Cheap models for high-volume work

At a few requests a day the price per million tokens is noise. At a hundred thousand requests a month it is the whole budget. This list is ordered by the cost of one realistic 1,000-word round trip — roughly 1,300 tokens in and the same out — rather than by a headline rate.

396 models in this category · prices in toman per 1M tokens

Model	Capabilities	Context	Input / 1M	Output / 1M	≈ 1,000 words
Extractscaledown/extract	Image inputFile input	1,000,000	13,849	0	18
Summarizescaledown/summarize	Image inputFile input	1,000,000	13,849	0	18
Ling 3.0 Tinyinclusionai/ling-3.0-tiny	Tool callingReasoningJSON output	262,144	5,193	15,580	27
Mistral Nemomistralai/mistral-nemo	Tool callingJSON output	131,072	10,040	10,387	27
Ling 3.0 Flashinclusionai/ling-3.0-flash	Tool callingReasoningJSON output	262,144	7,271	21,812	38
Llama 3 8B Lunarissao10k/l3-lunaris-8b	JSON output	8,192	13,849	17,311	41
GLM FlashLatest~z-ai/glm-flash-latest	Image inputTool callingReasoningJSON output	1,048,576	9,867	31,956	54
Nex-N2.5-Mininex-agi/nex-n2.5-mini	Image inputReasoningJSON output	262,144	8,655	34,622	56
Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct	Tool callingJSON output	131,072	17,311	27,698	59
Mistral Small 3mistralai/mistral-small-24b-instruct-2501	JSON output	32,768	17,311	27,698	59
gpt-oss-20bBatchopenai/gpt-oss-20b:batch	Tool callingReasoningJSON output	131,072	8,309	38,777	61
Gemma 3 4Bgoogle/gemma-3-4b-it	Image inputJSON output	131,072	17,311	34,622	68
gpt-oss-20bopenai/gpt-oss-20b	Tool callingReasoningJSON output	131,072	10,387	45,009	72
Qwen3.7 Flashqwen/qwen3.7-flash	Image inputTool callingReasoningJSON output	1,000,000	10,387	45,009	72
gpt-oss-120bBatchopenai/gpt-oss-120b:batch	Tool callingReasoningJSON output	131,072	10,248	47,086	75
Nova Micro 1.0amazon/nova-micro-v1	Tool calling	128,000	12,118	48,471	79
Schematron V2 Turboinference-net/schematron-v2-turbo	JSON output	128,000	10,387	51,933	81
Command R7B (12-2024)cohere/command-r7b-12-2024	JSON output	128,000	12,983	51,933	84
MythoMax 13Bgryphe/mythomax-l2-13b	JSON output	8,192	27,698	38,084	86
Mercury 2.5inception/mercury-2.5	Tool callingReasoningJSON output	260,000	13,849	51,933	86
Gemma 3 12Bgoogle/gemma-3-12b-it	Image inputTool callingJSON output	131,072	17,311	51,933	90
Ministral 3 3B 2512mistralai/ministral-3b-2512	Image inputTool callingJSON output	131,072	34,622	34,622	90
Reka Edgerekaai/reka-edge	Image inputTool callingJSON output	16,384	34,622	34,622	90
Phi 4microsoft/phi-4	JSON output	16,384	24,235	48,471	95
Ternary Bonsai 2 9Bprism-ml/ternary-bonsai-2-9b	Image inputTool callingReasoningJSON output	262,144	27,698	45,009	95
Hy-MT2-1.8Btencent/hy-mt2-1.8b		8,192	15,234	61,281	99
GPT-5 NanoBatchopenai/gpt-5-nano:batch	Image inputTool callingReasoningJSON output	400,000	8,655	69,244	101
Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct		60,000	9,348	69,590	103
GLM 5.3 FlashBatchz-ai/glm-5.3-flash:batch	Image inputTool callingReasoningJSON output	1,048,576	17,311	62,319	104
Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl	Image inputTool callingReasoningJSON output	131,072	20,773	62,319	108
Solar Mini 4upstage/solar-mini4	Tool callingReasoningJSON output	524,288	17,311	69,244	113
Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-it	Image inputTool callingReasoningJSON output	262,144	23,197	69,244	120
Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning	Tool callingReasoningJSON output	262,144	24,235	69,244	122
DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash	Tool callingReasoningJSON output	1,048,576	31,506	63,012	123
Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct	Image inputTool callingJSON output	256,000	25,966	69,244	124
Schematron V2 Smallinference-net/schematron-v2-small	JSON output	128,000	17,311	79,630	126
Nova Lite 1.0amazon/nova-lite-v1	Image inputTool calling	300,000	20,773	83,093	135
