claude-haiku-4.5
Anthropic
Low-latency classification, extraction and routing.
$0.80 / 1M in $4.00 / 1M out
Use it Model catalogue
180+ models. One key.
One endpoint, one bill. Filter by vendor, modality or context window. Availability and prices shown here are demo values for design review.
Catalogue
Pick the right model
Filter locally — nothing is fetched at runtime.
Demo data Model names, availability and prices are illustrative and not a live quote.
claude-opus-5.5
Anthropic
Deepest reasoning and long-form writing. Use for hard planning and review work.
$15.00 / 1M in $75.00 / 1M out
Use it claude-sonnet-4.5
Anthropic
Balanced production default for agents, coding and document analysis.
$3.00 / 1M in $15.00 / 1M out
Use it deepseek-r2
DeepSeek
Visible chain-of-thought for maths and multi-step analysis.
$0.55 / 1M in $2.19 / 1M out
Use it deepseek-v4.1
DeepSeek
Best cost-per-token for coding and agentic loops.
$0.28 / 1M in $0.42 / 1M out
Use it gemini-3-ultra
Maximum multimodal quality when latency is not the constraint.
$4.00 / 1M in $16.00 / 1M out
Use it gemini-3.5-flash
Cheapest long-context model for bulk summarisation.
$0.30 / 1M in $1.20 / 1M out
Use it gemini-3.5-pro
Million-token context for whole-codebase and long-document work.
$2.50 / 1M in $10.00 / 1M out
Use it gpt-5.5-codex
OpenAI
Repository-scale code generation, refactors and test writing.
$1.50 / 1M in $9.00 / 1M out
Use it gpt-6-astra
OpenAI
Broad general reasoning with strong tool use and structured output.
$5.00 / 1M in $20.00 / 1M out
Use it gpt-6-mini
OpenAI
High-volume assistants where cost per request dominates.
$0.60 / 1M in $2.40 / 1M out
Use it grok-5
xAI
Fast reasoning with a direct tone; good for research agents.
$3.00 / 1M in $15.00 / 1M out
Use it kimi-k3
Moonshot
Long-document reading with generous context at low cost.
$0.90 / 1M in $3.60 / 1M out
Use it llama-5-405b
Meta
Open-weights baseline for self-comparison and evals.
$2.20 / 1M in $6.60 / 1M out
Use it mistral-large-3
Mistral
EU-hosted option with clean function calling.
$1.80 / 1M in $5.40 / 1M out
Use it qwen-4-max
Qwen
Strong multilingual coverage across EN, ZH and 20+ languages.
$1.20 / 1M in $6.00 / 1M out
Use it qwen-4-vl
Qwen
Vision extraction and OCR at a low per-image cost.
$0.70 / 1M in $2.80 / 1M out
Use it whisper-3
OpenAI
Speech-to-text for meeting and call transcripts (per minute billing).
$0.36 / 1M in $0.00 / 1M out
Use it No models match those filters. Clear the search or pick a different vendor.
Ready to ignite? Start with $1.
Start with $1.
Get 180+ models.
Create account
No card required to start Cancel anytime GDPR ready