6 series: 15B active parameters and 1M tokens of context. The MiMo V2.6 Flash API on Zurelay takes text and images and is for teams running high-volume or latency-sensitive workloads who want near-Pro agent results at 46% below Xiaomi's list price.

mimo-v2.6-flash1M context

DeepSeek API

DeepSeek pricing

90%off

DeepSeek V4.1 Flash 1017

$0.03 / $0.12 per 1M tokens

DeepSeek V4.1 Flash 1017 is the October 17, 2026 update to DeepSeek V4.1 Flash, and the model DeepSeek's own API now serves for Flash requests. DeepSeek reports higher scores on every test it published, faster task completion and shorter outputs, at an unchanged price. The Zurelay DeepSeek V4.1 Flash 1017 API serves it through one OpenAI-compatible endpoint at 90% below DeepSeek's peak list price.

deepseek-v4.1-flash-10171M context

90%off

DeepSeek V4.1 Flash

$0.03 / $0.12 per 1M tokens

DeepSeek V4.1 Flash is the Flash model DeepSeek released on September 10, 2026, the first in its new architecture family. It reads text and images, holds 1M tokens of context and runs in thinking or non-thinking mode. The Zurelay DeepSeek V4.1 Flash API serves it through one OpenAI-compatible endpoint at 90% below DeepSeek's peak list price.

deepseek-v4.1-flash1M context

90%off

DeepSeek V4 Flash

$0.03 / $0.12 per 1M tokens

DeepSeek V4 Flash was the fast, low-cost half of DeepSeek's V4 launch in April 2026. DeepSeek has since retired it on its own API and answers the deepseek-v4-flash name with the newer V4.1 Flash. The Zurelay DeepSeek V4 Flash API does the same, so existing code keeps working at 90% below list price.

deepseek-v4-flash1M context

69%off

DeepSeek V4 Flash 0731

$0.029 / $0.087 per 1M tokens

DeepSeek V4 Flash 0731 is the official July 31, 2026 release of DeepSeek V4 Flash, a 284B-parameter open-weight model tuned for agents and coding. DeepSeek's own API has moved on to V4.1 Flash, so the DeepSeek V4 Flash 0731 API on Zurelay is how you keep this exact checkpoint in production.

deepseek-v4-flash-07311M context

84%off

DeepSeek V4 Pro 0813

$0.23 / $0.62 per 1M tokens

DeepSeek V4 Pro 0813 is the official August 13, 2026 release of DeepSeek V4 Pro, a 1.6-trillion-parameter open-weight model built for coding and agents. It is the model DeepSeek's own API serves as deepseek-v4-pro. The Zurelay DeepSeek V4 Pro API runs it through one OpenAI-compatible endpoint at 84% below DeepSeek's peak list price.

deepseek-v4-pro-08131M context

GLM API (Z.ai)

GLM pricing

73%off

GLM-5.3

$0.38 / $1.21 per 1M tokens

GLM-5.3 is Z.ai's flagship model for complex software engineering and long-running agents, with a 1M-token context window and up to 128K output tokens. The Zurelay GLM-5.3 API serves the same model through one OpenAI-compatible endpoint, billed per token at 73% below Z.ai's list price.

glm-5.31M context

73%off

GLM-5.2

$0.38 / $1.21 per 1M tokens

GLM-5.2 is Z.ai's open-weight model for long-horizon coding and the first GLM with a 1M-token context window. The Zurelay GLM-5.2 API serves the same model through one OpenAI-compatible endpoint at 73% below Z.ai's list price.

glm-5.21M context

62%off

GLM-5.3 Flash

$0.058 / $0.19 per 1M tokens

GLM-5.3 Flash is Z.ai's low-cost GLM, with 18B of its 320B parameters active per token. Z.ai says it outperforms GLM-5.2 and approaches Claude Opus 4.8 on coding and agent benchmarks. The Zurelay GLM-5.3 Flash API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 62% below Z.ai's list price.

glm-5.3-flash1M context

13%off

GLM-4.7 Flash Heretic

$0.061 / $0.35 per 1M tokens

GLM-4.7 Flash Heretic is a community uncensored version of Z.ai's GLM-4.7 Flash, made with Heretic, an open-source tool that removes a model's refusals automatically. It isn't made or endorsed by Z.ai. The Zurelay GLM-4.7 Flash Heretic API serves it through one OpenAI-compatible endpoint with a 200K-token context window, reasoning you can switch off and tool calling, at 13% below list price. Zurelay's Terms of Service still apply to everything you send it.

glm-4.7-flash-heretic200K context

Kimi API (Moonshot AI)

Kimi pricing

kimi-k3.1-pro-highspeed1M context

Kimi K3.1 Pro

$0.80 / $4.00 per 1M tokens

Kimi K3.1 Pro is Moonshot AI's newest flagship and the first model of its K3.1 series: Kimi K3 trained much further with reinforcement learning, with native vision and a 1M-token context window. The Zurelay Kimi K3.1 Pro API serves the same model through one OpenAI-compatible endpoint at 60% below Moonshot's list price.

kimi-k3.1-pro1M context

18%off

Kimi K3.1 Pro Highspeed

$3.30 / $16.50 per 1M tokens

Kimi K3.1 Pro Highspeed is the fast version of Moonshot AI's newest flagship: the same K3.1 Pro model, with the same 1M-token context and vision, served at two to three times the speed. The Zurelay API serves it through one OpenAI-compatible endpoint at 18% below Moonshot's list price.

