llama-3.2-1b-instruct

llama-3.2-1b-instruct is provide by Meta.

wan3.0-video

Wan 3.0 is a video generation model from Alibaba for text-to-video, image-to-video, and reference-guided video generation. It produces 480p, 720p, or 1080p video with durations from 2 to 30 seconds.

claude-sonnet-4-5-20250929

claude-sonnet-4-5-20250929 is provide by Anthropic.

claude-sonnet-5

Claude Sonnet 5 is Anthropic’s most agentic Sonnet model, released June 30, 2026. It nears Opus 4.8 performance at a lower price. On APISpace, Sonnet 5 API costs $1.6/$8 per million tokens—~20% below Anthropic’s rates—billed from a single shared balance across all models.

qwen3.7-max

qwen3.7-max is provide by Qwen.

gemini-2.5-flash-lite

gemini-2.5-flash-lite is provide by Google.

gemini-3.8-flash

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

qwen3.5-35b-a3b

qwen3.5-35b-a3b is provide by Qwen.

wen-max-2025-01-25

wen-max-2025-01-25 is provide by .

claude-sonnet-5-5

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor.

deepseek-v4-pro-0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

grok-1.5-video

Grok Imagine Video 1.5 is a video generation model from SpaceXAI. It creates videos from text prompts, with an optional starting image to guide the scene. It can direct subject and camera motion, pacing, atmosphere, and physical behavior while maintaining visual continuity, and can generate synchronized sound effects, ambience, and dialogue.

claude-opus-4-6

Claude-opus-4-6 marks the peak of Anthropic’s reasoning power, now available on the high-performance APISpace platform. Built for extreme precision, deep context understanding, and advanced creative writing, it excels where other models fall short. From complex legal documents and large-scale software design to refined brand narratives, it delivers professional-grade reliability and intelligence. APISpace integration offers unified billing and a stable environment for intensive AI workflows.

tts-1-hd-1106

tts-1-hd-1106 is provide by .

viduq3-turbo

Vidu Q3 marks a major leap in temporal consistency and cinematic rendering. It generates high-fidelity video sequences with subjects that stay consistent across frames. Integrated via GPTProto API on APISpace, it enables rapid prototyping of visual effects and marketing content. From complex narratives to short social clips, it delivers professional stability and detail—with no credit limits, making it highly scalable for modern AI video workflows.

wan2.5-i2v-preview

wan2.5-i2v-preview is provide by .

gpt-5.6-sol

gpt-5.6-sol is OpenAI’s flagship multi-step logic and autonomous agent reasoning model, released July 2026.

llama-2-7b

llama-2-7b is provide by Meta.

whisper-1

whisper-1 is provide by OpenAI.

z-image-turbo

z-image-turbo is provide by .

deepseek/deepseek-v4-flash-vision-exp

deepseek/deepseek-v4-flash-vision-exp is provide by DeepSeek.

gpt-6-astra

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.

kimi-k2.7-code

kimi-k2.7-code is provide by Moonshot.

qvq-max

qvq-max is provide by .

qwen3.7-plus

qwen3.7-plus is provide by Qwen.

glm-5

glm-5 is provide by Zhipu.

grok-4.7

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and managing long context, and it improves on its predecessor at professional knowledge work such as drafting documents and presentations. The model was trained with a longer reinforcement learning run weighted toward problems that take many hours to complete, and natively understands the Grok Bot harness for conversational tasks. It ships with a new safeguard stack that pairs strong jailbreak resistance with low refusal rates for legitimate cybersecurity and biology work. SpaceXAI's reported benchmark results use the xhigh reasoning effort.

grok-imagine-video-1.5-preview

grok-imagine-video-1.5-preview is provide by xAI.

