Compare LLM API Pricing
Pick two models and see a side-by-side breakdown of pricing, context windows, and real costs for your usage.
VS
Your Usage (per request)
API mode:
Input (per 1M tokens)
Output (per 1M tokens)
Context Window
Per-Request Cost
Cost per request
Cost per 1K requests
Monthly Cost Estimate
Input cost
Output cost
Total
Input (per 1M tokens)
Output (per 1M tokens)
Context Window
Per-Request Cost
Cost per request
Cost per 1K requests
Monthly Cost Estimate
Input cost
Output cost
Total
Popular Comparisons
Deep-dive into specific provider matchups with interactive calculators, use case recommendations, and FAQ.
Claude vs ChatGPT
Anthropic vs OpenAI
Claude vs DeepSeek
86-97% cheaper
Gemini vs Claude
Google vs Anthropic
Gemini vs ChatGPT
Google vs OpenAI
Provider Comparison
10 providers side by side
Open Source vs Commercial
Self-hosted vs API
GPT-5 mini vs Claude Haiku
Budget models compared
GPT-5 mini vs Llama 4 Scout
Open source vs closed at budget prices
GPT-5 mini vs Gemini Flash
OpenAI vs Google budget
DeepSeek V4 Flash vs Gemini Flash Lite
Ultra-budget showdown
GPT-5 mini vs DeepSeek V4 Flash
Budget showdown
DeepSeek V4 Flash vs Gemini Flash
Budget 1M-context showdown
Haiku 4.5 vs Gemini Flash
90% cheaper — Anthropic vs Google
Haiku 4.5 vs Mistral Large 3
50-70% cheaper — EU data sovereignty
Gemini 3.5 Flash vs Mistral Large 3
67% cheaper — mid-tier showdown
Gemini vs DeepSeek
Google vs DeepSeek
ChatGPT vs DeepSeek
OpenAI vs DeepSeek
Mistral vs DeepSeek
Budget providers compared
OpenAI vs Google
GPT-5 vs Gemini flagship models
GPT-5 vs Claude vs Gemini
Three-way comparison
xAI Grok vs OpenAI
Grok 4.3 vs GPT-5 matchup
xAI Grok vs Google
Grok 4.3 vs Gemini — premium vs budget
OpenAI vs DeepSeek
GPT-5 vs DeepSeek V4 — premium vs budget king
Premium Models
GPT-5.5 vs Opus vs Gemini Pro
OpenAI vs Anthropic
GPT-5 vs Claude — the big rivalry
Anthropic vs Google
Claude vs Gemini — quality vs budget
Mistral vs Google
Mistral vs Gemini — EU privacy vs scale
Mistral vs Anthropic
7-10x cheaper vs best reasoning quality
OpenAI vs Mistral
9 models vs 2 — EU sovereignty
xAI Grok vs Mistral
200x cheaper vs X data access
GPT-5.5 vs Gemini 3.1 Pro
2.5x cheaper — OpenAI vs Google flagship
GPT-5 vs Gemini 3.1 Pro
GPT-5 22% cheaper, Gemini 3.7x more context
GPT-5 vs GPT-5 Mini
Same context, Mini is 80% cheaper
Gemini 3.5 Flash vs Gemini 3 Flash
Same context, 3 Flash is 67% cheaper
Sonnet 4.6 vs Mistral Large 3
Mistral 83-90% cheaper, Sonnet 4x context
Anthropic vs DeepSeek
Premium vs budget — Claude Opus 4.7 vs DeepSeek V4 Pro
Claude Sonnet 4 vs Gemini 2.5 Pro
Gemini 40% cheaper with larger context
GPT-5.5 vs Claude Opus 4.7
Most capable models from OpenAI vs Anthropic
Claude Opus 4.8 vs GPT-5.5
Premium tier — Opus 17% cheaper on output
GPT-5.5 vs Claude Opus 4.8
Latest flagship showdown — OpenAI vs Anthropic
GPT-5.5 vs Gemini 3.5 Flash
Premium vs mid-tier — Flash 70% cheaper
GPT-5 vs Gemini 3.5 Flash
Close pricing — input/output ratio decides
Opus 4.8 vs DeepSeek V4 Pro
Premium vs budget — DeepSeek 91-97% cheaper
Grok 4.3 vs GPT-5
Grok 75% cheaper on output, 3.7x more context
GPT-5 vs Claude Sonnet 4.6
GPT-5 58% cheaper, Sonnet has 3.7x more context
DeepSeek V4 Pro vs Mistral Large 3
