Text generation models and pricing
The Qwen, GLM, and DeepSeek text generation models currently available through Star OS.
Star OS currently supports text generation models from Qwen, GLM, and DeepSeek. Use the exact Model ID below as the model value in your request.
How pricing works
Prices are in USD per 1 million tokens and are calculated separately for input and output tokens:
request cost = (input tokens × input rate) + (output tokens × output rate)The rates below are the current Star OS standard real-time prices. They exclude promotions, batch discounts, and context-cache discounts. For a live list of models enabled for your project, open Models. Your Star OS Console and billing records are the source of truth for charges.
Qwen
| Model ID | Best for | Input | Output | Notes |
|---|---|---|---|---|
qwen3.7-max | Complex reasoning and demanding production workloads | $2.50 | $7.50 | Flat rate to 1M input tokens |
qwen3.7-plus | General-purpose reasoning and agent workflows | $0.40 | $1.60 | $1.20 / $4.80 above 256K input tokens |
qwen3.6-plus | Balanced quality for production applications | $0.50 | $3.00 | $2.00 / $6.00 above 256K input tokens |
qwen-plus | Cost-conscious general text generation | $0.40 | $1.20 | $1.20 / $3.60 above 256K input tokens |
qwen3.6-flash | Fast, economical responses | $0.25 | $1.50 | $1.00 / $4.00 above 256K input tokens |
qwen3.5-flash | High-volume, low-latency text generation | $0.10 | $0.40 | Flat rate to 1M input tokens |
qwen-flash | Simple, high-volume text generation | $0.05 | $0.40 | $0.25 / $2.00 above 256K input tokens |
qwen3-coder-next | Code generation and software-engineering tasks | $0.30 | $1.50 | $0.50 / $2.50 above 32K; $0.80 / $4.00 above 128K |
GLM
| Model ID | Best for | Input | Output | Notes |
|---|---|---|---|---|
glm-5.2 | General text generation and reasoning | $1.40 | $4.40 | Flat rate; non-thinking and thinking modes |
glm-5.2-fast-preview | Latency-sensitive generation | $2.80 | $8.80 | Preview model; non-thinking and thinking modes |
glm-5.1 | General text generation and reasoning | $1.40 | $4.40 | Rate applies up to 200K input tokens |
DeepSeek
| Model ID | Best for | Input | Output | Notes |
|---|---|---|---|---|
deepseek-v4-pro | Complex reasoning, coding, and general workloads | $2.40 | $4.80 | Context-cache discount may apply |
deepseek-v4-flash | Fast, cost-efficient reasoning and text generation | $0.20 | $0.40 | Context-cache discount may apply |
deepseek-v3.2 | Balanced text generation and reasoning | $0.57 | $1.71 | Context-cache discount may apply |
Selecting a model
Start with a model that matches your workload, then set its Model ID in the request. For example:
{
"model": "qwen3.5-flash",
"messages": [{ "role": "user", "content": "Summarise this report." }]
}If a model is not marked Available in the Console, do not send requests to its ID. Model availability, model profiles, usage, and billing are all scoped to your project.
For throughput limits, see Rate limits.