Inferencing
Serverless Models
Model catalog for managed, on-demand inference on Qubrid AI.
Qubrid serverless inference gives you immediate access to hosted models over a standard API. There is no infrastructure to deploy: you send requests, and Qubrid runs the model on shared capacity. Billing is usage-based-typically per token for text models-so cost scales with actual consumption rather than reserved capacity.
Shared endpoints apply fair-use rate limits. They are a strong fit for development, benchmarks, and workloads with unpredictable volume. If you need predictable latency, sustained throughput, or private hardware, deploy on On-Demand GPUs or GPU Clusters instead.
The serverless catalog and self-managed GPU deployments do not always expose the same model lineup. Confirm model IDs in the tables below, then validate availability and pricing in the playground before shipping to production.
Pricing
Charges are metered from actual usage. There are no upfront commitments, idle fees, or cluster management overhead for serverless calls. Each table lists the API identifier, context window, and per-million-token prices. Some models use tiered pricing based on input length; the applicable tier is shown in the Pricing tier column.
Input and Output are shown in each table. Hover any row to see thinking, cache, batch, and other billing modes.
Each pricing table includes a short hint above the columns. Hover anywhere on a row to open a breakdown of every billing mode for that model.
For asynchronous or high-volume pipelines, ask support about batch pricing and enterprise rate cards.
Models
Jump to a category:
Text models
Hover any row to see additional billing modes (thinking, cache, batch, etc.).
| Organization | Model name | API model string | Context length | Pricing tier | Input (per 1M tokens) | Output (per 1M tokens) | Input (Thinking) (per 1M tokens) | Input (Implicit Cache) (per 1M tokens) | Input (Batch File) (per 1M tokens) | Explicit Cache Creation (per 1M tokens) | Explicit Cache Read (per 1M tokens) | Input (Batch Chat) (per 1M tokens) | Output (Batch File) (per 1M tokens) | Output (Batch Chat) (per 1M tokens) | Quantization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen | Qwen3.7 Max | 1,000,000 | - | $2.5 | $7.5 | $0.5 | $3.125 | $0.25 | - | - | - | - | - | - | |
| Z.ai | GLM 5 | 202,752 | ≤32k tokens | $0.573 | $2.58 | $0.115 | - | - | - | - | - | - | - | FP4 | |
| 32k–200k tokens | $0.86 | $3.154 | $0.172 | - | - | - | - | - | - | - | |||||
| Z.ai | GLM 5.1 | 202,752 | - | $1.68 | $5.28 | $0.312 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 5.2 | 202,752 | - | $1.1 | $3.851 | $0.275 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 5 Turbo | 202,752 | - | $1.44 | $4.8 | $0.288 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4.5 Air | 128,000 | - | $0.24 | $1.32 | $0.036 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4.5 AirX | 128,000 | - | $1.32 | $5.4 | $0.264 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4.5 X | 202,752 | - | $2.64 | $10.68 | $0.54 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4.5 Flash | 128,000 | - | $0 | $0 | $0 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4.7 Flash | 128,000 | - | $0 | $0 | $0 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4.7 FlashX | 128,000 | - | $0.084 | $0.48 | $0.012 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4 32B 0414 128K | 128,000 | - | $0.12 | $0.12 | - | - | - | - | - | - | - | - | FP4 | |