58%off

Kimi K3

$1.27 / $6.37 per 1M tokens

Kimi K3 is Moonshot AI's flagship model: 2.8 trillion parameters, native vision and a 1M-token context window, built for long-horizon coding and knowledge work. The Zurelay Kimi K3 API serves the same model through one OpenAI-compatible endpoint at 58% below Moonshot's list price.

kimi-k31M context

68%off

Kimi K2.6

$0.30 / $1.30 per 1M tokens

Kimi K2.6 is Moonshot AI's open-weight K2 model for long-horizon coding, front-end design and agents, released in April 2026, with a 262K-token context window and image and video input. The Zurelay Kimi K2.6 API serves it through one OpenAI-compatible endpoint at 68% below Moonshot's list price.

kimi-k2.6256K context

68%off

Kimi K2.5

$0.20 / $0.95 per 1M tokens

Kimi K2.5 is Moonshot AI's open-weight, natively multimodal K2 model for coding, vision and agent work, released in January 2026, with a 262K-token context window and image and video input. The Zurelay Kimi K2.5 API serves it through one OpenAI-compatible endpoint at 68% below Moonshot's list price.

kimi-k2.5256K context

Qwen and Wan APIs (Alibaba)

Qwen pricing

40%off

Qwen 3.8 Max

$1.20 / $3.60 per 1M tokens

Qwen 3.8 Max is Alibaba's flagship Qwen 3.8 model, a 2.4-trillion-parameter mixture-of-experts with a 1M-token context window and native vision. The Zurelay Qwen 3.8 Max API serves it through one OpenAI-compatible endpoint at 40% below Alibaba's international list price, for coding, agent and long-document work.

qwen3.8-max1M context

53%off

Qwen 3.8 Flash

$0.07 / $0.22 per 1M tokens

Qwen 3.8 Flash is Alibaba's fast, low-cost Qwen 3.8 model, a 125B-parameter mixture-of-experts with only 6B active per token and a 1M-token context window. The Zurelay Qwen 3.8 Flash API serves it through one OpenAI-compatible endpoint at 53% below Alibaba's international list price, for coding helpers, agents and high-volume pipelines.

qwen3.8-flash1M context

50%off

Qwen 3.8 Omni Flash

$0.075 / $0.235 per 1M tokens

Qwen 3.8 Omni Flash is Alibaba's multimodal Qwen 3.8 model for audio and video understanding: it takes text, images, audio and video in one request and answers in text. The Zurelay Qwen 3.8 Omni Flash API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 50% below Alibaba's international list price.

qwen3.8-omni-flash1M context

Wan 3.0 Prime

from $0.06 per second

Wan 3.0 Prime is the high-speed version of Alibaba's Wan 3.0 video model, with the same inputs and options. On Zurelay it makes 480p to 1080p clips from 2 to 30 seconds long, with generated sound, from text, a first and last frame, or up to 10 reference images. The Zurelay Wan 3.0 Prime API starts at $0.06 per second, under Alibaba's own price, and a video is charged only once it's delivered.

wan-3.0-prime1080p video

Wan 3.0

from $0.039 per second

Wan 3.0 is Alibaba's newest video generation model, built as one model for reference, editing, replication and driving. On Zurelay it makes 480p to 1080p clips from 2 to 30 seconds long, with generated sound, from text, a first and last frame, or up to 10 reference images. The Zurelay Wan 3.0 API starts at $0.039 per second of video, and a video is charged only once it's delivered.

wan-3.01080p video

MiniMax API

MiniMax pricing

minimax-m3.1-flash1M context

MiniMax M3.1 Flash

$0.06 / $0.24 per 1M tokens

MiniMax M3.1 Flash is MiniMax's fast, low-cost reasoning model for agents, coding, computer use and security work, released on October 19, 2026. The Zurelay MiniMax M3.1 Flash API serves it through one OpenAI-compatible endpoint with a 1M-token context window and image and video input, at 60% below MiniMax's list price.