Claude Haiku 5.5Batchanthropic/claude-haiku-5.5:batch	Image inputTool callingReasoningJSON output	1,000,000	17,311	86,555	135
UI-TARS 7Bbytedance/ui-tars-1.5-7b	Image inputJSON output	128,000	34,622	69,244	135
Ling 3.1 Flashinclusionai/ling-3.1-flash	Tool callingReasoningJSON output	1,000,000	25,966	77,899	135
Ministral 3 8B 2512mistralai/ministral-8b-2512	Image inputTool callingJSON output	262,144	51,933	51,933	135
Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b	Tool callingReasoningJSON output	262,144	20,773	83,093	135
GPT-6 Luna ProBatchopenai/gpt-6-luna-pro:batch	Image inputTool callingReasoningJSON output	1,050,000	17,311	86,555	135
GPT-6 LunaBatchopenai/gpt-6-luna:batch	Image inputTool callingReasoningJSON output	1,050,000	17,311	86,555	135
Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct	Tool callingJSON output	32,768	34,622	69,244	135
Reka Flash 3rekaai/reka-flash-3	ReasoningJSON output	65,536	34,622	69,244	135
Granite 4.2 8Bibm-granite/granite-4.2-8b	Tool callingReasoningJSON output	131,072	20,773	86,555	140
Nex-N2.5-Pronex-agi/nex-n2.5-pro	Image inputTool callingReasoningJSON output	262,144	25,966	86,555	146
Qwen3.5-Flashqwen/qwen3.5-flash-02-23	Image inputTool callingReasoningJSON output	1,000,000	22,504	90,017	146
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731	Tool callingReasoningJSON output	1,048,576	20,427	103,866	162
Llama Guard 4 12Bmeta-llama/llama-guard-4-12b	Image input	163,840	62,319	62,319	162
Qwen3 14Bqwen/qwen3-14b	Tool callingReasoningJSON output	40,960	41,546	83,093	162
Qwen3 32Bqwen/qwen3-32b	Tool callingReasoningJSON output	131,072	27,698	96,941	162
DeepSeek V4 FlashLatest~deepseek/deepseek-v4-flash-latest	Tool callingReasoningJSON output	1,048,576	20,427	103,866	162
Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3b	JSON output	8,192	25,620	102,135	166
Hy-MT2-7Btencent/hy-mt2-7b	JSON output	8,192	25,620	102,135	166
Seed 1.6 Flashbytedance-seed/seed-1.6-flash	Image inputTool callingReasoningJSON output	262,144	25,966	103,866	169
gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20b	Tool callingReasoningJSON output	131,072	25,966	103,866	169
Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct	JSON output	131,072	17,623	115,983	174
Llama 4 Scoutmeta-llama/llama-4-scout	Image inputTool callingJSON output	327,680	34,622	103,866	180
Ministral 3 14B 2512mistralai/ministral-14b-2512	Image inputTool callingJSON output	262,144	69,244	69,244	180
Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507	Tool callingJSON outputFile inputAudio input	32,768	34,622	103,866	180
Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety	Image inputReasoning	131,072	69,244	69,244	180
Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507	Tool callingJSON output	262,144	34,622	103,866	180
Step 3.5 Flashstepfun/step-3.5-flash	Tool callingReasoning	262,144	34,622	103,866	180
Qwen3.5-9Bqwen/qwen3.5-9b	Image inputTool callingReasoningJSON output	262,144	58,857	86,555	189
MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash	Image inputTool callingReasoningJSON output	1,050,000	48,471	96,941	189
Gemma 3 27Bgoogle/gemma-3-27b-it	Image inputTool callingJSON output	131,072	27,698	121,177	194
DeepSeek V4.1 FlashBatchdeepseek/deepseek-v4.1-flash:batch	Image inputTool callingReasoningJSON output	1,048,576	38,777	116,330	202
Mercury 3inception/mercury-3	Tool callingReasoningJSON output	1,000,000	34,622	121,177	203
GPT-5 Nanoopenai/gpt-5-nano	Image inputTool callingReasoningJSON output	400,000	17,311	138,488	203
GLM 4.7 Flashz-ai/glm-4.7-flash	Tool callingReasoningJSON output	200,000	20,946	138,488	207
Seed-2.0-Minibytedance-seed/seed-2.0-mini	Image inputTool callingReasoningJSON output	262,144	34,622	138,488	225
Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite	Image inputTool callingReasoningJSON output	1,048,576	34,622	138,488	225
GPT-4.1 Nanoopenai/gpt-4.1-nano	Image inputTool callingJSON outputFile input	1,047,576	34,622	138,488	225