| DeepSeek | DeepSeek V4 Flash | 1,000,000 | - | $0.138 | $0.275 | $0.028 | - | - | - | - | - | - | - | FP4 | |
| DeepSeek | DeepSeek V4 Pro | 1,000,000 | - | $1.65 | $3.301 | $0.138 | - | - | - | - | - | - | - | FP4 | |
| NVIDIA | Nemotron 3 Nano Omni | 256,000 | - | $0.069 | $0.276 | - | - | - | - | - | - | - | - | BF16 | |
| Qwen | Qwen3.6 Max Preview | 262,144 | ≤128k tokens | $1.3 | $7.8 | $1.625 | $0.13 | - | - | - | - | - | - | - | |
| 128k–256k tokens | $2 | $12 | $2.5 | $0.2 | - | - | - | - | - | - | |||||
| DeepSeek | DeepSeek V3.2 | 163,000 | - | $0.287 | $0.216 | $0.058 | $0.144 | $0.359 | $0.029 | $0.287 | $0.431 | $0.431 | - | - | |
| Z.ai | GLM 4.7 | 202,752 | - | $0.72 | $2.64 | $0.132 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4.5 | 202,752 | - | $0.72 | $2.64 | $0.132 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4.6 | 202,752 | - | $0.72 | $2.64 | $0.132 | - | - | - | - | - | - | - | FP4 | |
| MiniMax | MiniMax M2.7 | 204,800 | - | $0.36 | $1.44 | $0.45 | $0.072 | - | - | - | - | - | - | FP4 | |
| NVIDIA | NVIDIA Nemotron 3 Super 120B A12B | 1,000,000 | - | $0.345 | $1.035 | - | - | - | - | - | - | - | - | FP8 | |
| MiniMax | MiniMax M2.5 | 196,608 | - | $0.304 | $1.213 | $0.061 | - | - | - | - | - | - | - | - | |
| NVIDIA | NVIDIA Nemotron 3 Nano 30B A3B | 128,000 | - | $0.04 | $0.16 | - | - | - | - | - | - | - | - | BF16 | |
| Moonshot AI | Kimi K2 Thinking | 262,144 | - | $0.574 | $2.294 | $0.115 | - | - | - | - | - | - | - | FP4 | |
| Qwen | Qwen3 Next 80B A3B Thinking | 262,144 | - | $0.15 | $1.2 | - | - | - | - | - | - | - | - | - | |
| Moonshot AI | Kimi K2 Instruct | 128,000 | - | $0.574 | $2.294 | $0.115 | - | - | - | - | - | - | - | - | |
| DeepSeek | DeepSeek R1 0528 | 163,840 | - | $0.574 | $2.294 | - | - | - | - | - | - | - | - | - | |
| Qwen | Qwen3 Max | 256,000 | ≤32k tokens | $1.2 | $6 | - | - | - | - | - | - | - | - | - | |
| 32k–128k tokens | $2.4 | $12 | - | - | - | - | - | - | - | - | |||||
| 128k–256k tokens | $3 | $15 | - | - | - | - | - | - | - | - | |||||
| Microsoft | Fara 7B | 128,000 | - | $0.168 | $0.2 | - | - | - | - | - | - | - | - | - | |
| DeepSeek | DeepSeek R1 Distill Llama 70B | 131,100 | - | $0.56 | $0.64 | - | - | - | - | - | - | - | - | - | |
| DeepSeek | DeepSeek V3 | 128,000 | - | $0.287 | $1.147 | $0.057 | $0.143 | - | - | - | - | $0.573 | - | - | |
| MistralAI | Mistral 7B Instruct v0.3 | 32,768 | - | $0.088 | $0.152 | - | - | - | - | - | - | - | - | - | |
| Meta | Llama 3.3 70B Instruct | 128,000 | - | $0.096 | $0.304 | - | - | - | - | - | - | - | - | - | |
| OpenAI | GPT OSS 120B | 256,000 | - | $0.12 | $0.48 | $0.012 | - | - | - | - | - | - | - | - | |
| Qwen | Qwen Plus | 1,000,000 | ≤256k tokens | $0.4 | $1.2 | $0.4 | - | - | - | - | - | - | - | - | |
| 256k–1M tokens | $1.2 | $3.6 | $1.2 | - | - | - | - | - | - | - |
Code models
Hover any row to see additional billing modes (thinking, cache, batch, etc.).
