Models
Frontier models, curated.
Every model is exposed via both the OpenAI Chat Completions and Anthropic Messages APIs. Pricing below is per million tokens — actual cost is metered per request.
128K
DeepSeek Flash
DeepSeek
Cheapest path to a competent model. Excellent for chat and tools.
FastCheapAgentic
from $0.14 / 1M inView →
128K
DeepSeek V4 Pro
DeepSeek
Long-context reasoning model. Strong on math, coding, and planning.
ReasoningCodingLong context
from $0.55 / 1M inView →
128K
Qwen Flash
Qwen
Tiny, quick, and remarkably cheap. Great default for high-volume jobs.
FastCheap
from $0.05 / 1M inView →
256K
Qwen Coder
Qwen
Coding-specialised. Excellent on long files and tool-use loops.
CodingAgenticLong context
from $0.30 / 1M inView →
128K
GLM 4.6
Z.ai (GLM)
Balanced generalist. Strong instruction-following for agents.
AgenticReasoning
from $0.50 / 1M inView →
200K
GLM Pro
Z.ai (GLM)
Top-tier GLM. For complex agents and document workflows.
ReasoningLong contextAgentic
from $0.80 / 1M inView →
200K
MiniMax M2
MiniMax
Long-context generalist with strong document understanding.
Long contextAgentic
from $0.20 / 1M inView →
1M
Kimi K2
Moonshot
Million-token context. Designed for codebases and document corpora.
Long contextReasoning
from $0.55 / 1M inView →
Start with $1 in free credit.
No card required. Plug into your editor in under a minute.