Showing 18 groups
LLM
Text Generation
GLM-5.2
Zhipu GLM-5.2 — a next-gen bilingual (Chinese/English) LLM for general chat, code generation, and agentic tasks, strong in Chinese-language contexts
Input
Output
Input
3,750 credits/1M
≈ $1.88-$3.75
Output
12,500 credits/1M
≈ $6.25-$12.5
Cache
750 credits/1M
≈ $0.375-$0.75
LLM
Text Generation
Gemini 3.5 Flash
Google Gemini 3.5 Flash — a fast, cost-efficient multimodal chat model with image+text input and a million-token context window, for high-concurrency workloads
Input
Output
Input
1,875 credits/1M
≈ $0.938-$1.88
Output
12,500 credits/1M
≈ $6.25-$12.5
Cache
187.5 credits/1M
≈ $0.0938-$0.188
LLM
Text Generation
MiniMax M3
MiniMax M3 — a large language model with a million-token context window, excelling at long-document understanding, complex reasoning, and tool use
Input
Output
Input
2,400 credits/1M
≈ $1.2-$2.4
Output
10,000 credits/1M
≈ $5-$10
Cache
3,000 credits/1M
≈ $1.5-$3
LLM
Text Generation2 models
DeepSeek V4
DeepSeek V4 — a reasoning-focused LLM with a 128K-token context window, excelling at code generation and complex logic at a highly competitive price
Input
Output
Input
425 credits/1M
≈ $0.212-$0.425
Output
950 credits/1M
≈ $0.475-$0.95
Cache
50 credits/1M
≈ $0.025-$0.05
LLM
Text Generation
GPT 5.5
OpenAI GPT-5.5 — a flagship model for complex reasoning, code generation, and multi-step instructions, with a 400K-token context window for demanding apps
Input
Output
Input
8,500 credits/1M
≈ $4.25-$8.5
Output
50,000 credits/1M
≈ $25-$50
Cache
850 credits/1M
≈ $0.425-$0.85
LLM
Text Generation2 models
GPT 5.6
OpenAI GPT-5.6 — a flagship model for complex reasoning, code generation, and multi-step instructions, with a 400K-token context window for demanding apps
Input
Output
Input
12,000 credits/1M
≈ $6-$12
Output
80,000 credits/1M
≈ $40-$80
Cache
1,700 credits/1M
≈ $0.85-$1.7
G
LLM
Text Generation
GPT 6
OpenAI GPT-6 — a flagship model for complex reasoning, code generation, and multi-step instructions, with a 400K-token context window for demanding apps
Input
Output
Input
7,000 credits/1M
≈ $3.5-$7
Output
60,000 credits/1M
≈ $30-$60
Cache
1,062.47 credits/1M
≈ $0.531-$1.06
LLM
Text Generation2 models
Grok 4.5
Grok 4.5 is an advanced AI model designed to deliver fast, writing, coding, research, data analysis, and creative problem-solving through natural conversation
Input
Output
Input
1,200 credits/1M
≈ $0.6-$1.2
Output
2,400 credits/1M
≈ $1.2-$2.4
Cache
1,200 credits/1M
≈ $0.6-$1.2
G
LLM
Text Generation
Grok 4.6
Grok 4.6 is an advanced AI model designed to deliver fast, writing, coding, research, data analysis, and creative problem-solving through natural conversation
Input
Output
Input
1,200 credits/1M
≈ $0.6-$1.2
Output
2,400 credits/1M
≈ $1.2-$2.4
Cache
1,200 credits/1M
≈ $0.6-$1.2
LLM
Text Generation
Kimi K3
A premium reasoning route for visual front-end prototyping, repository-scale coding, large evidence sets, long-running agents, and complex knowledge work that benefits from a 1.05M-token working context.
Input
Output
Input
4,000 credits/1M
≈ $2-$4
Output
20,000 credits/1M
≈ $10-$20
Cache
400 credits/1M
≈ $0.2-$0.4
LLM
Text Generation
Gemini 2.5 Flash Lite
Google Gemini 2.5 Flash Lite — an ultra-low-cost, low-latency chat model with a million-token context window, ideal for high-frequency everyday tasks
Input
Output
Input
200 credits/1M
≈ $0.1-$0.2
Output
300 credits/1M
≈ $0.15-$0.3
Cache
20 credits/1M
≈ $0.01-$0.02
LLM
Text Generation
Gemini 3.1 Flash Lite
Google Gemini 3.1 Flash Lite — improved reasoning over the 2.5 generation while staying economical, balancing speed and quality for lightweight tasks
Input
Output
Input
300 credits/1M
≈ $0.15-$0.3
Output
2,000 credits/1M
≈ $1-$2
Cache
25 credits/1M
≈ $0.0125-$0.025
LLM
Text Generation
Gemini 3.1 Pro
Google Gemini 3.1 Pro — the flagship multimodal Gemini model, offering strong complex reasoning and long-context capability for demanding production apps
Input
Output
Input
2,500 credits/1M
≈ $1.25-$2.5
Output
15,000 credits/1M
≈ $7.5-$15
Cache
1,250 credits/1M
≈ $0.625-$1.25
LLM
Text Generation
GPT 4o Mini
OpenAI GPT-4o mini — a fast, affordable multimodal chat model with quick responses and low cost, ideal for everyday Q&A and lightweight coding help
Input
Output
Input
550 credits/1M
≈ $0.275-$0.55
Output
825 credits/1M
≈ $0.412-$0.825
Cache
27.5 credits/1M
≈ $0.0138-$0.0275
LLM
Text Generation3 models
GPT 5.4
OpenAI GPT-5.4 — a high-capability model for advanced reasoning, code generation, and agentic workflows, with a 400K-token context window for production use
Input
Output
Input
5,000 credits/1M
≈ $2.5-$5
Output
30,000 credits/1M
≈ $15-$30
Cache
500 credits/1M
≈ $0.25-$0.5
LLM
Text Generation
Claude Opus 4.8
Anthropic Claude Opus 4.8 — the flagship Claude model for the most demanding reasoning, coding, and long-form writing tasks, with excellent long context
Input
Output
Input
5,000 credits/1M
≈ $2.5-$5
Output
24,000 credits/1M
≈ $12-$24
Cache
500 credits/1M
≈ $0.25-$0.5
LLM
Text Generation
Claude Opus 5
Anthropic Claude Opus 5 from APIAny — Anthropic’s newest Opus-tier flagship for the hardest coding, long-running agents, and judgment-heavy review.