MiniMax-M3

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.

wan3.0-video-prime

Wan 3.0 Prime is a fast-mode variant of Wan 3.0 from Alibaba. It supports text-to-video and first-frame image-to-video generation.

claude-opus-5

Access Anthropic’s Opus-class model at $4/M input tokens and $20/M output tokens. Claude Opus 5 is built for repo-scale coding, long-running agents, and document-heavy enterprise work—with 1M context, up to 128K output, vision, and adaptive thinking.

glm-4.5-air

glm-4.5-air is provide by Zhipu.

gemini-4-argon

gemini-4-argon is provide by Google.

gemini-nano-banana-2.1

gemini-nano-banana-2.1 is provide by Google.

glm-4-long

glm-4-long is provide by Zhipu.

glm-4.6

glm-4.6 is provide by Zhipu.

grok-4.5

The Grok 4.5 API gives developers access to xAI’s frontier reasoning model, built for agentic software engineering, multi-step tool calling, and long-context coding.

veo_3_1-components

veo_3_1-components is provide by .

qwen3.5-plus-2026-02-15

qwen3.5-plus-2026-02-15 is provide by Qwen.

qwen3.5-27b

qwen3.5-27b is provide by Qwen.

qwen3.6-27b

qwen3.6-27b is provide by Qwen.

gemini-3.1-flash-image

Nano Banana API delivers sub-second visual reasoning and a 1M-token context window. Optimized for high-throughput OCR, native video analysis, and spatial detection, it provides pro-grade vision at far lower cost than peers.

llama-3.1-70b

llama-3.1-70b is provide by Meta.

llama-3.3-70b-instruct

llama-3.3-70b-instruct is provide by Meta.

qwen3.8-flash

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

text-embedding-3-large

text-embedding-3-large is provide by .

gemini-3.5-flash

gemini-3.5-flash is provide by Google.

grok-imagine-image-quality

Grok Imagine Image Quality is SpaceXAI's fast, high-fidelity image generation and editing model. It accepts text prompts and optional reference images, producing photorealistic outputs at 1K or 2K across a range of aspect ratios, including flexible adjustment of reference images.

kimi-k2-0711-preview

kimi-k2-0711-preview is provide by Moonshot.

llama-2-70b

llama-2-70b is provide by Meta.

llama-3.1-8b

llama-3.1-8b is provide by Meta.

glm-5.2

GLM-5.2 is Z.ai’s (formerly Zhipu AI) open-weight model with 753B parameters and a lossless 1M-token context window, trained for long-horizon agentic coding and full-repo refactoring.

qwen3-8b

qwen3-8b is provide by Qwen.

qwen3.6-plus-2026-04-02

qwen3.6-plus-2026-04-02 is provide by Qwen.

qwq-32b

qwq-32b is provide by .

qwq-72b-preview

qwq-72b-preview is provide by .

tts-1

tts-1 is provide by .

veo_3_1-fast

veo_3_1-fast is provide by .

grok-4.3

grok-4.3 is provide by xAI.

llama-3.2-11b-vision-instruct

llama-3.2-11b-vision-instruct is provide by Meta.

llama-3.2-90b-vision-instruct

llama-3.2-90b-vision-instruct is provide by Meta.

claude-opus-4-7

Claude Opus 4.7 marks a major leap in autonomous AI, built for longer, more complex tasks with minimal human oversight. It introduces revolutionary xhigh thinking levels and Ultra Review commands for Claude Code developers. Enhanced vision (up to 2,576-pixel images) plus new self-verification logic delivers higher accuracy in technical reports and code. Integrate this powerful API on APISpace with flexible billing—same competitive pricing as prior versions, superior reasoning.

kimi-k2.6

kimi-k2.6 is provide by Moonshot.

llama-3-70b

llama-3-70b is provide by Meta.

qwen3.8-27b

qwen3.8-27b is provide by Qwen.

qwen3.8-max-0902

qwen3.8-max-0902 is provide by Qwen.

claude-fable-5-1

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.

gemini-2.5-flash

gemini-2.5-flash is provide by Google.

glm-4-flash

glm-4-flash is provide by Zhipu.

