Provider
Tensormesh
Use this page to inspect prices within one provider and, when reviewed route identity exists, compare the same model across other providers.
Listed models 10
Chat
Chat models 10
Rows with mode=chat
Lowest input $0.0700 / 1M tokens
Vs global median: 0.1x
Lowest output $0.2800 / 1M tokens
Vs global median: 0.2x
Model pricing
10 rows include direct source URLs. Real invoices can still vary by discounts, regions, and cache rules.
| Model | Mode | Input | Output | Context | Other routes | Lowest elsewhere |
|---|---|---|---|---|---|---|
| DeepSeek-V4-Flash Source linked | Chat | $0.1400 / 1M tokens | $0.2800 / 1M tokens | N/A | N/A | N/A |
| gemma-4-31B-it Source linked | Chat | $0.1400 / 1M tokens | $0.5600 / 1M tokens | N/A | N/A | N/A |
| GLM-5.1-NVFP4-MTP Source linked | Chat | $1.4000 / 1M tokens | $4.4000 / 1M tokens | N/A | N/A | N/A |
| gpt-oss-120b Source linked | Chat | $0.1500 / 1M tokens | $0.6000 / 1M tokens | N/A | N/A | N/A |
| gpt-oss-20b Source linked | Chat | $0.0700 / 1M tokens | $0.2800 / 1M tokens | N/A | N/A | N/A |
| Kimi-K2.6 Source linked | Chat | $0.9600 / 1M tokens | $4.0000 / 1M tokens | N/A | N/A | N/A |
| MiniMax-M2.5 Source linked | Chat | $0.3000 / 1M tokens | $1.2000 / 1M tokens | N/A | N/A | N/A |
| Qwen3-Coder-480B-A35B-Instruct-FP8 Source linked | Chat | $0.4500 / 1M tokens | $1.8000 / 1M tokens | N/A | N/A | N/A |
| Qwen3.5-397B-A17B-FP8 Source linked | Chat | $0.6000 / 1M tokens | $3.6000 / 1M tokens | N/A | N/A | N/A |
| Qwen3.6-27B-FP8 Source linked | Chat | $0.3200 / 1M tokens | $3.2000 / 1M tokens | N/A | N/A | N/A |