Model Recommendations Nebula API supports 150+ mainstream AI models. This page provides detailed model information, pricing, and usage instructions.
Enterprise-grade AI model API gateway. Aggregating excellent large models. No rate limits, no expiration, pay-as-you-go, reliable long-term service.
Below are the currently stable and popular models. For the complete model list and real-time pricing, visit Nebula API Console .
Status legend — available: verified working over the API. partial: reachable but works only with payload constraints (see the notes below each table). unavailable: currently access-limited or returning errors. All model IDs below come from the live GET /v1/models snapshot (151 models).
Model Categories Reasoning Models Model Name Model ID Features Recommended For Status o4-mini o4-mini Lightweight reasoning model Coding tasks available o3-mini o3-mini Latest reasoning model, great value Complex reasoning, math, coding available o1 o1 Strong general-purpose reasoning Complex reasoning, analysis available
GPT Series Model Name Model ID Context Features Recommended For Status GPT 5.5 gpt-5.5 400K Latest flagship, most capable general model Conversation, thinking, copywriting, coding available GPT 5.4 gpt-5.4 400K High-capability reasoning and coding Conversation, thinking, copywriting, coding available GPT 5.2 gpt-5.2 400K Improved on GPT-5.1, more reliable, flexible and user-friendly interaction Conversation, thinking, copywriting, coding available GPT 5.1 Codex gpt-5.1-codex 400K Enhanced developer toolchain, stronger reasoning framework, context-aware code analysis and generation Conversation, coding, copywriting available GPT 5.1 Chat gpt-5.1-chat 128K First to introduce chain-of-thought in chat, faster, more natural, context-aware dialogue Conversation, copywriting available GPT 5.1 gpt-5.1 400K On-demand reasoning, adaptive reasoning Conversation, thinking, copywriting, coding available GPT 5.1 Codex Mini gpt-5.1-codex-mini 128K Lightweight and efficient, for resource-constrained, cost-sensitive scenarios Conversation, coding, copywriting available GPT Chat Latest gpt-chat-latest 128K Rolling “latest chat” alias Conversation, copywriting partial GPT 5 Pro gpt-5-pro 400K Highest-effort reasoning variant Complex reasoning, agents partial
gpt-chat-latest rejects max_tokens — send max_completion_tokens instead.gpt-5-pro must be called via /v1/responses; several /v1/chat/completions parameters are unsupported. Image Generation Models Model Name Model ID Features Status GPT-Image-2 gpt-image-2 OpenAI latest image generation available GPT-Image-1.5 gpt-image-1.5 OpenAI image generation, improved fidelity available GPT-Image-1 gpt-image-1 OpenAI official image generation available
Audio & Realtime Model Name Model ID Capability Status GPT Realtime 2 gpt-realtime-2 Realtime speech-to-speech available GPT Realtime gpt-realtime Realtime speech-to-speech available GPT Realtime Mini gpt-realtime-mini Lightweight realtime audio available GPT-4o Mini TTS gpt-4o-mini-tts Text-to-speech (/v1/audio/speech) available
Claude 4 Series (Latest) Model Name Model ID Context Features Recommended For Status Claude Opus 4.8 claude-opus-4-8 1M Anthropic’s latest flagship, frontier coding and agent performance Conversation, reasoning, coding, copywriting partial Claude Opus 4.7 claude-opus-4-7 1M High-capability reasoning and coding Conversation, reasoning, coding, copywriting partial Claude Opus 4.6 claude-opus-4-6 1M Sets new standards for production code, complex agents and office tasks Conversation, reasoning, coding, copywriting available Claude Opus 4.5 claude-opus-4-5-20251101 200K Highly capable model for production code and complex agents Conversation, thinking, copywriting, coding available Claude Sonnet 4.6 claude-sonnet-4-6 200K Balanced speed and capability, strong tool use Conversation, thinking, copywriting, coding available Claude Sonnet 4.5 claude-sonnet-4-5-20250929 200K Agent improvements, tool handling, memory and context processing enhanced Conversation, thinking, copywriting, coding available Claude Haiku 4.5 claude-haiku-4-5-20251001 200K Anthropic’s most efficient model, fast and cost-effective near-frontier performance Conversation, thinking, copywriting, coding available
Claude Opus 4.7 / 4.8 deprecate the temperature parameter — omit sampling parameters or send a minimal payload to avoid 400 errors.