veo_3_1

Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio — including dialogue, ambient effects, and background sound. Supports scene extension (up to 20 chained clips for 140+ second narratives), frames-to-video transitions between two images, vertical video for Shorts, and 4K upscaling.

deepseek-v4-pro-ga-260813

deepseek-v4-pro-ga-260813 is provide by DeepSeek.

llama-3.2-3b-instruct

llama-3.2-3b-instruct is provide by Meta.

qwen3.6-35b-a3b

qwen3.6-35b-a3b is provide by Qwen.

claude-haiku-4-5-20251001

claude-haiku-4-5-20251001 is provide by Anthropic.

deepseek-v4-pro

DeepSeek 4 Pro API delivers flagship reasoning with a 1M context window. Optimized for agentic coding and STEM logic, it achieves top performance at 1/8th the cost of competitors. Access it now on APISpace.

gemini-3.7-flash

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.

grok-imagine-image-2.0

Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and medium quality modes.

qwen3.5-397b-a17b

qwen3.5-397b-a17b is provide by Qwen.

qwen3.8-max

2.4T-parameter MoE flagship with fully upgraded coding and office capabilities. Autonomously codes for 10+ days to deliver complete projects. Handles hundreds of professional tasks in law, finance, design, and more—delivering production-ready results end-to-end in one conversation. Native vision understanding spans planning, execution, and verification, enabling deep semantic analysis of ultra-long documents and long videos. For long-horizon tasks, it autonomously plans, closes the loop through iteration, and continuously evolves.

claude-opus-4-5-20251101

claude-opus-4-5-20251101 is provide by Anthropic.

glm-4-airx

glm-4-airx is provide by Zhipu.

kimi-k2.5

kimi-k2.5 is provide by Moonshot.

qwq-plus

qwq-plus is provide by .

glm-5.3-flash

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.

gpt-5.5

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.

o4-mini

o4-mini is provide by OpenAI.

claude-haiku-5-5

claude-haiku-5-5 is provide by Anthropic.

DeepSeek-V4.1-Flash

DeepSeek-V4.1-Flash is provide by DeepSeek.

gemini-3.6-flash

Access Google Gemini 3.6 Flash API via APISpace. It supports text, images, video, audio, and PDF—with 1,048,576 input tokens, 65,536 output tokens, plus configurable thinking and agent tools.

gpt-5.6-luna

gpt-5.6-luna is the fastest and cheapest version in OpenAI’s GPT-5.6 series, built for cost-sensitive high-volume workloads: classification, extraction, summarization, and user-facing chat.

text-embedding-3-small

text-embedding-3-small is provide by .

text-embedding-ada-002

text-embedding-ada-002 is provide by .

claude-opus-5-5

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up. The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.

deepseek-v4-flash

DeepSeek 4 Flash API delivers sub-second responses and 128k context. This MoE model excels at coding and high-throughput tasks at a fraction of the cost of rivals like GPT-4o-mini.

deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.

qwen3.5-plus

qwen3.5-plus is provide by Qwen.

grok-imagine-video

grok-imagine-video is provide by xAI.

tts-1-1106

tts-1-1106 is provide by .

gemini-3.1-flash-lite-image

Nano Banana Lite API powers Gemini 3.1 Flash-Lite for image generation under 5 seconds. Optimized for high-speed workflows, this lightweight vision tool delivers 1K resolution and native image-to-image editing at scale.

glm-5.3

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.

gpt-5.6-terra

gpt-5.6-terra is the balanced tier in OpenAI’s GPT-5.6 series, built for everyday production traffic: coding, RAG, document analysis, and structured output.

llama-3.1-405b

llama-3.1-405b is provide by Meta.

qwen-image-3.0-pro

qwen-image-3.0-pro is provide by Qwen.

doubao-seedance-2-5-260628

Seedance 2.5 is ByteDance Seed’s next-generation unified multimodal audio-video generation model, designed for filmmaking, advertising, education, simulation, and long-form content creation. It generates up to 30 seconds of synchronized audio and video in one pass and supports multi-round extensions. Compared with Seedance 2.0, it offers stronger storytelling, smoother transitions, richer reference support, improved realism, and more precise editing.

