Find the most affordable AI models across 95 providers. All prices per million tokens, from first-party data. Aggregator providers excluded to avoid duplicates.
The absolute lowest-priced models across all providers.
| # | Model | Provider | Input $/1M | Output $/1M | Context | Tool Call |
|---|---|---|---|---|---|---|
| 1 | openai--gpt-image-1-mini | aimlapi | $0.007 | $0.676 | ? | |
| 2 | mistralai--Mistral-Nemo-Instruct-2407 | klusterai | $0.008 | $0.001 | 131K | |
| 3 | qwen3.5-0.8b | deepinfra | $0.01 | $0.05 | 262K | |
| 4 | ling-2.6-flash | inclusionai | $0.01 | $0.03 | 262K | ✅ |
| 5 | bdc-coder | inferencenet | $0.01 | $0.01 | 131K | ✅ |
| 6 | openai--gpt-image-1-model | aimlapi | $0.012 | $0.175 | ? | |
| 7 | klusterai--Meta-Llama-3.1-8B-Instruct-Turbo | klusterai | $0.015 | $0.02 | 131K | ✅ |
| 8 | granite-4.0-h-micro | cloudflare | $0.017 | $0.112 | 131K | ✅ |
| 9 | meta-llama-3.1-8b-instruct-turbo | deepinfra | $0.02 | $0.03 | 131K | |
| 10 | meta-llama-3.1-8b-instruct | deepinfra | $0.02 | $0.05 | 131K | |
| 11 | mistral-nemo-instruct-2407 | deepinfra | $0.02 | $0.04 | 131K | |
| 12 | qwen3.5-2b | deepinfra | $0.02 | $0.1 | 262K | |
| 13 | llama-3.1-8b-instruct--fp-16 | inferencenet | $0.02 | $0.03 | 131K | ✅ |
| 14 | schematron-3b | inferencenet | $0.02 | $0.05 | 131K | ✅ |
| 15 | schematron-v3 | inferencenet | $0.02 | $0.05 | 131K | ✅ |
| 16 | Gemma-2-2b-it | nebius | $0.02 | $0.06 | 8K | |
| 17 | Meta-Llama-3.1-8B-Instruct | nebius | $0.02 | $0.06 | 131K | |
| 18 | meta-llama--llama-3.1-8b-instruct | novitaai | $0.02 | $0.05 | 16K | |
| 19 | paddlepaddle--paddleocr-vl | novitaai | $0.02 | $0.02 | 16K | |
| 20 | text-embedding-3-small | openai | $0.02 | $0 | 8K |
Most affordable models that support function/tool calling — essential for agents and automation.
| Model | Provider | Input $/1M | Output $/1M | Context |
|---|---|---|---|---|
| ling-2.6-flash | inclusionai | $0.01 | $0.03 | 262K |
| bdc-coder | inferencenet | $0.01 | $0.01 | 131K |
| klusterai--Meta-Llama-3.1-8B-Instruct-Turbo | klusterai | $0.015 | $0.02 | 131K |
| granite-4.0-h-micro | cloudflare | $0.017 | $0.112 | 131K |
| llama-3.1-8b-instruct--fp-16 | inferencenet | $0.02 | $0.03 | 131K |
| schematron-3b | inferencenet | $0.02 | $0.05 | 131K |
| schematron-v3 | inferencenet | $0.02 | $0.05 | 131K |
| gpt-oss-20b | inferencenet | $0.03 | $0.15 | 131K |
| schematron-v2-turbo | inferencenet | $0.03 | $0.15 | 131K |
| openai--gpt-oss-20b | neuralwatt | $0.03 | $0.16 | ? |
| qwen--qwen3-4b-fp8 | novitaai | $0.03 | $0.03 | 128K |
| liquid-ai--LFM2-24B-A2B | togetherai | $0.03 | $0.12 | 131K |
| amazon-nova-micro | amazon | $0.035 | $0.14 | 128K |
| amazon-nova-micro | amazon-bedrock | $0.035 | $0.14 | 128K |
| mistral-nemo-12b-instruct--fp-8 | inferencenet | $0.0375 | $0.1 | 131K |
Most affordable reasoning models — chain-of-thought for complex problems on a budget.