Input
Output
Input
7,500 credits/1M
≈ $3.75-$7.5
Output
37,500 credits/1M
≈ $18.75-$37.5
Cache
750 credits/1M
≈ $0.375-$0.75
LLM
Text Generation
Claude Sonnet 4.6
Anthropic Claude Sonnet 4.6 — a balanced flagship model delivering strong reasoning at production speed and cost, for large-scale, stable deployment
Input
Output
Input
3,000 credits/1M
≈ $1.5-$3
Output
15,000 credits/1M
≈ $7.5-$15
Cache
2,000 credits/1M
≈ $1-$2
What text generation models does APIAny expose?
APIAny lists public chat and text models on one OpenAI-compatible endpoint, with live credit prices on each model page.
By APIAny Editorial · Updated
How do you find the right APIAny model?
Filter by type or provider, compare credit prices, then open a model page for playground tests and request examples.
Which models are in this view?
- GLM-5.2Zhipu GLM-5.2 — a next-gen bilingual (Chinese/English) LLM for general chat, code generation, and agentic tasks, strong in Chinese-language contexts
- Gemini 3.5 FlashGoogle Gemini 3.5 Flash — a fast, cost-efficient multimodal chat model with image+text input and a million-token context window, for high-concurrency workloads
- MiniMax M3MiniMax M3 — a large language model with a million-token context window, excelling at long-document understanding, complex reasoning, and tool use
- DeepSeek V4DeepSeek V4 — a reasoning-focused LLM with a 128K-token context window, excelling at code generation and complex logic at a highly competitive price
- GPT 5.5OpenAI GPT-5.5 — a flagship model for complex reasoning, code generation, and multi-step instructions, with a 400K-token context window for demanding apps
- GPT 5.6OpenAI GPT-5.6 — a flagship model for complex reasoning, code generation, and multi-step instructions, with a 400K-token context window for demanding apps
- GPT 6OpenAI GPT-6 — a flagship model for complex reasoning, code generation, and multi-step instructions, with a 400K-token context window for demanding apps
- Grok 4.5Grok 4.5 is an advanced AI model designed to deliver fast, writing, coding, research, data analysis, and creative problem-solving through natural conversation
- Grok 4.6Grok 4.6 is an advanced AI model designed to deliver fast, writing, coding, research, data analysis, and creative problem-solving through natural conversation
- Kimi K3A premium reasoning route for visual front-end prototyping, repository-scale coding, large evidence sets, long-running agents, and complex knowledge work that benefits from a 1.05M-token working context.
- Gemini 2.5 Flash LiteGoogle Gemini 2.5 Flash Lite — an ultra-low-cost, low-latency chat model with a million-token context window, ideal for high-frequency everyday tasks
- Gemini 3.1 Flash LiteGoogle Gemini 3.1 Flash Lite — improved reasoning over the 2.5 generation while staying economical, balancing speed and quality for lightweight tasks
- Gemini 3.1 ProGoogle Gemini 3.1 Pro — the flagship multimodal Gemini model, offering strong complex reasoning and long-context capability for demanding production apps
- GPT 4o MiniOpenAI GPT-4o mini — a fast, affordable multimodal chat model with quick responses and low cost, ideal for everyday Q&A and lightweight coding help
- GPT 5.4OpenAI GPT-5.4 — a high-capability model for advanced reasoning, code generation, and agentic workflows, with a 400K-token context window for production use
- Claude Opus 4.8Anthropic Claude Opus 4.8 — the flagship Claude model for the most demanding reasoning, coding, and long-form writing tasks, with excellent long context
- Claude Opus 5Anthropic Claude Opus 5 from APIAny — Anthropic’s newest Opus-tier flagship for the hardest coding, long-running agents, and judgment-heavy review.
- Claude Sonnet 4.6Anthropic Claude Sonnet 4.6 — a balanced flagship model delivering strong reasoning at production speed and cost, for large-scale, stable deployment
Sources
Which official references does this page cite?
The quotations below are from official API documentation that APIAny implements against.
The Chat Completions API endpoint will generate a model response from a list of messages comprising a conversation.
The Gemini API provides access to Google's most capable generative AI models.
The Images API provides several endpoints that let you generate images from text prompts or create edits of existing images.
What AI models does APIAny expose?
The APIAny models catalog is the live list of public chat, image, video, audio, and safety models you can call with one API key.