Budget showdown — DeepSeek 42% cheaper on output
GPT-5 vs Claude Opus 4.8
GPT-5 64% cheaper, Opus has 3.7x more context
Claude Opus 4.8 vs Gemini 3.1 Pro
1M context showdown — Gemini 52% cheaper on output
GPT-5 vs DeepSeek V4 Pro
DeepSeek 65% cheaper on input tokens
GPT-5.5 vs DeepSeek V4 Pro
96% cheaper — premium vs budget king
DeepSeek V4 Pro vs GPT-5.5
96% cheaper — biggest price gap in premium AI
Claude Opus 4.8 vs Grok 4.3
Same 1M context, Grok 86% cheaper
Kimi K2.6 vs GPT-5
Similar context, Kimi 53% cheaper
Claude Opus 4.8 vs DeepSeek V4 Pro
Same 1M context, 95% cheaper — open source vs closed
DeepSeek V4 Pro vs Gemini 2.5 Pro
Same 1M context, 65-91% cheaper — open source vs Google
GPT-5 vs Gemini 2.5 Pro
Same price, 3.7x context — OpenAI vs Google
AI Coding Assistants
Copilot vs Cursor vs Claude Code vs Windsurf
Best AI API for Startups
Compare cost, free tiers, and ease of integration
Free vs Pro
APIpulse feature comparison — what you get with Pro
GPT-5 vs Claude Sonnet 4
GPT-5 58% cheaper, same 200K context
GPT-5.3 Codex vs Claude Opus 4.8
Coding showdown — Codex 65% cheaper, Opus 2.5x more context
Claude Sonnet 4.6 vs DeepSeek V4 Flash
Mid-tier vs budget — DeepSeek 95% cheaper, same 1M context
GPT-5 mini vs DeepSeek V4 Pro
DeepSeek 67% cheaper on output — budget showdown
Claude Sonnet 4.6 vs GPT-5 mini
GPT-5 mini 92% cheaper, Sonnet 3.7x more context
GPT-oss vs Llama 4
Open-source showdown — both self-hostable
Kimi K2.6 vs DeepSeek V4 Pro
Chinese AI budget showdown — DeepSeek dominates
DeepSeek V4 Pro vs Claude Opus 4.8
91% cheaper — budget vs premium flagship
DeepSeek V4 Pro vs GPT-5
65% cheaper — budget vs premium, 3.7x more context
Gemini 3.5 Flash vs DeepSeek V4 Pro
Mid-tier vs budget — DeepSeek 71% cheaper on input
Mistral Medium 3.5 vs Claude Sonnet 4.6
European data sovereignty — Mistral 50% cheaper
Grok 4.3 vs Claude Sonnet 4.6
Mid-tier showdown — Grok 83% cheaper on output
Gemini 3.5 Flash vs DeepSeek V4 Flash
Cheapest API showdown — DeepSeek 95% cheaper
Gemini 3.5 Flash vs GPT-5
Mid-tier showdown — GPT-5 17% cheaper input, Gemini 3.7x context
Claude Sonnet 4.6 vs Gemini 3.1 Pro
Mid-tier showdown — Gemini 25% cheaper
GPT-5 vs DeepSeek V3.2
82-97% cheaper — mid-tier vs budget
Claude Opus 4.8 vs Kimi K2.6
83% cheaper — premium Western vs budget Chinese
Llama 4 Maverick vs Kimi K2.6
76% cheaper — open source vs Chinese budget
Mistral Medium 3.5 vs Kimi K2.6
44% cheaper — mid-tier European vs budget Chinese
GPT-5.5 vs Claude Sonnet 4.6
Sonnet 40-50% cheaper with same 1M context
Gemini 3.1 Pro vs Claude Opus 4.8
Same 1M context, Gemini 52% cheaper
Claude Haiku 4.5 vs GPT-5 mini
GPT-5 mini 60-75% cheaper, 36% more context
Gemini 3.5 Flash vs Mistral Medium 3.5
Same input, Mistral 17% cheaper output, Gemini 8x context
GPT-oss 120B vs Llama 4 Scout
Both under $1/M — Llama 8x more context
Grok 4.3 vs Gemini 3.1 Pro
Grok 37-79% cheaper, same 1M context
DeepSeek V4 Pro vs Grok 4.3
65% cheaper, same 1M context, open source
Gemini 2.5 Pro vs Claude Sonnet 4.6
40% cheaper, same 1M context, mid-tier showdown
Llama 4 Maverick vs GPT-5
89% cheaper, 4x more context, open source MIT
GPT-5.5 vs Grok 4.3
Grok 75-92% cheaper, both ~1M context
GPT-5.5 vs Llama 4 Maverick
95-97% cheaper — open source budget alternative