| Model | Provider | Input $/1M | Output $/1M | Context |
|---|---|---|---|---|
| qwen3.5-0.8b | deepinfra | $0.01 | $0.05 | 262K |
| qwen3.5-2b | deepinfra | $0.02 | $0.1 | 262K |
| gpt-oss-20b | deepinfra | $0.03 | $0.14 | 131K |
| qwen3.5-4b | deepinfra | $0.03 | $0.15 | 262K |
| openai--gpt-oss-20b | neuralwatt | $0.03 | $0.16 | ? |
| qwen--qwen3-4b-fp8 | novitaai | $0.03 | $0.03 | 128K |
| gpt-oss-120b | deepinfra | $0.039 | $0.19 | 131K |
| nvidia-nemotron-nano-9b-v2 | deepinfra | $0.04 | $0.16 | 131K |
| openai--gpt-oss-20b | novitaai | $0.04 | $0.15 | 131K |
| nemotron-3-nano-30b-a3b | deepinfra | $0.05 | $0.2 | 262K |
| gpt-oss-120b | inferencenet | $0.05 | $0.45 | 131K |
| Qwen--Qwen3.6-35B-A3B | neuralwatt | $0.05 | $0.1 | ? |
| openai--gpt-oss-120b | novitaai | $0.05 | $0.25 | 131K |
| qwen3-30b-a3b-fp8 | cloudflare | $0.051 | $0.335 | 40K |
| glm-4.7-flash | cloudflare | $0.06 | $0.4 | 131K |
Most affordable models that can process images — for OCR, visual Q&A, and multimodal tasks.
| Model | Provider | Input $/1M | Output $/1M | Context |
|---|---|---|---|---|
| qwen3.5-0.8b | deepinfra | $0.01 | $0.05 | 262K |
| qwen3.5-2b | deepinfra | $0.02 | $0.1 | 262K |
| paddlepaddle--paddleocr-vl | novitaai | $0.02 | $0.02 | 16K |
| qwen3.5-4b | deepinfra | $0.03 | $0.15 | 262K |
| deepseek--deepseek-ocr-2 | novitaai | $0.03 | $0.03 | 8K |
| deepseek--deepseek-ocr | novitaai | $0.03 | $0.03 | 8K |
| reka-edge-2 | reka | $0.03 | $0.1 | 131K |
| zai-org--autoglm-phone-9b-multilingual | novitaai | $0.035 | $0.138 | 65K |
| gemini-1.5-flash-8b | deepinfra | $0.0375 | $0.15 | 1M |
| google-gemma-3-4b | amazon-bedrock | $0.04 | $0.08 | 131K |
| gemma-3-12b-it | deepinfra | $0.04 | $0.13 | 131K |
| gemma-3-4b-it | deepinfra | $0.04 | $0.08 | 131K |
| qwen3.5-9b | deepinfra | $0.04 | $0.15 | 262K |
| openai--gpt-oss-20b | novitaai | $0.04 | $0.15 | 131K |
| llama-3.2-11b-vision-instruct | cloudflare | $0.049 | $0.676 | 131K |
Most affordable models with large context windows — for long documents, codebases, and conversations.
