Skip to main content

​
Overview

Text models support chat completions, language understanding, and text generation tasks. All models are accessible through our unified API.

​
Anthropic

Inputs: Text
Use Cases: General-purpose language tasks, content generation, conversation Claude Sonnet 4
  • Model ID: anthropic/claude-sonnet-4
  • Overview: Balanced, high-accuracy reasoning and coding; great for complex agents and long-form generation.
  • Context Length: 128K tokens
  • Pricing: Input $3 per 1M tokens; Output $15 per 1M tokens
  • Status: Active
Claude Sonnet 4.5
  • Model ID: anthropic/claude-sonnet-4.5
  • Overview: Latest Claude for top-tier reasoning and code; excels at tool use and instruction following.
  • Context Length: 128K tokens
  • Pricing: Input $3 per 1M tokens; Output $15 per 1M tokens
  • Status: Active
Claude Haiku 4.5
  • Model ID: anthropic/claude-haiku-4.5
  • Overview: Fast, budget-friendly Claude; ideal for high-throughput chat, classification, and lightweight RAG.
  • Context Length: 128K tokens
  • Pricing: Input $0.40 per 1M tokens; Output $1.60 per 1M tokens
  • Status: Active

​
Google

Inputs: Text
Use Cases: General-purpose language tasks, content generation, conversation Gemini 2.5 Pro
  • Model ID: google/gemini-2.5-pro
  • Overview: Strong analytical and coding capabilities with long context; great for complex reasoning and math.
  • Context Length: 128K tokens
  • Pricing: Input $1.25 per 1M tokens; Output $10 per 1M tokens
  • Status: Active
Gemini 2.5 Flash
  • Model ID: google/gemini-2.5-flash
  • Overview: Low-latency, cost-efficient Gemini; ideal for assistants, drafts, and autocomplete.
  • Context Length: 128K tokens
  • Pricing: Input $0.30 per 1M tokens; Output $2.50 per 1M tokens
  • Status: Active
Gemini 2.5 Flash Lite
  • Model ID: google/gemini-2.5-flash-lite
  • Overview: Ultra-low-cost variant for simple tasks at massive scale.
  • Context Length: 128K tokens
  • Pricing: Input $0.30 per 1M tokens; Output $2.50 per 1M tokens
  • Status: Active
Gemini 2.0 Flash
  • Model ID: google/gemini-2.0-flash
  • Overview: Fast general-purpose text model; good for summarization and interactive assistants.
  • Context Length: 128K tokens
  • Pricing: Input $0.30 per 1M tokens; Output $2.50 per 1M tokens
  • Status: Active

​
OpenAI

Inputs: Text
Use Cases: General-purpose language tasks, content generation, conversation GPT-5
  • Model ID: openai/gpt-5
  • Overview: General-purpose frontier model; best for complex reasoning, coding, and agent workflows.
  • Context Length: 128K tokens
  • Pricing: Input $3 per 1M tokens; Output $15 per 1M tokens
  • Status: Active
GPT-5 Mini
  • Model ID: openai/gpt-5-mini
  • Overview: Lightweight, low-latency GPT; great for fast chat, routing, and control flows.
  • Context Length: 128K tokens
  • Pricing: Input $0.40 per 1M tokens; Output $1.60 per 1M tokens
  • Status: Active
GPT-4.1 Mini
  • Model ID: openai/gpt-4.1-mini
  • Overview: Balanced quality and cost; strong at instruction following and structured outputs.
  • Context Length: 128K tokens
  • Pricing: Input $0.40 per 1M tokens; Output $1.60 per 1M tokens
  • Status: Active
GPT-4o Mini
  • Model ID: openai/gpt-4o-mini
  • Overview: Optimized for low latency; ideal for interactive assistants and streaming responses.
  • Context Length: 128K tokens
  • Pricing: Input $0.40 per 1M tokens; Output $1.60 per 1M tokens
  • Status: Active
GPT-OSS 120B
  • Model ID: openai/gpt-oss-120b
  • Overview: Large-capacity model for research and batch generation; good for long-form text.
  • Context Length: 128K tokens
  • Pricing: Input $0.08 per 1M tokens; Output $0.30 per 1M tokens
  • Status: Active

