Runcrate
Aggregator
OpenAI-compatible inference gateway with 170+ open and proprietary models for text, image, video, audio and embeddings, routed across providers and billed per use from a prepaid balance shared with its GPU cloud.
Features
OpenAI Compatible
Streaming
Batching
Fine-tuning
Embeddings
Vision
Audio
Function Calling
JSON Mode
Compliance
SOC 2
HIPAA
GDPR
Pricing Model
per token Free tier: DeepSeek V4.1 Flash, GLM 5.3, GLM 5.3 Flash, gpt-oss 120B and Qwen3.8 Flash free with a GitHub account at least 30 days old (session cap plus weekly allowance, resets Monday)
Details
Models 94
API Base
https://api.runcrate.ai/v1 EmbeddingsImage GenerationLLM Inference
Model Catalog (94)
| Model | Type | Input $/1M | Output $/1M | Context | Speed | Status |
|---|---|---|---|---|---|---|
| BGE-M3 BAAI | embedding | $0.011 | see notes | 8k | — | |
| Claude Fable 5 Anthropic | llm | $10.50 | $52.50 | 1M | — | |
| Claude Fable 5.1 Anthropic | llm | $10.50 | $52.50 | 1M | — | |
| Claude Opus 5 Anthropic | llm | $5.25 | $26.25 | 1M | — | |
| Claude Opus 5.5 Anthropic | llm | $4.20 | $21.00 | 1M | — | |
| Claude Sonnet 5 Anthropic | llm | $3.15 | $15.75 | 1M | — | |
| Claude Sonnet 5.5 Anthropic | llm | $2.10 | $10.50 | 1M | — | |
| DeepSeek R1 0528 DeepSeek · 671B MoE | llm | $0.525 | $2.26 | 164k | — | |
| DeepSeek V3.2 DeepSeek · 671B MoE (37B active) | llm | $0.273 | $0.399 | 164k | — | |
| DeepSeek V4 Flash DeepSeek | llm | $0.095 | $0.189 | 1.0M | — | |
| DeepSeek V4 Pro DeepSeek | llm | $1.36 | $2.73 | 1.0M | — | |
| DeepSeek V4.1 Flash DeepSeek | llm | $0.147 | $0.441 | 1.0M | — | |
| Flux 1 Dev Black Forest Labs | image gen | $0.026/img | — | — | — | |
| Flux 1 Schnell Black Forest Labs | image gen | $0.0032/img | — | — | — | |
| Flux 1.1 Pro Black Forest Labs | image gen | $0.042/img | — | — | — | |
| Flux 2 Dev Black Forest Labs | image gen | $0.013/img | — | — | — | |
| Flux 2 Flex Black Forest Labs | image gen | $0.063/img | — | — | — | |
| Flux 2 Max Black Forest Labs | image gen | $0.073/img | — | — | — | |
| Flux 2 Pro Black Forest Labs | image gen | $0.032/img | — | — | — | |
| GLM 4.7 Zhipu AI | llm | $0.336 | $1.47 | 203k | — | |
| GLM 5.2 Z.ai | llm | $0.591 | $1.89 | 1.0M | — | |
| GLM 5.3 Z.ai | llm | $0.591 | $2.63 | 1.0M | — | |
| GLM 5.3 Flash Z.ai | llm | $0.158 | $0.525 | 1.0M | — | |
| GLM 5.3 Prime Z.ai | llm | $2.94 | $9.24 | 1M | — | |
| GPT Image 2 OpenAI | image gen | $0.013/img | — | — | — | |
| GPT OSS 120B OpenAI · 117B MoE (5.1B active) | llm | $0.039 | $0.178 | 131k | — | |
| GPT-5.3 Codex OpenAI | llm | $1.84 | $14.70 | 400k | — | |