| Model | Provider | Input $/1M | Output $/1M | Context |
|---|---|---|---|---|
| mistralai--Mistral-Nemo-Instruct-2407 | klusterai | $0.008 | $0.001 | 131K |
| qwen3.5-0.8b | deepinfra | $0.01 | $0.05 | 262K |
| ling-2.6-flash | inclusionai | $0.01 | $0.03 | 262K |
| bdc-coder | inferencenet | $0.01 | $0.01 | 131K |
| klusterai--Meta-Llama-3.1-8B-Instruct-Turbo | klusterai | $0.015 | $0.02 | 131K |
| granite-4.0-h-micro | cloudflare | $0.017 | $0.112 | 131K |
| meta-llama-3.1-8b-instruct-turbo | deepinfra | $0.02 | $0.03 | 131K |
| meta-llama-3.1-8b-instruct | deepinfra | $0.02 | $0.05 | 131K |
| mistral-nemo-instruct-2407 | deepinfra | $0.02 | $0.04 | 131K |
| qwen3.5-2b | deepinfra | $0.02 | $0.1 | 262K |
| llama-3.1-8b-instruct--fp-16 | inferencenet | $0.02 | $0.03 | 131K |
| schematron-3b | inferencenet | $0.02 | $0.05 | 131K |
| schematron-v3 | inferencenet | $0.02 | $0.05 | 131K |
| Meta-Llama-3.1-8B-Instruct | nebius | $0.02 | $0.06 | 131K |
| llama-3.2-1b-instruct | cloudflare | $0.027 | $0.201 | 131K |
The most affordable model from each provider — find the best deal from your preferred provider.
| Provider | Cheapest Model | Input $/1M | Output $/1M | Context |
|---|---|---|---|---|
| 01ai | yi-lightning | $1 | $1 | 16K |
| ai21 | jamba-mini-2-2026-01 | $0.2 | $0.4 | 256K |
| aimlapi | openai--gpt-image-1-mini | $0.007 | $0.676 | ? |
| aion | aion-1.0-mini | $0.7 | $1.4 | 131K |
| alibaba | qwen-flash | $0.15 | $1.5 | ? |
| amazon | amazon-nova-micro | $0.035 | $0.14 | 128K |
| amazon-bedrock | amazon-nova-micro | $0.035 | $0.14 | 128K |
| anthropic | claude-haiku-4-5 | $1 | $5 | 200K |
| arcee | trinity-mini | $0.04 | $0.15 | 131K |
| baichuan | baichuan4-air | $0.98 | $0.98 | 32K |
| baidu | deepseek-v4-flash | $0.126 | $0.252 | 1M |
| baseten | gpt-oss-120b | $0.1 | $0.5 | 131K |
| berget | meta-llama--Llama-3.1-8B-Instruct | $0.2 | $0.2 | ? |
| bytedance | seed-1.6-flash | $0.07 | $0.3 | 262K |
| cerebras | llama3.1-8b | $0.1 | $0.1 | 131K |
| chutes | Qwen--Qwen3-32B-TEE | $0.08 | $0.24 | 40K |
| clarifai | gpt-oss-120b | $0.09 | $0.36 | 131K |
| cloudferro-sherlock | minimax-m2.5 | $0.26 | $1.04 | 1M |
| cloudflare | granite-4.0-h-micro | $0.017 | $0.112 | 131K |
| databricks | databricks-gpt-5-nano | $0.05 | $0.4 | 200K |
| deepinfra | qwen3.5-0.8b | $0.01 | $0.05 | 262K |
| deepseek | deepseek-chat | $0.14 | $0.28 | 1M |
| digitalocean | openai-gpt-oss-20b | $0.05 | $0.45 | 131K |
| dinference | gpt-oss-20b | $0.07 | $0.25 | 131K |
| evroc | Qwen--Qwen3-30B-A3B-Instruct | $0.1 | $0.8 | 40K |
| fireworks | gpt-oss-20b | $0.07 | $0.3 | 131K |
| friendli | meta-llama-3.1-8b-instruct | $0.1 | $0.1 | 131K |
| gmicloud | openai--gpt-oss-120b | $0.07 | $0.28 | 131K |
