LLM Prices

LLM Prices

2,200+ models. Real costs. No BS.

OpenCode Go — $10/mo

$60 of usage included. Real multiplier depends on model.

ModelRequests/moValueMultiplierCost/ReqContextBest For
Muse Spark 1.2226,600$787.8x$0.00031MVolume tasks
MiMo-V2.5150,400$606.0x$0.00041MBulk coding, agents
DeepSeek V4 Flash37,800$222.2x$0.00061MFast inference
Qwen3.7 Plus21,600$222.2x$0.0010256KGeneral coding
Hy321,500$101.0x$0.00051MReasoning
MiniMax M316,000$131.3x$0.00081MGeneral
Kimi K2.7 Code6,750$151.5x$0.0022128KCode generation
GPT 5.6 Luna10,250$70.7x$0.0007272KQuality code
DeepSeek V4 Pro5,200$70.7x$0.00131MPro reasoning
Grok 4.5600$20.2x$0.0036500KFrontier reasoning

Cheapest API Models

Pay-per-token. Blended = input + 3×output per 1M tokens.

ModelProviderBlended/1MInput/1MOutput/1MContext
Llama 3.3 70BGroqFREE$0$0128K
Llama 3.1 8BCerebrasFREE$0$08K
Gemini 2.5 FlashGoogleFREE$0$01M
DeepSeek V3.2DeepSeek$3.58$0.28$1.10128K
Llama 3.3 70BTogether AI$3.52$0.88$0.88128K
DeepSeek R1OpenRouter$7.12$0.55$2.19128K
Claude Opus 4.6Anthropic$80.00$5.00$25.00200K
GPT 5.5OpenAI$32.50$2.50$10.00128K

Free Tiers

No credit card. Rate limits apply.

ProviderModelContextRate Limit
GroqLlama 3.3 70B128K30 RPM
CerebrasLlama 3.1 8B8K30 RPM
Google GeminiGemini 2.5 Flash1M10 RPM
OpenRouter~30 free modelsvaries20 RPM
GitHub Models100+ modelsvaries15 RPM
xAIGrok128K$25 credits

When to Use What

Bulk Coding

MiMo-V2.5 — 150K req/mo, 6x value, 1M context. Tests, refactors, mechanical work.

Reasoning

Hy3 — Thinks before acting. Architecture, debugging, complex tasks.

Fast Inference

Groq free — 30 RPM, LPU hardware. Quick questions, chat.

Cheapest API

DeepSeek V3.2 — $3.58/1M blended. Pay-per-token, no subscription.

Quality Code

GPT 5.6 Luna — Best code quality, 272K context. Production code.

Free

Groq/Cerebras — No credit card. Light usage, prototyping.