57%off

MiniMax M3

$0.13 / $0.51 per 1M tokens

MiniMax M3 is MiniMax's natively multimodal model for agentic coding, tool use and long context, released on June 1, 2026, with about 428B total and 23B active parameters. The Zurelay MiniMax M3 API serves it through one OpenAI-compatible endpoint with a 1M-token context window and image input, at 57% below MiniMax's list price.

minimax-m31M context

MiniMax H3

from $0.039 per second

MiniMax H3 (Hailuo 03) is MiniMax's general video model, built to read text, images, video and audio together and follow detailed instructions about all of them. On Zurelay it makes 768p and 2K clips from 4 to 15 seconds long with native sound, from a prompt and up to 9 reference images, 3 reference videos and 3 reference audio clips in any mix. The Zurelay MiniMax H3 API starts at $0.039 per second, below MiniMax's own price, with the references included.

minimax-h32K video

68%off

MiniMax M2.5

$0.10 / $0.39 per 1M tokens

MiniMax M2.5 is MiniMax's open-weight model for coding, agentic tool use and search, and office work, released on February 12, 2026. The Zurelay MiniMax M2.5 API serves it through one OpenAI-compatible endpoint with a 204,800-token context window and up to 131,072 output tokens per answer, at 68% below MiniMax's list price.

minimax-m2.5205K context

HY4 API (Tencent)

HY4 Preview

$0.40 / $1.20 per 1M tokens

HY4 Preview is Tencent's new HY model (formerly Hunyuan), with 770B total parameters and 49B active, built for agents, coding and productivity work. The Zurelay HY4 Preview API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 52% below Tencent's official price.

hy4-preview1M context

Step API (StepFun)

Step 5 Preview

$0.25 / $0.68 per 1M tokens

Step 5 Preview is StepFun's flagship model for agentic work: software engineering, long tool-calling tasks and professional knowledge work, with particular strength in finance. The Zurelay Step 5 Preview API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 75% below StepFun's list price.

step-5-preview1M context

FLUX API (Black Forest Labs)

17%off

FLUX 3 Image

from $0.04 per image

FLUX 3 Image is Black Forest Labs' image model, up to 4K. The Zurelay FLUX 3 Image API makes images from a prompt for $0.04 at 1K, $0.05 at 2K and $0.09 at 4K, against BFL's $0.048, $0.10 and $0.607. Requests with reference images are made by Nano Banana Pro, at its price.

flux-3-imageImage

Seedance API (ByteDance)

Seedance pricing

Seedance 2.5

from $0.135 per second

Seedance 2.5 is the newest model in ByteDance's Seedance video family. It turns a text prompt, or a prompt with images, into a video with generated sound, at up to 1080p and up to 30 seconds long. The Zurelay Seedance 2.5 API starts at $0.135 per second of video, and a video is charged only once it's delivered.

seedance-2.51080p video

Seedance 2.0

from $0.097 per second

Seedance 2.0 is ByteDance's video generation model for text-to-video and image-to-video, with generated sound. It makes clips from 480p up to 4K, 4 to 15 seconds long. The Zurelay Seedance 2.0 API starts at $0.097 per second of video, and a video is charged only once it's delivered.

seedance-2.04K video

seedance-2.0-fast720p video

Seedance 2.0 Fast

from $0.074 per second

Seedance 2.0 Fast is a quicker, lower-cost version of ByteDance's Seedance 2.0 video model, trading some quality for speed and price. It makes 480p and 720p clips from 4 to 15 seconds long, with generated sound, from text or images. On Zurelay it starts at $0.074 per second of video, charged only once a video is delivered.

seedance-2.0-mini720p video

Seedance 2.0 Mini

from $0.047 per second

Seedance 2.0 Mini is the lowest-cost model in ByteDance's Seedance 2.0 family, trading some quality for speed and price. It makes 480p and 720p clips from 4 to 15 seconds long, with generated sound, from text or images. On Zurelay it costs from $0.047 per second of video, charged only once a video is delivered.

Kling API (Kuaishou)

Kling 4.0

from $0.15 per second

Kling 4.0 is Kuaishou's newest video generation model. It makes 720p and 1080p clips from 3 to 30 seconds long in a single take, always with generated sound, from a text prompt, a first and last frame, or up to 10 reference images. The Zurelay Kling 4.0 API costs $0.15 per second of 720p video, and a video is charged only once it's delivered.

kling-4.01080p video

Kling 3.0

from $0.125 per second

Kling 3.0 is Kuaishou's video generation model for text-to-video and image-to-video, with optional generated sound that includes speech in five languages. It makes 720p and 1080p clips from 3 to 15 seconds long. The Zurelay Kling 3.0 API starts at $0.125 per second of video, and a video is charged only once it's delivered.

kling-3.01080p video

Muse API (Meta)

Muse Video

from $0.02 per second

Muse Video is Meta Superintelligence Labs' video generation model, which makes video and its sound together from a text prompt. On Zurelay it makes 720p clips of 5 to 10 seconds in 16:9 or 9:16, with the ambience, effects, music or dialogue your prompt describes. The Zurelay Muse Video API costs $0.02 per second, and a video is charged only once it's delivered.

muse-video720p video

Vidu API (ShengShu)

Vidu Q3 Turbo

from $0.03 per second

Vidu Q3 Turbo is the fast model in ShengShu's Vidu Q3 series, and it generates sound with the picture. On Zurelay it makes 540p, 720p and 1080p clips from 1 to 16 seconds long, from text, a first frame, or a first and a last frame. The Zurelay Vidu Q3 Turbo API starts at $0.03 per second of video, and a video is charged only once it's delivered.

vidu-q3-turbo1080p video

PixVerse API