Kimi K2.6 vs DeepSeek V4 Pro
DeepSeek 54-78% cheaper, 4x more context
Mistral Medium 3.5 vs Gemini 3.1 Pro
Mistral 25-38% cheaper, Gemini 8x more context
Claude 4 Opus vs Llama 4 Maverick
Deprecated proprietary vs open source MIT, Llama 50-75% cheaper
Claude 4 Sonnet vs Mistral Medium 3.5
Deprecated vs EU data sovereignty, Mistral 30-50% cheaper
Claude 4 Sonnet vs Llama 4 Maverick
Deprecated vs open source MIT, Llama 91% cheaper
Claude Opus 4.8 vs DeepSeek V4 Flash
Premium vs ultra-budget, DeepSeek 97% cheaper
Claude Opus 4.8 vs Claude Sonnet 4.6
Same provider, Sonnet 40% cheaper, same 1M context
GPT-5.5 Pro vs Claude Opus 4.8
Premium showdown — Opus 83% cheaper on input
GPT-5.5 Pro vs DeepSeek V4 Pro
99% cheaper — DeepSeek $0.435 vs $30.00 input
GPT-5.5 Pro vs Llama 4 Maverick
99% cheaper — Llama $0.27 vs $30.00 input, open-source
Claude 4 Sonnet vs GPT-5
Deprecated vs active — GPT-5 58% cheaper, 36% more context
Claude 4 Sonnet vs DeepSeek V4 Pro
85% cheaper — cheapest migration path, open source
Claude 4 Sonnet vs Gemini 2.5 Pro
58% cheaper, 5x more context — Google mid-tier alternative
Claude 4 Opus vs DeepSeek V4 Pro
97% cheaper — biggest price gap in Claude 4 migration
Claude 4 Opus vs Gemini 2.5 Pro
92% cheaper, 5x more context — Google premium alternative
Claude 4 Opus vs Mistral Medium 3.5
90% cheaper — cost-effective mid-tier alternative
GPT-5.3 Codex vs Claude Sonnet 4.6
Coding models — Codex 42% cheaper, Sonnet 2.5x more context
Gemini 3.5 Flash vs GPT-5.5
70% cheaper premium — same 1M context
Kimi K2.6 vs Gemini 3.1 Pro
Budget vs mid-tier — Kimi 52% cheaper, Gemini 4x context
Claude Sonnet 4.6 vs DeepSeek V4 Pro
85% cheaper coding alternative — same 1M context
Mistral Large 3 vs DeepSeek V4 Pro
Budget vs budget — DeepSeek 42% cheaper, 3.8x more context
GPT-oss 120B vs Llama 4 Scout
Open source showdown — GPT-oss 17% cheaper input, Llama 7.8x context
Claude Haiku 4.5 vs Gemini 3.5 Flash
Haiku 33% cheaper input, Gemini 5x more context
Claude Haiku 4.5 vs Llama 4 Scout
Llama 82% cheaper, 2.5x more context
Claude Haiku 4.5 vs DeepSeek V4 Flash
DeepSeek 86% cheaper input, 94% cheaper output
Gemini 3.5 Flash vs Llama 4 Scout
Llama 88% cheaper, Gemini 2x more context
GPT-5 mini vs Mistral Large 3
GPT-5 mini 50% cheaper input, Mistral 25% cheaper output
Command A vs Mistral Medium 3.5
Mistral 40% cheaper with same 128K context
Mistral Large 3 vs Claude Opus 4.8
Mistral 90% cheaper with same 128K context
Kimi K2.6 vs Claude Sonnet 4.6
Kimi 68% cheaper, Sonnet 4x more context
DeepSeek V4 Pro vs Gemini 3.1 Pro
DeepSeek 78% cheaper with same 1M context
Llama 4 Scout vs DeepSeek V4 Flash
DeepSeek 41% cheaper, both 1M context
Kimi K2.6 vs Mistral Large 3
Mistral 47% cheaper, similar context
Kimi K2.6 vs Gemini 3.5 Flash
Kimi 37% cheaper, Gemini 4x context
Llama 4 Maverick vs DeepSeek V4 Pro
Llama 38% cheaper input, both 1M context
Claude Opus 4.8 vs GPT-5.5 Pro
Premium vs ultra-premium — Opus 83-86% cheaper
Claude Sonnet 4.6 vs Gemini 3.5 Flash
Mid-tier showdown — Gemini 40-50% cheaper, same 1M context
Llama 4 Maverick vs Mistral Large 3
Budget open-source — Llama 43-46% cheaper, 4x more context
GPT-4o vs Claude Sonnet 4.6
GPT-4o 17-33% cheaper, Sonnet 7.8x more context
Jamba 1.7 vs Mistral Medium 3.5