| GPT-5.4 Mini OpenAI | llm | $0.787 | $4.72 | 400k | — | |
| GPT-5.4 Nano OpenAI | llm | $0.210 | $1.31 | 400k | — | |
| GPT-5.4 Pro OpenAI | llm | $31.50 | $189.00 | 1M | — | |
| GPT-5.5 OpenAI | llm | $5.25 | $31.50 | 1M | — | |
| GPT-5.6 Sol Pro OpenAI | llm | $4.20 | $21.00 | 1.1M | — | |
| GPT-5.6 Terra OpenAI | llm | $2.10 | $12.60 | 1.1M | — | |
| GPT-6 Astra OpenAI | llm | $10.50 | $52.50 | 1.1M | — | |
| GPT-6 Luna OpenAI | llm | $0.105 | $0.525 | 1.1M | — | |
| GPT-6.1 Sol OpenAI | llm | $2.10 | $10.50 | 1.1M | — | |
| Gemini 2.5 Flash Image Google | image gen | $0.042/img | — | — | — | |
| Gemini 3.1 Flash Lite Google | llm | $0.263 | $1.57 | 1M | — | |
| Gemini 3.1 Pro Google | llm | $2.10 | $12.60 | 1M | — | |
| Gemini 3.5 Flash Google | llm | $1.57 | $9.45 | 1M | — | |
| Gemini 3.5 Flash Lite Google | llm | $0.315 | $2.63 | 1M | — | |
| Gemini 3.7 Flash Google | llm | $0.787 | $3.94 | 1M | — | |
| Gemini 3.8 Flash Google | llm | $0.866 | $4.33 | 1.0M | — | |
| Gemma 3 12B Google · 12B | llm | $0.042 | $0.126 | 131k | — | |
| Gemma 3 27B Google · 27B | llm | $0.084 | $0.168 | 131k | — | |
| Gemma 3 4B Google · 4B | llm | $0.052 | $0.105 | 131k | — | |
| Gemma 4 26B A4B Google | llm | $0.073 | $0.357 | 262k | — | |
| Gemma 4 31B Google · 27B | llm | $0.142 | $0.535 | 262k | — | |
| Granite 4.2 8B IBM | llm | $0.063 | $0.263 | 131k | — | |
| Grok 4.5 xAI | llm | $2.10 | $6.30 | 500k | — | |
| Grok 4.7 xAI | llm | $2.10 | $6.30 | 500k | — | |
| Grok Build 0.1 xAI | code | $1.05 | $2.10 | 256k | — | |
| Hy4 Preview Tencent | llm | $0.876 | $2.63 | 1.0M | — | |
| Ideogram 3.0 Ideogram | image gen | $0.063/img | — | — | — | |
| Inkling Small Thinking Machines | llm | $0.472 | $1.26 | 524k | — | |
| Kimi K2.6 Moonshot AI · 1T MoE (32B active) | llm | $0.787 | $3.67 | 262k | — | |
| Kimi K3 Moonshot AI | llm | $2.99 | $14.96 | 1.0M | — | |
| Llama 3.3 70B Meta · 70B | llm | $0.105 | $0.336 | 131k | — | |
| MiMo V2.6 Flash Xiaomi | llm | $0.096 | $0.191 | 1.0M | — | |
| MiMo V2.6 Pro Xiaomi | llm | $0.406 | $0.822 | 1.0M | — | |
| MiniMax M3 MiniMax | llm | $0.294 | $1.16 | 524k | — | |
| Ministral 3 8B Mistral AI · 8B | llm | $0.158 | $0.158 | 128k | — | |
| Mistral Large 3 Mistral AI · 675B MoE (41B active) | llm | $0.525 | $1.57 | 256k | — | |
| Mistral Small 4 Mistral AI · 119B | llm | $0.158 | $0.630 | 256k | — | |
| Muse Glimmer 30B Meta | llm | $0.315 | $1.26 | 131k | — | |
| Muse Spark 1.3 Muse | llm | $1.31 | $4.46 | 1.0M | — | |
| Nemotron 3.5 Lightning NVIDIA | llm | $0.063 | $0.168 | 262k | — | |