​
Meta

Inputs: Text
Use Cases: General-purpose language tasks, content generation, conversation Llama 4 Scout
  • Model ID: moonshotai/kimi-k2-0905
  • Overview: Open and efficient; strong for coding, multilingual tasks, and retrieval-augmented workflows.
  • Context Length: 128K tokens
  • Pricing: Input 0.08per1Mtokens;Output0.08 per 1M tokens; Output 0.30 per 1M tokens
  • Status: Active

​
Qwen

Inputs: Text
Use Cases: General-purpose language tasks, content generation, conversation Qwen3 235B
  • Model ID: qwen/qwen3-235b-a22b-2507
  • Overview: Multilingual, long-context (262K) model; excels at math, coding, and tool use.
  • Context Length: 262K tokens
  • Pricing: Input $0.08 per 1M tokens; Output $0.55 per 1M tokens
  • Status: Active

​
Moonshot AI

Inputs: Text
Use Cases: General-purpose language tasks, content generation, conversation Kimi K2
  • Model ID: moonshotai/kimi-k2-0905
  • Overview: Agentic model optimized for planning and tool use; strong long-context summarization.
  • Context Length: 128K tokens
  • Pricing: Input $0.39 per 1M tokens; Output $1.90 per 1M tokens
  • Status: Active

​
DeepSeek

Inputs: Text
Use Cases: General-purpose language tasks, content generation, conversation DeepSeek V3.1
  • Model ID: deepseek/deepseek-v3.1
  • Overview: Reasoning-focused model; great for quantitative analysis, coding, and stepwise problem solving.
  • Context Length: 128K tokens
  • Pricing: Input $0.20 per 1M tokens; Output $1.50 per 1M tokens
  • Status: Active
DeepSeek V3
  • Model ID: deepseek/deepseek-v3-0324
  • Overview: General-purpose DeepSeek; strong in code generation and math with fast responses.
  • Context Length: 128K tokens
  • Pricing: Input $0.20 per 1M tokens; Output $1.50 per 1M tokens
  • Status: Active
DeepSeek R1T2 Chimera
  • Model ID: deepseek/deepseek-r1t2-chimera
  • Overview: Reasoning + tool-use hybrid; ideal for agent loops, planning, and complex tasks.
  • Context Length: 128K tokens
  • Pricing: Input $0.20 per 1M tokens; Output $1.50 per 1M tokens
  • Status: Active

​
xAI

Inputs: Text
Use Cases: General-purpose language tasks, content generation, conversation Grok Code Fast 1
  • Model ID: x-ai/grok-code-fast-1
  • Overview: Fast, economical code generation and editing; excels in agentic coding workflows.
  • Context Length: 128K tokens
  • Pricing: Input $0.20 per 1M tokens; Output $1.50 per 1M tokens
  • Status: Active
Grok 4 Fast
  • Model ID: x-ai/grok-4-fast
  • Overview: High-speed general reasoning; good for chat, analysis, and routing.
  • Context Length: 128K tokens
  • Pricing: Input $0.20 per 1M tokens; Output $1.50 per 1M tokens
  • Status: Active

​
z-ai (GLM)

Inputs: Text
Use Cases: General-purpose language tasks, content generation, conversation GLM-4.6
  • Model ID: z-ai/glm-4.6
  • Overview: Multilingual general-purpose model; strong for Chinese-English tasks and Q&A.
  • Context Length: 128K tokens
  • Pricing: Input $0.08 per 1M tokens; Output $0.30 per 1M tokens
  • Status: Active

​
Listing Text Models

Get a complete list of all available text models via API: 
curl "https://api.compilelabs.com/v1/models?type=text_to_text" \
  -H "Authorization: Bearer YOUR_API_KEY"

​
Model Status

  • Active: Currently available for use
  • Pending: Under review / not yet available

​
Next Steps

Chat Completions (OpenAI)

Start using text models with OpenAI SDK

Image Models

Browse image generation models

Providers

Learn about our AI providers