LLM API model pricing and model list
Compare live API prices for GPT, Claude, Grok, DeepSeek and Qwen. Check token rates in CNY, model IDs, context windows, image support and integration guides.
| Model | Provider | Price | Context | Image capabilities | Copy action |
|---|---|---|---|---|---|
| DeepSeek | 7.5× · ¥3 / 1M tokensSource discrepancy | 1M | Text input | ||
Get an API key Best for: Complex reasoning, Software development, Long documents
Complex reasoningSoftware developmentLong documents Source discrepancy | |||||
7.5× · ¥3 / 1M tokens
Best for: Complex reasoning, Software development, Long documents
- Provider / source
- DeepSeek
- Model type
- Complex reasoning · Software development
- Context
- 1M
- Price
- 7.5× · ¥3 / 1M tokens
Source discrepancy
Data scopeUpdated Nov 22, 2026, 8:49 PM
Check the model ID, price, and billing unit in the current catalog before making a request.
How to estimate the cost of a request
Use the model’s separate input and output rates per million tokens. For example, at illustrative rates of ¥2 for input and ¥8 for output, a request with 10,000 uncached input tokens and 1,000 output tokens costs (10,000 × 2 + 1,000 × 8) ÷ 1,000,000 = ¥0.028.
Use the catalog rates for your exact model, not the example rates. For cached input use the applicable cache rate; for models billed per call, use the per-call price instead.
Try a Chinese model with the Python SDK · Configure OpenCode
Model pricing and integration guides
GPT-5.6 Sol API
Compare GPT-5.6 Sol live API prices, gateway rates and documented 1M context for coding, documents and image understanding.
Grok 4.6 API
Check Grok 4.6 live gateway API prices, token rates, documented 500K context and image input for coding and agent tasks.
Grok 4.7 API
Review Grok 4.7's published 6x rate and coding-agent integration guidance; the reference lists 500K context and image support.
Claude Sonnet 5.5 API
Review Claude Sonnet 5.5's 10x rate, documented 1M context, image support, and coding-agent integration.
Claude Opus 5.5 API
Review Claude Opus 5.5's published 15x rate, documented 1M context, image understanding, and complex-agent integration guidance.
Qwen 3.8 Max API
Review Qwen 3.8 Max gateway prices, documented 1M context and image support for complex coding and agent workflows.
MiniMax M3.1 Flash API
Review MiniMax M3.1 Flash's published 1x rate, 1M context, and image support.
MiniMax M3.1 API
Review MiniMax M3.1's published 2x rate, 1M context, and image support.
Jev(latest) API
Review Jev System One decision routing, documented 64K context, Choice/Score/Noul questions, and API integration boundaries.
LongCat 2.0 API
Review LongCat 2.0's published 2x rate, 1M context, and text-agent integration guidance.
LongCat 2.5 API
Review LongCat 2.5's 1M context, native vision and long-horizon agent integration; the 2x reference and live billing are listed separately.
MiMo V2.6 Pro API
Review MiMo V2.6 Pro's published 4x rate, 1M context, and image-understanding integration guidance.
MiMo V2.6 Flash API
Review MiMo V2.6 Flash's published 2x rate, 1M context, image understanding, and high-throughput integration guidance.
Kimi K3.1 Pro API
Review Kimi K3.1 Pro gateway pricing at 15x, documented 1M context and image support for coding and long-running agents.
Kimi K2.8 API
Explore Kimi K2.8 gateway pricing at 6x, documented 1M context and image support for coding and agent workflows.
GPT-6 Astra API
Check GPT-6 Astra gateway API rates, live pricing and documented 1M context for complex reasoning, coding and long-running agents.
DeepSeek V4.1 Flash 1017 API
Explore DeepSeek V4.1 Flash 1017, released October 17, 2026, for coding agents, documented 1M context and multimodal integration. The gateway ID remains deepseek-v4.1-flash.
GPT-6.1 Sol API
Review GPT-6.1 Sol's published 3x rate, 1.05M context, and coding-agent integration guidance.
GPT-6.1 Terra API
Review GPT-6.1 Terra API pricing at 2x, image understanding and Responses API requirements for visual reasoning, computer use and writing.
Gemini 3.8 Flash API
Review Gemini 3.8 Flash's 5x reference rate, documented 1M context and image support for frequent coding and agent tasks.
Gemini 4 Argon API
Review Gemini 4 Argon's 5x reference pricing and documented multimodal capabilities for complex code, long documents and research tasks.