No credit card required · $1 credit at sign-up
59 models · 7 makers · all 15% off
ApiFlux prices are shown in USD per 1M tokens, including reviewed cache rates where available.
glm-5.3
Z.ai's large-scale GLM reasoning model for complex software engineering and long-horizon agent tasks, with improved coding and token efficiency over GLM 5.2.
Providers
1 channelgemini-3.7-flash
A multimodal Gemini Flash model for fast agentic workflows, coding, and complex multi-step reasoning.
Providers
2 channelsqwen3.8-max
Alibaba's flagship 2.4-trillion-parameter Qwen mixture-of-experts model with a 1M-token context, multimodal input, and controllable reasoning.
Providers
1 channelclaude-opus-5
Anthropic's flagship Opus model for demanding reasoning, coding, and long-horizon agentic work.
Providers
3 channelsgemini-3.5-flash-lite
A high-efficiency Gemini model with upgraded agentic capabilities, suited for focused subagent tasks in multi-agent workflows.
Providers
2 channelskimi-k3
Kimi K3 is Moonshot AI's open-weight flagship model for complex coding, knowledge work, and long-horizon agentic workflows.
Providers
1 channelgpt-5.6-sol
The flagship GPT-5.6 model for complex reasoning, coding, and long-running agentic workflows.
Providers
2 channelsgpt-5.6-luna
A fast, cost-efficient GPT-5.6 model for chat, classification, and lightweight agentic workflows.
Providers
2 channelsgpt-5.6-terra
A balanced GPT-5.6 model for everyday coding, reasoning, and agentic tasks.
Providers
2 channelsclaude-sonnet-5
Anthropic's frontier Sonnet model for coding, agents, and professional knowledge work.
Providers
1 channelglm-5.2
A large-scale GLM reasoning model for long-horizon agents, software engineering, and tool use.
Providers
1 channelkimi-k2.7-code
A coding-focused Kimi model built for reliable end-to-end programming tasks over long contexts.
Providers
1 channelclaude-fable-5
An Anthropic model designed for autonomous knowledge work and end-to-end coding tasks.
Providers
1 channelqwen3.7-plus
A cost-effective Qwen3.7 model for general-purpose, coding, and agentic workloads.
Providers
1 channelclaude-opus-4.8
Anthropic's most capable generally available Opus model for demanding professional and agentic work.
Providers
3 channelsqwen3.7-max
Alibaba's flagship Qwen3.7 model for coding, productivity, and agent-centric workloads.
Providers
1 channelgemini-3.5-flash
A high-efficiency Gemini model that targets strong coding and reasoning at Flash-tier speed and cost.
Providers
2 channelsgemini-3.1-flash-lite
Google's high-efficiency Gemini model for low-latency, high-volume workloads and lightweight agents.
Providers
2 channelsqwen3.6-35b-a3b
An open-weight Qwen mixture-of-experts model designed for efficient multimodal reasoning.
Providers
1 channelqwen3.6-27b
A dense 27-billion-parameter Qwen model for general-purpose and multimodal tasks.
Providers
1 channelgpt-5.5
OpenAI's frontier model for complex professional workloads, with an emphasis on reliability and token efficiency.
Providers
2 channelsdeepseek-v4-flash
An efficiency-focused DeepSeek mixture-of-experts model for fast inference and long-context work.
Providers
1 channeldeepseek-v4-pro
A large-scale DeepSeek mixture-of-experts model for advanced reasoning, coding, and agent workflows.
Providers
1 channelkimi-k2.6
A Kimi model designed for long-horizon coding, interface generation, and multi-agent orchestration.
Providers
1 channelclaude-opus-4.7
An Opus model built for long-running, asynchronous agents and complex coding workflows.
Providers
3 channelsglm-5.1
A GLM model focused on stronger coding performance and sustained long-horizon execution.
Providers
1 channelqwen3.6-plus
A scalable Qwen model combining efficient attention with sparse expert routing for high-performance inference.
Providers
1 channelgpt-5.4-mini
An efficient GPT-5.4 model optimized for high-throughput reasoning, coding, and agent workloads.