| Organization | Model name | API model string | Context length | Pricing tier | Input (per 1M tokens) | Output (per 1M tokens) | Input (Thinking) (per 1M tokens) | Input (Implicit Cache) (per 1M tokens) | Input (Batch File) (per 1M tokens) | Explicit Cache Creation (per 1M tokens) | Explicit Cache Read (per 1M tokens) | Input (Batch Chat) (per 1M tokens) | Output (Batch File) (per 1M tokens) | Output (Batch Chat) (per 1M tokens) | Quantization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen | Qwen3 Coder Plus | 262,000 | ≤32k tokens | $1 | $5 | $0.2 | $1.25 | $0.1 | - | - | - | - | - | - | |
| 32k–128k tokens | $1.8 | $9 | $0.36 | $2.25 | $0.18 | - | - | - | - | - | |||||
| 128k–256k tokens | $3 | $15 | $0.6 | $3.75 | $0.3 | - | - | - | - | - | |||||
| 256k–1M tokens | $6 | $60 | $1.2 | $7.5 | $0.6 | - | - | - | - | - | |||||
| Qwen | Qwen3 Coder Next | 262,144 | ≤32k tokens | $0.3 | $1.5 | - | - | - | - | - | - | - | - | - | |
| 32k–128k tokens | $0.5 | $2.5 | - | - | - | - | - | - | - | - | |||||
| 128k–256k tokens | $0.8 | $4 | - | - | - | - | - | - | - | - | |||||
| Qwen | Qwen3 Coder 30B A3B Instruct | 262,114 | ≤32k tokens | $0.45 | $2.25 | - | - | - | - | - | - | - | - | - | |
| 32k–128k tokens | $0.75 | $3.75 | - | - | - | - | - | - | - | - | |||||
| 128k–256k tokens | $1.2 | $6 | - | - | - | - | - | - | - | - | |||||
| 256k–1M tokens | $2.4 | $14.4 | - | - | - | - | - | - | - | - | |||||
| Qwen | Qwen3 Coder 480B A35B Instruct | 262,114 | ≤32k tokens | $1.5 | $7.5 | - | - | - | - | - | - | - | - | - | |
| 32k–128k tokens | $2.7 | $13.5 | - | - | - | - | - | - | - | - | |||||
| 128k–256k tokens | $4.5 | $22.5 | - | - | - | - | - | - | - | - | |||||
| 256k–1M tokens | $9 | $90 | - | - | - | - | - | - | - | - | |||||
| Qwen | Qwen3 Coder Flash | 262,114 | ≤32k tokens | $0.3 | $1.5 | $0.06 | $0.375 | $0.03 | - | - | - | - | - | - | |
| 32k–128k tokens | $0.5 | $2.5 | $0.1 | $0.625 | $0.05 | - | - | - | - | - | |||||
| 128k–256k tokens | $0.8 | $4 | $0.16 | $1 | $0.08 | - | - | - | - | - | |||||
| 256k–1M tokens | $1.6 | $9.6 | $0.32 | $2 | $0.16 | - | - | - | - | - | |||||
| Moonshot AI | Kimi K2.7 Code | 256,000 | - | $1.14 | $4.8 | $0.228 | - | - | - | - | - | - | - | - |
Vision models
Hover any row to see additional billing modes (thinking, cache, batch, etc.).
| Organization | Model name | API model string | Context length | Pricing tier | Input (per 1M tokens) | Output (per 1M tokens) | Input (Thinking) (per 1M tokens) | Input (Implicit Cache) (per 1M tokens) | Input (Batch File) (per 1M tokens) | Explicit Cache Creation (per 1M tokens) | Explicit Cache Read (per 1M tokens) | Input (Batch Chat) (per 1M tokens) | Output (Batch File) (per 1M tokens) | Output (Batch Chat) (per 1M tokens) | Quantization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MiniMax | MiniMax M3 | 1,000,000 | ≤512k tokens | $0.36 | $1.44 | $0.072 | - | - | - | - | - | - | - | - | |
| 512k–1M tokens | $0.72 | $2.88 | $0.144 | - | - | - | - | - | - | - | |||||
| Qwen | Qwen3.7 Plus | 256,000 | ≤256k tokens | $0.4 | $1.6 | $0.08 | $0.5 | $0.04 | - | - | - | - | - | - | |
| 256k–1M tokens | $1.2 | $4.8 | $0.24 | $1.5 | $0.12 | - | - | - | - | - | |||||
| Qwen | Qwen3.6 Plus | 256,000 | ≤256k tokens | $0.5 | $3 | $0.625 | $0.05 | - | - | - | - | - | - | - | |
