# CoreWeave
HQ US · datacenters US · serves 20 tracked open-weights models. · privacy policy
- models
- 20
- verified
- —
- of overall top 10
- 5
- cheapest on
- 1 models
- vs best $
- 1.76×
- ctx (median)
- 256k
- uptime
- 100.0%
# models
| model | rank | $/M in | $/M out | ✓ |
|---|---|---|---|---|
| glm-5.3 | #1 | $1.20 | $4.00 | — |
| glm-5.3-flash | #3 | $0.15 | $0.50 | — |
| deepseek-v4-flash-0731 | #6 | $0.13 | $0.28 | — |
| qwen3.8-27b | #8 | $0.40 | $3.00 | — |
| glm-5.2 | #10 | $0.62 | $2.42 | — |
| minimax-m3 | #12 | $0.23 | $0.96 | — |
| kimi-k2.6 | #15 | $0.65 | $3.41 | — |
| kimi-k2.7-code | #19 | $0.71 | $3.50 | — |
| qwen3.6-35b-a3b | #43 | $0.25 | $1.25 | — |
| gemma-4-26b-a4b-it | #47 | $0.10 | $0.30 | — |
| gemma-4-31b-it | #49 | $0.10 | $0.34 | — |
| deepseek-v3.1 | #57 | $0.55 | $1.65 | — |
| gpt-oss-120b | #63 | $0.03 | $0.17 | — |
| granite-4.2-8b | #64 | $0.10 | $0.15 | — |
| gpt-oss-20b | #75 | $0.03 | $0.13 | — |
| llama-3.3-70b-instruct | #94 | $0.71 | $0.71 | — |
| beam-1.0-501b-a23b | — | $0.30 | $1.00 | — |
| deepseek-v4-pro-0813 | — | $1.31 | $3.96 | — |
| deepseek-v4.1-flash | — | $0.15 | $0.65 | — |
| nemotron-3.5-super-vl | — | $0.15 | $0.50 | — |
all providers · machine-readable: providers.json