| gemini-1.5-flash-8b | $0.075 | $0.3 | 1M | |
| google-vertex | gpt-oss-20b | $0.07 | $0.25 | 131K |
| groq | llama-3.1-8b-instant | $0.05 | $0.08 | 131K |
| hpc-ai | deepseek--deepseek-v4-flash | $0.14 | $0.28 | 1M |
| hyperbolic | meta-llama--Llama-3.1-8B-BF16-Base | $0.1 | $0.1 | 131K |
| iflytek | spark-ultra | $0.8 | $0.8 | 131K |
| inception | mercury-2 | $0.25 | $0.75 | 128K |
| inclusionai | ling-2.6-flash | $0.01 | $0.03 | 262K |
| inferencenet | bdc-coder | $0.01 | $0.01 | 131K |
| klusterai | mistralai--Mistral-Nemo-Instruct-2407 | $0.008 | $0.001 | 131K |
| meta | meta-llama-3.2-1b | $0.1 | $0.1 | 128K |
| microsoft | microsoft-phi-4-mini-reasoning | $0.075 | $0.3 | 128K |
| minimax | M2-her | $2.1 | $8.4 | 64K |
| mistral | ministral-3b | $0.04 | $0.04 | 128K |
| mixlayer | qwen--qwen3.5-9b | $0.1 | $0.4 | 131K |
| moonshotai | moonshot-v1-8k-vision-preview | $2 | $10 | 8K |
| morph | morph-compact | $0.2 | $0.5 | 1M |
| nebius | Gemma-2-2b-it | $0.02 | $0.06 | 8K |
| neuralwatt | openai--gpt-oss-20b | $0.03 | $0.16 | ? |
| nousresearch | hermes-3-llama-3.1-8b | $0.06 | $0.12 | 131K |
| novitaai | meta-llama--llama-3.1-8b-instruct | $0.02 | $0.05 | 16K |
| openai | text-embedding-3-small | $0.02 | $0 | 8K |
| ovhcloud | gpt-oss-20b | $0.05 | $0.18 | 131K |
| perplexity | sonar | $1 | $1 | 127K |
| ppio | qwen--qwen3-4b-fp8 | $0.2145 | $0.2145 | 128K |
| privatemode | gpt-oss-120b | $0.43 | $1.7 | 131K |
| reka | reka-edge-2 | $0.03 | $0.1 | 131K |
| sambanova | gpt-oss-120b | $0.22 | $0.59 | 131K |
| scaleway | gpt-oss-120b | $0.15 | $0.6 | 131K |
| siliconflow | gpt-oss-20b | $0.04 | $0.18 | 131K |
| siliconflow-cn | ling-mini-2.0 | $0.5 | $2 | 131K |
| stepfun | step-3.5-flash-2603 | $0.7 | $2.1 | 256K |
| submodel | openai--gpt-oss-120b | $0.1 | $0.5 | 131K |
| tencent | hunyuan-a13b | $0.5 | $2 | 224K |
| tencent-tokenhub | deepseek-v4-flash | $1 | $2 | 1M |
| textsynth | EleutherAI--gpt-j-6B | $0.2 | $2 | 2K |
| togetherai | liquid-ai--LFM2-24B-A2B | $0.03 | $0.12 | 131K |
| upstage | solar-embedding-1-large | $0.1 | $0 | ? |
| voyage | rerank-2.5-lite | $0.02 | $0 | ? |
| vultr | cosmos-reason-2-2b | $0.55 | $2.75 | 131K |
| wafer | Qwen3.5-397B-A17B | $0.6 | $3.6 | 262K |
| writer | palmyra-x5 | $0.6 | $6 | 1M |
| xai | xai-grok-4-fast | $0.2 | $0.5 | 131K |
| xiaomi | mimo-v2-flash | $0.1 | $0.3 | 262K |
| zhipuai | glm-4-flashx-250414 | $0.1 | $0.1 | 128K |
All data is sourced from first-party APIs — not third-party aggregators. Prices are per million tokens as listed by each provider. Aggregator providers (OpenRouter, Requesty, etc.) are excluded from ranking tables to avoid duplicate models. Actual costs may vary based on usage patterns, caching, and batch discounts.