| 256k–1M tokens | $2 | $6 | $2.5 | $0.2 | - | - | - | - | - | - | |||||
| Moonshot AI | Kimi K2.5 | 256,000 | - | $0.574 | $3.011 | $0.115 | $0.718 | $0.057 | - | - | - | - | - | - | |
| Moonshot AI | Kimi K2.6 | 256,000 | - | $0.8939 | $3.7131 | $0.1788 | $1.1174 | $0.0894 | - | - | - | - | - | - | |
| Qwen | Qwen3.6 27B | 256,000 | - | $0.6 | $3.6 | - | - | - | - | - | - | - | - | - | |
| Qwen | Qwen3.6 35B A3B | 256,000 | - | $0.375 | $2.25 | - | - | - | - | - | - | - | - | - | |
| Qwen | Qwen3.5 122B A10B | 256,000 | - | $0.4 | $3.2 | - | - | - | - | - | - | - | - | - | |
| Qwen | Qwen3.5 27B | 256,000 | - | $0.3 | $2.4 | - | - | - | - | - | - | - | - | - | |
| Qwen | Qwen3.5 35B A3B | 256,000 | - | $0.25 | $2 | - | - | - | - | - | - | - | - | - | |
| Qwen | Qwen3.5 397B A17B | 256,000 | - | $0.6 | $3.6 | - | - | - | - | - | - | - | - | - | |
| Qwen | Qwen3.5 Flash | 1,000,000 | - | $0.1 | $0.4 | $0.125 | $0.01 | - | - | - | - | - | - | - | |
| Qwen | Qwen3.5 Plus | 1,000,000 | ≤256k tokens | $0.4 | $2.4 | $0.5 | $0.04 | - | - | - | - | - | - | - | |
| 256k–1M tokens | $0.5 | $3 | $0.625 | $0.05 | - | - | - | - | - | - | |||||
| Qwen | Qwen3 VL 235B A22B Thinking | 256,000 | - | $0.4 | $4 | - | - | - | - | - | - | - | - | - | |
| Qwen | Qwen3 VL 235B A22B Instruct | 256,000 | - | $0.4 | $1.6 | - | - | - | - | - | - | - | - | - | |
| Qwen | Qwen3 VL 30B A3B Instruct | 256,000 | - | $0.104 | $0.104 | - | - | - | - | - | - | - | - | - | |
| Qwen | Qwen3 VL 8B Instruct | 256,000 | - | $0.064 | $0.064 | - | - | - | - | - | - | - | - | - | |
| Qwen | Qwen3 VL Flash | 256,000 | ≤32k tokens | $0.05 | - | $0.01 | $0.025 | $0.0625 | $0.005 | $0.4 | $0.2 | - | - | - | |
| 32k–128k tokens | $0.075 | - | $0.015 | $0.038 | $0.09375 | $0.0075 | $0.6 | $0.3 | - | - | |||||
| 128k–256k tokens | $0.12 | - | $0.024 | $0.06 | $0.15 | $0.012 | $0.96 | $0.48 | - | - | |||||
| Qwen | Qwen3 VL Plus | 256,000 | ≤32k tokens | $0.2 | $1.6 | - | - | - | - | - | - | - | - | - | |
| 32k–128k tokens | $0.3 | $2.4 | - | - | - | - | - | - | - | - | |||||
| 128k–256k tokens | $0.6 | $4.8 | - | - | - | - | - | - | - | - | |||||
| Z.ai | GLM 4.5V | 202,752 | - | $0.72 | $2.16 | $0.132 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4.6V | 202,752 | - | $0.36 | $1.08 | $0.06 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4.6V Flash | 128,000 | - | $0 | $0 | $0 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 4.6V FlashX | 128,000 | - | $0.048 | $0.48 | $0.0048 | - | - | - | - | - | - | - | FP4 | |
| Z.ai | GLM 5V Turbo | 202,752 | - | $1.44 | $4.8 | $0.288 | - | - | - | - | - | - | - | FP4 |
OCR models
Hover any row to see additional billing modes (thinking, cache, batch, etc.).
| Organization | Model name | API model string | Context length | Pricing tier | Input (per 1M tokens) | Output (per 1M tokens) | Input (Thinking) (per 1M tokens) | Input (Implicit Cache) (per 1M tokens) | Input (Batch File) (per 1M tokens) | Explicit Cache Creation (per 1M tokens) | Explicit Cache Read (per 1M tokens) | Input (Batch Chat) (per 1M tokens) | Output (Batch File) (per 1M tokens) | Output (Batch Chat) (per 1M tokens) | Quantization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Tencent Hunyuan | HunyuanOCR | 16,000 | - | $0.168 | $0.28 | - | - | - | - | - | - | - | - | - |