BlogTagged
Posts tagged “Text models”
Guides, pricing breakdowns and engineering notes on image generation APIs: Nano Banana, Qwen-Image, Seedream and Wan compared by price per image.
7 min readgenmux API Team
Function calling on DeepSeek, Qwen and Doubao, emulated
How genmux gives OpenAI-style tools to DeepSeek, Qwen3 and Doubao when the upstream drops the tools field: prompt tags, tolerant parser, pass rates, JSON mode.
4 min readgenmux API Team
Thinking models: when to enable reasoning and what it costs
How enable_thinking works across genmux's chat models, why reasoning tokens are billed as output, and a worked example of what that does to your bill.
4 min readgenmux API Team
Streaming chat completions over SSE, cost in the last chunk
Parse genmux's server-sent event stream for chat completions in Python and Node, find the usage object in the final chunk, and handle mid-stream aborts.
3 min readgenmux API Team
Qwen3 API pricing per 1M tokens: 7-Max, Max, Flash
Live Qwen3 lineup on one API key: 7-Max, Max, 3.6-Flash prices per 1M tokens, context, and which model fits which job. Plus/Coder return once fixed upstream.
6 min readgenmux API Team
OpenCode with DeepSeek V4 through one genmux key
Point OpenCode at genmux with one opencode.json block, pick DeepSeek V4 Flash or Pro, see what tool calling looks like, and what a real agent session costs.
5 min readgenmux API Team
Use the OpenAI SDK with DeepSeek, Qwen and GLM: one base_url
How genmux serves DeepSeek, Qwen3 and Doubao via the OpenAI-compatible chat.completions schema: supported fields, tools, JSON mode, rejections, error codes.
4 min readgenmux API Team
LLM API prices per 1M tokens in 2026: 10 models vs list
The 10 live genmux chat models in one table: price per 1M tokens in credits and USD, context, thinking support, and how each compares to the vendor list price.
2 min readgenmux API Team
Doubao Seed 2.0 API without a Volcengine account
Call Doubao Seed 2.0 (Pro, Code, Lite, Mini) through one genmux API key, with web_search on Pro and pricing above Volcengine list. Kimi K3 is paused.
4 min readgenmux API Team
DeepSeek V4 API without a DeepSeek account: pay per token
Call DeepSeek V4 Pro, V4 Flash and V3 through one genmux API key, billed per token from a prepaid balance, with curl and Python examples and real prices.
5 min readgenmux API Team
Continue (IDE and cn CLI) on genmux: config.yaml and tools
Continue in VS Code, JetBrains and the cn CLI on DeepSeek V4 and Qwen3 through genmux: config.yaml, capabilities tool_use, chat/edit/apply roles, headless runs.
5 min readgenmux API Team
Cline and Roo Code with an OpenAI-compatible provider
Cline and Roo Code in VS Code with genmux as the OpenAI-compatible provider: the exact fields, which DeepSeek, Qwen3 and Doubao models to pick, vision, limits.
5 min readgenmux API Team
Aider with Qwen3-Max and DeepSeek: OPENAI_API_BASE and done
Run aider on Qwen3-Max or DeepSeek V4 through genmux: two environment variables, the openai/ model prefix, edit formats, and what a 200K-token session costs.