| Qwen 3.5 9B Alibaba · 9B | llm | $0.105 | $0.158 | 262k | — | |
| Qwen Image Alibaba | image gen | $0.032/img | — | — | — | |
| Qwen3 Coder 480B A35B Alibaba | code | $0.315 | $1.05 | 262k | — | |
| Qwen3 Embedding 0.6B Alibaba · 0.6B | embedding | $0.011 | see notes | 33k | — | |
| Qwen3 Embedding 4B Alibaba · 4B | embedding | $0.021 | see notes | 33k | — | |
| Qwen3 Embedding 8B Alibaba · 8B | embedding | $0.011 | see notes | 33k | — | |
| Qwen3 Next 80B A3B Instruct Alibaba | llm | $0.076 | $0.924 | 262k | — | |
| Qwen3 VL 235B A22B Instruct Alibaba | multimodal | $0.210 | $0.924 | 262k | — | |
| Qwen3 VL 30B A3B Instruct Alibaba | multimodal | $0.158 | $0.630 | 262k | — | |
| Qwen3.5 397B A17B Alibaba | llm | $0.472 | $3.15 | 262k | — | |
| Qwen3.5-27B Alibaba | llm | $0.273 | $2.73 | 262k | — | |
| Qwen3.5-35B-A3B Alibaba | llm | $0.147 | $1.05 | 262k | — | |
| Qwen3.6 27B Alibaba | llm | $0.336 | $3.36 | 262k | — | |
| Qwen3.6 35B A3B Alibaba | llm | $0.105 | $0.998 | 262k | — | |
| Qwen3.7 Max Alibaba | llm | $2.63 | $7.88 | 256k | — | |
| Qwen3.7 Plus Alibaba | llm | $0.525 | $2.10 | 256k | — | |
| Qwen3.8 27B Alibaba | llm | $0.158 | $1.97 | 262k | — | |
| Qwen3.8 Flash Alibaba | llm | $0.119 | $0.401 | 1M | — | |
| Qwen3.8 Max Alibaba | llm | $1.73 | $5.20 | 256k | — | |
| Qwen3.8 Omni Flash Alibaba | llm | $0.158 | $0.493 | 1M | — | |
| Seed 2.0 Code ByteDance | llm | $0.525 | $3.15 | 256k | — | |
| Seed 2.1 Turbo ByteDance | llm | $0.525 | $2.63 | 256k | — | |
| Seed-2.0-Mini ByteDance | llm | $0.105 | $0.420 | 256k | — | |
| Seedream 4.5 ByteDance | image gen | $0.042/img | — | — | — | |
| Stable Diffusion 3.5 Large Stability AI | image gen | $0.068/img | — | — | — | |
| Whisper Large V3 OpenAI · 1.5B | speech to_text | $47250.00 | $47250.00 | — | — | |
| gpt-oss-20b OpenAI | llm | $0.032 | $0.147 | 131k | — |
Runcrate API FAQ
Is the Runcrate API free?
Yes, Runcrate has a free tier: DeepSeek V4.1 Flash, GLM 5.3, GLM 5.3 Flash, gpt-oss 120B and Qwen3.8 Flash free with a GitHub account at least 30 days old (session cap plus weekly allowance, resets Monday). Paid usage is billed per model.
What is the cheapest Runcrate model?
BGE-M3 at $0.01 in per 1M tokens, based on the 94 models we track for Runcrate.
How many models does Runcrate offer?
We track 94 Runcrate models: 72 LLM, 13 image generation, 4 embedding, 2 coding, 2 multimodal, 1 speech-to-text.
Is the Runcrate API OpenAI-compatible?
Yes. Runcrate exposes an OpenAI-compatible endpoint, so you can use the OpenAI SDKs by changing the base URL and API key.