gemini-3.1-pro-preview

Gemini-3.1-pro-preview/text-to-text marks the peak of long-context LLMs with a 2M-token window, transforming massive dataset handling. Integrate on APISpace for superior reasoning, high-fidelity retrieval, and multi-shot in-context learning. From thousands of lines of code to full legal document sets, it misses no detail—delivering stable, authoritative text for the toughest professional workflows.

glm-5.1

glm-5.1 is provide by Zhipu.

gpt-6-sol

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

gpt-image-2.5-flare

gpt-image-2.5-flare is provide by OpenAI.

gpt-image-2.5-sunburst

gpt-image-2.5-sunburst is provide by OpenAI.

kimi-k2

kimi-k2 is provide by Moonshot.

o4-mini-2025-04-16

o4-mini-2025-04-16 is provide by .

claude-fable-5

The affordable Claude-Fable-5 API delivers Mythos-level intelligence for your most challenging projects. It excels at autonomous programming, multi-day reasoning, and complex visual tasks, while maintaining high safety standards and token efficiency.

gemini-3.5-flash-lite

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

glm-4.5

glm-4.5 is provide by Zhipu.

gpt-6-luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

grok-4.6

Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

grok-imagine-image

grok-imagine-image is provide by xAI.

MiniMax-M2.5

MiniMax-M2.5 is provide by MiniMax.

deepseek-v4-flash-ga-260731

deepseek-v4-flash-ga-260731 is provide by DeepSeek.

doubao-seedance-2-0-260128

Doubao Seedance 2.0 is ByteDance’s second-gen video model with a unified audio-video architecture. It accepts text, images, video, and audio in one call and generates synchronized video + audio. Use the text-to-video endpoint: prompt to get 4–15s clips up to 1080p with native sound.

gemini-3.1-flash-lite

gemini-3.1-flash-lite is provide by Google.

grok-4

grok-4 is provide by xAI.

kimi-k3

Kimi K3 is Moonshot AI’s 2.8T-parameter multimodal reasoning model, built for long-horizon coding and knowledge work.

kling-v3.0-pro

Kling-v3.0-pro/text-to-video marks the peak of generative video tech, with unmatched control over motion, lighting, and physical consistency. Built for high-end production, it turns complex text into fluid, high-res visual narratives. On APISpace, access this pro tool via solid API support and transparent pricing—every frame meets modern digital media and cinematic standards.

llama-3-8b

llama-3-8b is provide by Meta.

tts-1-hd

tts-1-hd is provide by .

claude-opus-4-8

Claude Opus 4.8 delivers top-tier reasoning and long-context processing. Use it for deep research or complex coding. Integrate via our unified API for reliable performance and easy scaling across AI apps.

claude-sonnet-4-6

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

grok-build-0.1

grok-build-0.1 is provide by xAI.

qwen-image-3.0

qwen-image-3.0 is provide by Qwen.

gpt-image-2

gpt-image-2 is OpenAI’s image model from April 2026. It features agentic “thinking” that plans composition before rendering, native 2K output, multilingual in-image text (including CJK), and masked editing with up to 16 reference images. Call it on APISpace via standard OpenAI request format.

grok-4-20-reasoning

grok-4-20-reasoning is provide by xAI.

MiniMax-M2.7

MiniMax-M2.7 is provide by MiniMax.

qwen3.6-plus

qwen3.6-plus is provide by Qwen.

wan2.6-i2v

wan2.6-i2v is provide by .

qwen3.5-122b-a10b

qwen3.5-122b-a10b is provide by Qwen.

deepseek-v4.1-flash

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp(opens in new tab). It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro(opens in new tab) on performance, speed, and task completion time.

glm-4.7

glm-4.7 is provide by Zhipu.

gpt-6.1-sol

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

grok-4-20-non-reasoning

grok-4-20-non-reasoning is provide by xAI.