Best for Coding
DeepSeek V3
$0.27/$1.10 per 1M tokens
Best value for daily coding
Claude Sonnet 4.5
$3/$15 per 1M tokens
Best quality for complex code
Live pricing for Claude, GPT, Gemini, DeepSeek, Llama, Mistral and 100+ AI models. All accessible through one SkillBoss API key with zero markup.
All prices per 1 million tokens. SkillBoss passes through provider pricing with zero markup.
| Model | Provider | Input /1M | Output /1M | Context | Tier | Best For |
|---|---|---|---|---|---|---|
| Claude Opus 4 | Anthropic | $15.00 | $75.00 | 200K | Frontier | Complex reasoning, research |
| GPT-4.1 | OpenAI | $2.00 | $8.00 | 1M | Frontier | Large context tasks |
| Claude Sonnet 4.5 | Anthropic | $3.00 | $15.00 | 200K | Premium | Coding, analysis |
| GPT-4o | OpenAI | $2.50 | $10.00 | 128K | Premium | General purpose |
| Gemini 2.5 Pro | $1.25 | $10.00 | 1M | Premium | Long context, multimodal | |
| Claude Haiku 3.5 | Anthropic | $0.80 | $4.00 | 200K | Mid-Tier | Fast tasks, chat |
| GPT-4o mini | OpenAI | $0.15 | $0.60 | 128K | Mid-Tier | Light tasks, classification |
| Gemini 2.5 Flash | $0.075 | $0.30 | 1M | Mid-Tier | Speed, cost efficiency | |
| Llama 4 Scout | Meta | $0.15 | $0.60 | 128K | Mid-Tier | Open source, privacy |
| DeepSeek V3 | DeepSeek | $0.27 | $1.10 | 128K | Budget | Best value coding |
| DeepSeek R1 | DeepSeek | $0.55 | $2.19 | 128K | Budget | Reasoning on a budget |
| Mistral Small | Mistral | $0.10 | $0.30 | 128K | Budget | European compliance |
Prices as of April 2026. Check model catalog for real-time pricing.
What does 1 million tokens look like? Roughly 750,000 words or 1,500 pages of text.
~50K tokens/day (prompts + completions)
~500K tokens/day (1,000 conversations)
SkillBoss provides an OpenAI-compatible API. Switch models by changing the model name — no new API keys needed.
api.skillboss.co/v1
Switch between 100+ models instantly.
curl https://api.skillboss.co/v1/chat/completions \
-H "Authorization: Bearer $SKILLBOSS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-chat",
"messages": [{"role": "user", "content": "Hello!"}]
}'| Feature | SkillBoss | OpenRouter | Direct APIs |
|---|---|---|---|
| Pricing | Zero markup | Zero markup | Provider pricing |
| LLM Models | 100+ models | 200+ models | 1 provider each |
| Non-LLM APIs | 50+ (image, video, scraping, email) | None | None |
| API Keys Needed | 1 | 1 | 1 per provider |
| OpenAI Compatible | Yes | Yes | Varies |
| Works with Cursor/Claude Code | Yes | Yes | Only OpenAI |
| Billing | Pay-as-you-go USD wallet | Credits | Per-provider billing |
DeepSeek V3 is the cheapest high-quality LLM API at $0.27 per million input tokens and $1.10 per million output tokens. For even lower costs, Gemini 2.5 Flash offers $0.075/$0.30 per million tokens. Access both through SkillBoss with zero markup at api.skillboss.co/v1.
LLM APIs charge per token (roughly 4 characters = 1 token). Pricing is split into input tokens (your prompt) and output tokens (the response). Costs are quoted per million tokens. For example, Claude Sonnet costs $3/M input and $15/M output tokens.
SkillBoss passes through provider pricing with zero markup, same as OpenRouter. The key difference: SkillBoss includes 100+ non-LLM APIs (image generation, video, scraping, email, search) alongside LLMs — all through one API key. OpenRouter is LLM-only.
Yes. SkillBoss provides a single OpenAI-compatible API key that works with Claude, GPT, Gemini, DeepSeek, Llama, Mistral, and 100+ other models. Set base_url to api.skillboss.co/v1 in Claude Code, Cursor, Windsurf, or any OpenAI-compatible client.
SkillBoss offers free credits on signup so you can test any model before committing. DeepSeek and Gemini Flash are the most cost-effective options for production use, costing less than $1 per million tokens.
LLM API pricing is calculated per token, where one token is roughly 4 characters or 0.75 words. Providers charge separately for input tokens (your prompt) and output tokens (the response), quoted per million tokens. For example, GPT-4o costs $2.50 per million input tokens and $10 per million output tokens. SkillBoss shows all prices transparently with zero markup.
Gemini 2.5 Flash is the cheapest high-quality LLM at $0.075 per million input tokens and $0.30 per million output tokens. DeepSeek V3 offers the best value for coding at $0.27/$1.10 per million tokens. Both are available through SkillBoss with zero markup.
No. SkillBoss passes through provider pricing with zero markup — you pay the exact same per-token rate as going directly to each provider. The difference is you get one API key for 100+ models instead of managing separate accounts with each provider.
Zero markup. Pay-as-you-go. Works with Claude Code, Cursor, Windsurf.
AI Agents
Tell your agent:
set up skillboss.co/skill.mdAuto-configures base URL, auth, and model access. Works with Claude Code, Cursor, Windsurf, and any MCP-compatible agent.
Developers
1. Get API key at skillboss.co/console
2. POST to api.skillboss.co/v1/run
3. Pick a model from 600+ APIs
Pay-as-you-go. $2 free credit. No subscription required.