Exact weights, declared precision.Models
Open-weight models served on Kurrens infrastructure. Estimated prices in USD per million tokens — may change before launch.
| Model | Context | Max output | Input $/M (est.) | Cached $/M | Output $/M (est.) | Quant. | Capabilities |
|---|---|---|---|---|---|---|---|
| MiMo-V2.6-Pro | 1M | 922K | $0.43 | $0.004 | $0.87 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| MiMo-V2.6-Flash | 1M | 128K | $0.14 | $0.003 | $0.28 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| DeepSeek V4.1 Flash | 1M | 922K | $0.22 | $0.006 | $0.84 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| GLM 5.3 Flash | 1.3M | 243K | $0.15 | $0.030 | $0.50 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| Qwen3.8 Flash | 1M | 128K | $0.15 | $0.016 | $0.47 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| GLM 5.3 | 1.3M | 256K | $1.19 | $0.19 | $4.40 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| Qwen3.8 27B | 1M | 230K | $0.21 | $0.050 | $2.52 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| DeepSeek V4 Pro 0813 | 1M | 384K | $1.31 | $0.044 | $3.96 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| Qwen3.8 2.4T A95B | 1M | 128K | $2.00 | $0.25 | $6.00 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| DeepSeek V4 Flash 0731 | 1.3M | 642K | $0.14 | $0.025 | $0.37 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| Kimi K3 | 1M | 922K | $3.00 | $0.30 | $15.00 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| GLM 5.2 | 1M | 230K | $1.40 | $0.21 | $4.40 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| Kimi K2.7 Code | 256K | 230K | $0.91 | $0.18 | $3.84 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| MiniMax M3 | 1M | 500K | $0.30 | $0.060 | $1.20 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| Qwen3.6 35B A3B | 256K | 179K | $0.13 | $0.050 | $1.00 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| Kimi K2.6 | 256K | 230K | $0.75 | $0.15 | $3.50 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| Gemma 4 31B | 256K | 64K | $0.14 | $0.095 | $0.40 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| MiniMax M2.7 | 200K | 128K | $0.30 | $0.060 | $1.20 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| Qwen3 Coder Next | 256K | 64K | $0.19 | $0.053 | $1.20 | fp8 | Tool calling, Structured outputs, Prompt caching |
| gpt-oss-120b | 128K | 115K | $0.12 | $0.065 | $0.60 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
| gpt-oss-20b | 128K | 115K | $0.035 | $0.025 | $0.15 | fp8 | Tool calling, Structured outputs, Reasoning, Prompt caching |
Looking for a model we don't serve? Request a model →