Text Models Model Name Model ID Context Features Recommended For Status Gemini 3.1 Pro Preview gemini-3.1-pro-preview 1M Powerful agent and coding model, best multimodal understanding Conversation, thinking, copywriting, coding available Gemini 3.5 Flash gemini-3.5-flash-global 1M Fast, cost-effective multi-turn dialogue Conversation, thinking, copywriting, coding available Gemini 3 Flash Preview gemini-3-flash-preview 1M Powerful agentic capabilities at speed and value Conversation, thinking, copywriting, coding partial Gemini 3.1 Flash Lite gemini-3.1-flash-lite 1M Lightweight, low-latency variant Conversation, fast response available Gemini 2.5 Pro gemini-2.5-pro 1M High-capability multimodal reasoning Conversation, thinking, copywriting, coding available Gemini 2.5 Flash gemini-2.5-flash 1M Fast, cost-effective general model Conversation, fast response available
gemini-3-flash-preview may time out on /v1/chat/completions when extended parameters are supplied — prefer a minimal payload.
Image Models Model Name Model ID Features Status Gemini 3 Pro Image gemini-3-pro-image-preview Gemini 3 Pro image generation with reasoning available Gemini 3.1 Flash Image gemini-3.1-flash-image-preview Fast Gemini image generation available Gemini 2.5 Flash Image gemini-2.5-flash-image Gemini 2.5 image generation available
Model Name Model ID Context Features Recommended For Status Grok 4.3 grok-4.3 See console Latest Grok flagship, strong natural language, math and reasoning Conversation, thinking, copywriting, coding available Grok 4.20 Reasoning grok-4.20-0309-reasoning See console Reasoning variant Conversation, thinking, coding available Grok 4.20 Non-Reasoning grok-4.20-0309-non-reasoning See console Fast non-reasoning variant Conversation, copywriting available Grok 4.1 Fast Reasoning grok-4-1-fast-reasoning See console Cost-effective, fast reasoning variant Conversation, thinking, coding available Grok 4.1 Fast Non-Reasoning grok-4-1-fast-non-reasoning See console Cost-effective, fast non-reasoning variant Conversation, copywriting available
Model Name Model ID Context Features Recommended For Status DeepSeek V4 Pro deepseek-v4-pro See console Latest DeepSeek flagship, strongest overall capability Conversation, thinking, copywriting, coding available DeepSeek V4 Flash deepseek-v4-flash See console Fast, cost-effective V4 variant Conversation, fast response, coding available DeepSeek V3.2 deepseek-v3-2-251201 128K Hybrid reasoning model, thinking and non-thinking modes Conversation, thinking, copywriting, coding available DeepSeek V3 (0324) deepseek-v3-250324 128K Strong overall, cost-effective General use available DeepSeek R1 deepseek-r1-250528 64K Reasoning model Math, reasoning available
Zhipu AI (GLM) Model Name Model ID Context Features Recommended For Status GLM-5.2 glm-5.2 See console Latest Zhipu flagship chat model Conversation, copywriting, coding available GLM-5.1 glm-5.1 See console Zhipu flagship chat model Conversation, copywriting, coding available GLM-4.7 glm-4.7 200K Strong coding and multi-step reasoning, 355B params Conversation, thinking, long-range planning, coding, tool use available
Doubao Seed Series Model Name Model ID Context Features Recommended For Status Doubao Seed 2.1 Pro doubao-seed-2-1-pro-260628 See console Latest Doubao flagship chat model Conversation, thinking, copywriting available Doubao Seed 2.0 Pro doubao-seed-2-0-pro-260215 See console High-capability Doubao chat model Conversation, thinking, copywriting available Doubao Seed 1.8 doubao-seed-1-8-251228 See console Doubao chat model Conversation, copywriting available
Alibaba Qwen Model Name Model ID Capability Features Recommended For Status Qwen3.7 Max qwen3.7-max text Latest Qwen flagship Conversation, thinking, copywriting, coding available Qwen3 Max qwen3-max text High-capability Qwen model Conversation, thinking, copywriting available Qwen3 Coder Plus qwen3-coder-plus text Code model with strong Coding Agent, tool use and environment interaction Conversation, thinking, coding, copywriting available Qwen Image Plus qwen-image-plus image Qwen image generation, strong text rendering Text-to-image, image generation available
