OpenRouter - mistralai/mistral-nemo
Source-backed AI pricing
OpenRouter API pricing
Browse source-backed OpenRouter API pricing and sample monthly costs.
Prices are normalized from official provider pricing sources. Marketplace offers are labeled by hosting platform; verify the linked source before purchasing or deploying.
Provider trends
OpenRouter historical trend page
Review model launches, deprecated models, average input and output pricing evolution, and latest pricing changes for OpenRouter.
Provider pricing
OpenRouter API pricing
Sample workload: 10,000 requests/month, 8,000 input tokens, 1,500 output tokens, 30% cached input when listed.
| Model | Input / 1M | Cached / 1M | Output / 1M | Sample monthly cost | Source |
|---|---|---|---|---|---|
| mistralai/mistral-nemo USD per 1M tokens | $0.019 | Not listed | $0.030 | $1.97 | Source |
| inclusionai/ling-3.0-flash-vl USD per 1M tokens | $0.021 | $0.004 | $0.062 | $2.20 | Source |
| inclusionai/ling-3.0-flash USD per 1M tokens | $0.021 | $0.004 | $0.063 | $2.22 | Source |
| openai/gpt-oss-20b USD per 1M tokens | $0.018 | $0.009 | $0.090 | $2.57 | Source |
| nex-agi/nex-n2.5-mini USD per 1M tokens | $0.025 | $0.003 | $0.100 | $2.96 | Source |
| ibm-granite/granite-4.0-h-micro USD per 1M tokens | $0.017 | Not listed | $0.112 | $3.04 | Source |
| openai/gpt-oss-20b:batch USD per 1M tokens | $0.024 | Not listed | $0.112 | $3.60 | Source |
| sao10k/l3-lunaris-8b USD per 1M tokens | $0.040 | Not listed | $0.050 | $3.95 | Source |
| inclusionai/ling-3.0-flash-fin USD per 1M tokens | $0.042 | $0.008 | $0.123 | $4.40 | Source |
| openai/gpt-oss-120b:batch USD per 1M tokens | $0.030 | Not listed | $0.136 | $4.41 | Source |
| openai/gpt-5-nano:batch USD per 1M tokens | $0.025 | $0.003 | $0.200 | $4.46 | Source |
| inception/mercury-2.5 USD per 1M tokens | $0.040 | $0.004 | $0.150 | $4.59 | Source |
| meta-llama/llama-3.1-8b-instruct USD per 1M tokens | $0.050 | $0.025 | $0.080 | $4.60 | Source |
| inference-net/schematron-v2-turbo USD per 1M tokens | $0.030 | $0.030 | $0.150 | $4.65 | Source |
| amazon/nova-micro-v1 USD per 1M tokens | $0.035 | Not listed | $0.140 | $4.90 | Source |
| meta-llama/llama-3.2-1b-instruct USD per 1M tokens | $0.027 | Not listed | $0.201 | $5.17 | Source |
| mistralai/mistral-small-24b-instruct-2501 USD per 1M tokens | $0.050 | Not listed | $0.080 | $5.20 | Source |
| cohere/command-r7b-12-2024 USD per 1M tokens | $0.037 | Not listed | $0.150 | $5.25 | Source |
| nvidia/nemotron-3.5-lightning USD per 1M tokens | $0.049 | $0.025 | $0.140 | $5.43 | Source |
| google/gemma-3-4b-it USD per 1M tokens | $0.050 | Not listed | $0.100 | $5.50 | Source |
| mistralai/ministral-8b-2512:batch USD per 1M tokens | $0.075 | $0.007 | $0.075 | $5.50 | Source |
| openai/gpt-oss-120b USD per 1M tokens | $0.037 | Not listed | $0.170 | $5.51 | Source |
| poolside/laguna-xs-2.1 USD per 1M tokens | $0.060 | $0.030 | $0.120 | $5.88 | Source |
| upstage/solar-mini4 USD per 1M tokens | $0.050 | $0.005 | $0.200 | $5.92 | Source |
| google/gemini-2.5-flash-lite:batch USD per 1M tokens | $0.050 | $0.010 | $0.200 | $6.04 | Source |
