Best for fast agentic coding at a low price.
- 1M context
- Vision
- Input
- $0.15 / 1M
- Cache read
- $0.028 / 1M
- Output
- $0.60 / 1M
- Intelligence
- 33
- DeepSWE
- 77%
- Terminal-Bench
- 42.3%
Models
Pick the right model.
Every model we serve, side by side: list prices, context windows, and scores on the benchmarks we trust for agentic coding.
FeaturedThe model we push furthest with our in-house inference stack, from kernels to serving.
Best for the hardest agentic coding tasks.
- 1M context
- Vision
- Input
- $2.00 / 1M
- Cache read
- $0.20 / 1M
- Output
- $10.00 / 1M
- Intelligence
- 46
- DeepSWE
- 75.5%
- Terminal-Bench
- 67.2%
Best for complex, long-horizon coding.
- 1M context
- Text only
- Input
- $1.40 / 1M
- Cache read
- $0.26 / 1M
- Output
- $4.40 / 1M
- Intelligence
- 32
- DeepSWE
- 69%
- Terminal-Bench
- 41.9%
Kimi K3
Retiring November 9, 2026Kimi K3: Moonshot's most capable model and the first open 3T-class release - 2.8T parameters, a 1M-token context window, and native vision, built for repository-scale understanding and long agentic runs.
- 1M context
- Vision
- Input
- $3.00 / 1M
- Cache read
- Not listed
- Output
- $15.00 / 1M
- Intelligence
- on v4.344
- DeepSWE
- 68.5%
- Terminal-Bench
- on 2.185%
About the scores
Scores as of November 7, 2026. Each model's page links every score to its source.
Artificial Analysis Intelligence Index v5
By Artificial Analysis
An independent composite of reasoning, knowledge, maths, coding and agentic evaluations, run by Artificial Analysis on every model the same way.
MethodologyDeepSWE
By Datacurve
Long-horizon software engineering: real repository tasks an agent has to finish end to end.
MethodologyTerminal-Bench 4.0
By tbench.ai
Hard, realistic tasks an agent completes in a terminal sandbox: building, debugging, configuring.
MethodologyOne key, every model.
Create a key once, then switch models by changing one string in your tool.
Looking for a model we no longer serve? See past models.