Anvat / Models
Every frontier model. One key. 30% off.
Detailed pages for every model in the Anvat catalog — pricing (list + discounted), real-world strengths and weaknesses, the workloads each one is the right pick for, and code examples that actually run against api.anvat.app.
Anthropic
200K
Claude Opus 4.8
Anthropic's flagship — peak quality for the hardest reasoning and coding tasks
$15.00 / $75.00$10.50 / $52.50 per MTokAnthropic
200K (1M tier available)
Claude Sonnet 4.6
The default workhorse — best price-performance for >90% of agent traffic
$3.00 / $15.00$2.10 / $10.50 per MTokAnthropic
200K
Claude Haiku 4.5
Fast, cheap, surprisingly capable — the right pick for high-volume cost-sensitive work
$1.00 / $5.00$0.70 / $3.50 per MTokOpenAI
200K
GPT-5
OpenAI's frontier — strong reasoning, broad knowledge, fast tool use
$10.00 / $30.00$7.00 / $21.00 per MTokOpenAI
200K
GPT-5 mini
OpenAI's cheap fast tier — strong-enough quality for high-volume work
$0.75 / $4.50$0.53 / $3.15 per MTokGoogle
1M (2M experimental)
Gemini 2.5 Pro
Google's flagship — 1M-token context, strong multimodal, sharp on math
$1.25 / $10.00$0.88 / $7.00 per MTokDeepSeek
1M
DeepSeek V4 Pro
Open-weight flagship — 80.6% SWE-Bench at 1/20th the cost of Claude Opus 4.7
$1.74 / $3.48$1.22 / $2.44 per MTokDeepSeek
1M
DeepSeek V4 Flash
Ultra-cheap open-weight tier — $0.14/MTok input, 1M context, 13B active params
$0.14 / $0.28$0.10 / $0.20 per MTokGoogle
1M (128K with full long-context recall)
Gemini 3.5 Flash
Google's fast tier — beats Gemini 3.1 Pro on agentic + coding benchmarks at $0.30/$2.50
$0.30 / $2.50$0.21 / $1.75 per MTok