Moonshot Kimi Model Name Model ID Context Features Recommended For Status Kimi K2.7 Code kimi-k2.7-code See console Latest Kimi coding model Conversation, coding available Kimi K2.6 kimi-k2.6 See console Strong general and agent capabilities Conversation, thinking, copywriting, coding available kimi-k2.5 kimi-k2.5 256K Native multimodal, vision and text, thinking and non-thinking modes Conversation, thinking available Kimi K2 Thinking kimi-k2-thinking 256K Reasoning-focused MoE model Conversation, thinking, coding available
Video Generation Model Name Model ID Type Status Wan 2.7 (T2V) wan2.7-t2v Text-to-video available Wan 2.7 (I2V) wan2.7-i2v Image-to-video available Wan 2.7 (R2V) wan2.7-r2v Reference-to-video available Wan 2.6 (T2V) wan2.6-t2v Text-to-video available Wan 2.6 (I2V) wan2.6-i2v Image-to-video available Wan 2.6 (R2V) wan2.6-r2v Reference-to-video available Doubao Seedance 2.0 doubao-seedance-2-0-260128 Text/Image-to-video available Doubao Seedance 1.5 Pro doubao-seedance-1-5-pro-251215 Text/Image-to-video available Doubao Seedance 1.0 Pro doubao-seedance-1-0-pro-250528 Text/Image-to-video available Veo 3.1 veo-3.1-generate-001 Text/Image-to-video available Veo 3.1 Fast veo-3.1-fast-generate-001 Text/Image-to-video available Veo 3.0 Fast veo-3.0-fast-generate-001 Text/Image-to-video available HappyHorse 1.0 (T2V) happyhorse-1.0-t2v Text-to-video available Sora 2 sora-2 Text-to-video unavailable MiniMax Hailuo 2.3 MiniMax-Hailuo-2.3 Text/Image-to-video unavailable
Image Generation Model Name Model ID Provider Status Doubao Seedream 5.0 doubao-seedream-5-0-260128 Doubao available Doubao Seedream 4.5 doubao-seedream-4-5-251128 Doubao available Doubao Seedream 4.0 doubao-seedream-4-0-250828 Doubao available Imagen 4.0 Ultra imagen-4.0-ultra-generate-001 Google available Imagen 4.0 imagen-4.0-generate-001 Google available Imagen 3.0 imagen-3.0-generate-002 Google available Qwen Image Edit Plus qwen-image-edit-plus Qwen available MiniMax Image 01 minimax-image-01 MiniMax available Doubao Seedream 3.0 doubao-seedream-3-0-t2i-250415 Doubao unavailable Image 01 image-01 MiniMax unavailable
Embeddings Model Name Model ID Provider Status Text Embedding 3 Large text-embedding-3-large OpenAI available Text Embedding 3 Small text-embedding-3-small OpenAI available Text Embedding Ada 002 text-embedding-ada-002 OpenAI available
Billing
Pay-as-you-go : Billed by actual Token usageNo minimum : Use what you pay for, balance never expiresReal-time billing : Deducted immediately after each call
Price Advantages
Official source forwarding with competitive pricing
Contact support for bulk discounts
Model Selection Coding
Writing
Fast Response
Image Generation
Video Generation
Long Text
Top Performance : Claude Opus 4.8, GPT 5.5, Claude Sonnet 4.6Cost-effective : Claude Haiku 4.5, GPT 5.1 Codex Mini, DeepSeek V4 Flash, Grok 4.1 Fast Reasoning, GLM-4.7Alternative : o4-mini, Gemini 3.1 Pro Preview, Qwen3 Coder Plus, kimi-k2.5, doubao-seed-2-1-pro-260628
Primary : GPT 5.5, Claude Opus 4.8, Claude Sonnet 4.6, GLM-5.2Alternative : Gemini 3.1 Pro Preview, Kimi K2.6, GLM-4.7, doubao-seed-2-1-pro-260628
Primary : Claude Haiku 4.5, Gemini 3.1 Flash Lite, Grok 4.1 Fast ReasoningAlternative : GLM-5.2, GLM-4.7, GPT 5.1 Codex Mini, doubao-seed-2-0-mini-260215
Recommended : GPT-Image-2, Qwen Image Plus, Gemini 3 Pro Image, Doubao Seedream 5.0
Recommended : Wan 2.7 (wan2.7-t2v), Doubao Seedance 2.0, Veo 3.1
Ultra-long context : Gemini 3.1 Pro Preview (1M), Claude Opus 4.8 (1M)Coding : Claude 4 series, kimi-k2.5, Kimi K2 Thinking Cost Optimization
Tiered usage : Use cheaper models for simple tasksTest first : Test with smaller models before scalingBatch processing : Use Mini versions for bulk tasksCache reuse : Cache repeated query results
API Docs Detailed API specifications
Quick Start Integration guide
Model list is continuously updated. We add new models as they become available. Contact support for specific model requests or bulk needs.