| openai/gpt-4.1-nano:batch USD per 1M tokens | $0.050 | $0.013 | $0.200 | $6.10 | Source |
| tencent/hy-mt2-1.8b USD per 1M tokens | $0.044 | Not listed | $0.177 | $6.17 | Source |
| google/gemma-3-12b-it USD per 1M tokens | $0.050 | Not listed | $0.150 | $6.25 | Source |
| z-ai/glm-5.3-flash:batch USD per 1M tokens | $0.060 | $0.012 | $0.200 | $6.65 | Source |
| nvidia/nemotron-3-nano-30b-a3b USD per 1M tokens | $0.050 | Not listed | $0.200 | $7.00 | Source |
| mistralai/ministral-3b-2512 USD per 1M tokens | $0.100 | $0.010 | $0.100 | $7.34 | Source |
| inference-net/schematron-v2-small USD per 1M tokens | $0.050 | $0.050 | $0.230 | $7.45 | Source |
| ibm-granite/granite-4.2-8b USD per 1M tokens | $0.060 | $0.015 | $0.250 | $7.47 | Source |
| microsoft/phi-4 USD per 1M tokens | $0.070 | Not listed | $0.140 | $7.70 | Source |
| poolside/laguna-s-2.1 USD per 1M tokens | $0.090 | $0.009 | $0.180 | $7.96 | Source |
| gryphe/mythomax-l2-13b USD per 1M tokens | $0.080 | Not listed | $0.110 | $8.05 | Source |
| nex-agi/nex-n2.5-pro USD per 1M tokens | $0.075 | $0.015 | $0.250 | $8.31 | Source |
| amazon/nova-lite-v1 USD per 1M tokens | $0.060 | Not listed | $0.240 | $8.40 | Source |
| meta/muse-spark-1.2-contributor USD per 1M tokens | $0.100 | $0.002 | $0.200 | $8.65 | Source |
| meta/muse-spark-1.3-contributor USD per 1M tokens | $0.100 | $0.002 | $0.200 | $8.65 | Source |
| mistralai/mistral-small-2603:batch USD per 1M tokens | $0.075 | $0.007 | $0.300 | $8.88 | Source |
| openai/gpt-5-nano USD per 1M tokens | $0.050 | $0.005 | $0.400 | $8.92 | Source |
| meta-llama/llama-3.2-3b-instruct USD per 1M tokens | $0.050 | Not listed | $0.330 | $8.95 | Source |
| qwen/qwen3.5-flash-02-23 USD per 1M tokens | $0.065 | Not listed | $0.260 | $9.10 | Source |
| google/gemma-4-26b-a4b-it USD per 1M tokens | $0.076 | $0.043 | $0.255 | $9.13 | Source |
| rekaai/reka-edge USD per 1M tokens | $0.100 | Not listed | $0.100 | $9.50 | Source |
| openai/gpt-4o-mini:batch USD per 1M tokens | $0.075 | $0.037 | $0.300 | $9.60 | Source |
| openai/gpt-oss-safeguard-20b USD per 1M tokens | $0.075 | $0.037 | $0.300 | $9.60 | Source |
| qwen/qwen3-coder-30b-a3b-instruct USD per 1M tokens | $0.070 | Not listed | $0.280 | $9.80 | Source |
| qwen/qwen3.5-9b USD per 1M tokens | $0.100 | Not listed | $0.150 | $10.25 | Source |
Guide
Related pricing pages
Cheapest AI API models for a real workload
Rank the cheapest AI API models for a standard monthly workload using source-backed token prices.
AI token cost calculator method
Estimate AI API spend from input, cached input, output, and monthly requests.
OpenAI vs Anthropic API pricing comparison
Compare OpenAI and Anthropic API pricing by model, input and output token cost, cached input rates, and sample workload estimates.
OpenAI vs Google Gemini pricing
Compare OpenAI vs Google Gemini token prices and sample workload costs.
Editorial information
Reviewed by AI Pricing Hub Editorial
2026-10-07
Methodology explains collection, validation, limitations, and update cadence.