Mistral 25% cheaper input, Jamba 2x more context
GPT-4o vs Gemini 3.1 Pro
Split decision — Gemini 20% cheaper input, GPT-4o 17% cheaper output
GPT-5.5 vs Kimi K2.6
Kimi 81-87% cheaper, GPT-5.5 4.1x more context
GPT-5.5 Pro vs Sonnet 4.6
Sonnet 90% cheaper with similar context
GPT-5.5 Pro vs Gemini 3.5 Flash
Gemini 70-95% cheaper, GPT-5.5 Pro for max reasoning
GPT-5.5 Pro vs Grok 4.3
Grok 75-99% cheaper, GPT-5.5 Pro for premium reasoning
Opus 4.7 vs GPT-5.5
Same input price, Opus 17% cheaper output
Gemini 3.1 Pro vs Kimi K2.6
Kimi 53-67% cheaper, Gemini 4x more context
GPT-5 Mini vs Gemini Flash Lite
Flash Lite 70-85% cheaper, 3.7x more context
GPT-4o vs DeepSeek V4 Pro
DeepSeek 83-91% cheaper, 7.8x more context
Gemini 3.5 Flash vs Kimi K2.6
Kimi 37-56% cheaper, Gemini 4x more context
Gemini 3.5 Flash vs Jamba 1.7
Split — Gemini 25% cheaper input, Jamba 11% cheaper output
Mistral Medium 3.5 vs Grok 4.3
Grok 17-67% cheaper, 7.8x more context
GPT-5 vs Grok 4.3
Grok 75% cheaper output, 3.7x more context
GPT-5 vs Llama 4 Scout
Llama 86-94% cheaper, 3.7x more context
Claude Sonnet 4.6 vs Llama 4 Scout
Llama 94-96% cheaper, same 1M context
GPT-5.5 vs Llama 4 Scout
Llama 96-98% cheaper, comparable context
DeepSeek V4 Pro vs Grok 4.3
DeepSeek 65% cheaper, same 1M context
Claude Opus 4.8 vs Gemini 3.5 Flash
Gemini 64-70% cheaper, same 1M context
GPT-4o vs Mistral Medium 3.5
Mistral 25-40% cheaper, same 128K context
GPT-5 vs Mistral Large 3
Mistral 60-85% cheaper, similar context
GPT-5.5 vs Grok 4.3
Grok 75-92% cheaper, comparable context
Claude Sonnet 4.6 vs Kimi K2.6
Kimi 68-73% cheaper, Sonnet 4x more context
GPT-5 vs Kimi K2.6
Kimi 24-60% cheaper, similar context windows
Gemini 3.5 Flash vs Haiku 4.5
Haiku 33-44% cheaper, Gemini 5x more context
Claude Opus 4.8 vs Kimi K2.6
Kimi 81-84% cheaper, Opus 4x more context
DeepSeek V4 Pro vs Claude Sonnet 4.6
DeepSeek 85-94% cheaper, same 1M context
Gemini 3.1 Pro vs Llama 4 Maverick
Llama 87-93% cheaper, same 1M context, open source
Related Reading
- Cheapest AI API in June 2026 — All 42 models ranked by cost with real scenarios
- AI API Pricing June 2026 — Complete guide, deprecation alerts, migration guide
- Claude 4 Migration Command Center — Live countdown, calculator, code changes, decision tree (deadline: June 15)
- The Complete Guide to LLM Cost Optimization — Strategies to cut your API spend by 40%+
- Cheapest LLM APIs in 2026 — Full ranking of every model by price
- LLM Pricing Cheat Sheet — Quick reference for all 42 models
- Cohere Cost Calculator — Command R+ & Command R pricing
- Moonshot Cost Calculator — Kimi K2.6 pricing
- Together.ai Cost Calculator — Llama 4 & Llama 3.1 pricing
- API Cost Report Card — Grade your spending efficiency, get a shareable report
- Pricing Badges — Embeddable SVG badges for 42 models, copy-paste into READMEs and docs
💡 Save up to 90% on your AI API bill
Pro shows you the cheapest model for your exact usage, with migration code and cost projections. Try free for 24 hours.
⚡ Try Pro Free for 24 HoursNo credit card required · Full access · Cancel anytime
Want more detailed cost modeling?
Use the full calculator to model scenarios, save configurations, and export PDF reports.
Open Full Calculator 📊 Live Pricing Dashboard