Providers
2 channelsgpt-5.4-nano
The lightest GPT-5.4 variant, optimized for speed-critical, high-volume tasks.
Providers
2 channelsgpt-5.4
OpenAI's frontier model combining general-purpose reasoning with advanced coding and agent capabilities.
Providers
2 channelsqwen3.5-flash
An efficient Qwen Flash model combining linear attention with sparse mixture-of-experts routing.
Providers
1 channelgemini-3.1-pro-preview
Google's frontier Gemini reasoning model for complex software engineering and agentic workflows.
Providers
2 channelsclaude-sonnet-4.6
A high-capability Sonnet model for iterative development, complex codebases, and professional workflows.
Providers
2 channelsglm-5
Z.ai's flagship open GLM model for complex systems design and long-horizon agent workflows.
Providers
1 channelclaude-opus-4.6
An Opus model designed for advanced coding and long-running professional workflows.
Providers
3 channelskimi-k2.5
A Kimi model focused on visual coding and coordinated agent workflows.
Providers
1 channelglm-4.7-flash
An efficient GLM model balancing coding performance, long-horizon planning, and inference cost.
Providers
1 channelglm-4.7
A flagship GLM model with improved programming and more stable multi-step reasoning.
Providers
1 channelgemini-3-flash-preview
A high-speed Gemini reasoning model for agentic workflows, multi-turn chat, and coding assistance.
Providers
2 channelsgpt-5.2
A frontier GPT-5 model focused on stronger agentic execution and long-context performance.
Providers
2 channelsdeepseek-v3.2
A DeepSeek model balancing computational efficiency with reasoning and agentic tool use.
Providers
1 channelclaude-opus-4.5
Anthropic's Opus 4.5 frontier model for complex software engineering, agents, and long-horizon computer use.
Providers
3 channelskimi-k2-thinking
An open Kimi reasoning model designed for agentic, long-horizon problem solving.
Providers
1 channelclaude-haiku-4.5
Anthropic's fast, efficient Haiku model for responsive applications and high-volume workloads.
Providers
3 channelsglm-4.6
A long-context GLM model designed to handle more complex reasoning and coding workloads.
Providers
1 channelclaude-sonnet-4.5
Anthropic's Sonnet 4.5 model optimized for real-world agents and coding workflows.
Providers
2 channelsqwen3-next-80b-a3b-instruct
An instruction-tuned Qwen chat model optimized for fast, stable responses across reasoning, coding, and multilingual tasks.
Providers
1 channelkimi-k2-0905
The September update to Kimi K2, a mixture-of-experts model built for agentic intelligence.
Providers
1 channeldeepseek-v3.1
A hybrid DeepSeek reasoning model that supports both thinking and direct-response modes.
Providers
1 channelgpt-5
OpenAI's advanced GPT-5 model for complex reasoning, coding, and instruction-following workloads.
Providers
2 channelsgpt-5-mini
A compact GPT-5 model for lighter-weight reasoning with lower latency and cost.
Providers
2 channelsgemini-2.5-flash-lite
A lightweight Gemini reasoning model optimized for low latency, high throughput, and cost efficiency.
Providers
2 channelsqwen3-235b-a22b-instruct-2507
A multilingual Qwen mixture-of-experts model tuned for instruction following and text generation.
Providers
1 channelgemini-2.5-flash
Google's workhorse Gemini model for advanced reasoning, coding, mathematics, and scientific tasks.
Providers
2 channelsgemini-2.5-pro
A high-capability Gemini model for advanced reasoning, coding, mathematics, and scientific work.
Providers
2 channelsr1-0528
A May 2025 update to DeepSeek R1 focused on open reasoning and complex problem solving.
Providers
1 channeldeepseek-v3-0324
A March 2025 update to DeepSeek's flagship mixture-of-experts chat model.
Providers
1 channelgpt-4o-mini
A compact GPT-4o model designed for fast, affordable general-purpose and multimodal tasks.
Providers
2 channelsgpt-4o
OpenAI's versatile, high-intelligence flagship model for general-purpose text and vision tasks.
Providers
2 channels