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017	Image inputTool callingReasoningJSON output	1,048,576	2,077	173,110	228
DeepSeek FlashLatest~deepseek/deepseek-flash-latest	Image inputTool callingReasoningJSON output	1,048,576	2,077	173,110	228
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash	Image inputTool callingReasoningJSON output	1,048,576	15,580	173,110	245
Particle-1particle-ai/particle-1	Image inputTool callingReasoningJSON output	1,048,576	17,311	173,110	248
Ternary Bonsai 2 27Bprism-ml/ternary-bonsai-2-27b	Image inputTool callingReasoningJSON output	262,144	25,966	173,110	259
Claude Haiku 5.5anthropic/claude-haiku-5.5	Image inputTool callingReasoningJSON output	1,000,000	34,622	173,110	270
Gemma 4 31Bgoogle/gemma-4-31b-it	Image inputTool callingReasoningJSON output	262,144	69,244	138,488	270
GPT-6 Lunaopenai/gpt-6-luna	Image inputTool callingReasoningJSON output	1,050,000	34,622	173,110	270
GPT-6 Luna Proopenai/gpt-6-luna-pro	Image inputTool callingReasoningJSON output	1,050,000	34,622	173,110	270
Claude HaikuLatest~anthropic/claude-haiku-latest	Image inputTool callingReasoningJSON output	1,000,000	34,622	173,110	270
GPT LunaLatest~openai/gpt-luna-latest	Image inputTool callingReasoningJSON output	1,050,000	34,622	173,110	270
Qwen3 30B A3Bqwen/qwen3-30b-a3b	Tool callingReasoningJSON output	40,960	41,546	173,110	279
Qwen3.8 Flashqwen/qwen3.8-flash	Image inputTool callingReasoningJSON output	1,000,000	51,933	162,723	279
Qwen3.8 Omni Flashqwen/qwen3.8-omni-flash	Image inputTool callingReasoningJSON output	1,000,000	51,933	162,723	279
DeepSeek V3.2deepseek/deepseek-v3.2	Tool callingReasoningJSON output	163,840	90,017	131,563	288
Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl	Image inputTool callingReasoningJSON output	1,048,576	51,933	173,110	293
GLM 5.3 Flashz-ai/glm-5.3-flash	Image inputTool callingReasoningJSON output	1,048,576	51,933	173,110	293
Hy3tencent/hy3	Tool callingReasoningJSON output	262,144	45,701	182,804	297
DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp	Tool callingReasoningJSON output	163,840	93,479	141,950	306
GPT-5.6 Luna ProBatchopenai/gpt-5.6-luna-pro:batch	Image inputTool callingReasoningJSON output	1,050,000	34,622	207,732	315
GPT-5.6 LunaBatchopenai/gpt-5.6-luna:batch	Image inputTool callingReasoningJSON output	1,050,000	34,622	207,732	315
Hunyuan A13B Instructtencent/hunyuan-a13b-instruct	ReasoningJSON output	131,072	48,471	197,345	320
Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct	Tool callingJSON output	131,072	69,244	180,034	324
Command R (08-2024)cohere/command-r-08-2024	Tool callingJSON output	128,000	51,933	207,732	338
LFM2.5-24B-A2Bliquid/lfm-2.5-24b-a2b	Tool callingReasoningJSON output	128,000	17,311	242,354	338
MiniMax M3.1 Flashminimax/minimax-m3.1-flash	Image inputTool callingReasoningJSON output	1,048,576	51,933	207,732	338
Mistral Small 4mistralai/mistral-small-2603	Image inputTool callingReasoningJSON output	262,144	51,933	207,732	338
GPT-4o-miniopenai/gpt-4o-mini	Image inputTool callingJSON outputFile input	128,000	51,933	207,732	338
GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18	Image inputTool callingJSON outputFile input	128,000	51,933	207,732	338
gpt-oss-120bopenai/gpt-oss-120b	Tool callingReasoningJSON output	131,072	51,933	207,732	338
Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct	Tool callingJSON output	262,144	51,933	207,732	338
Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct	Image inputTool callingJSON output	262,144	51,933	207,732	338
Solar Pro 4upstage/solar-pro4	Tool callingReasoningJSON output	524,288	51,933	207,732	338
Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct	Tool callingJSON output	32,768	124,639	138,488	342
Hy3 previewtencent/hy3-preview	Tool callingReasoning	262,144	62,319	207,732	351
Sabamistralai/mistral-saba	Tool callingJSON outputFile input	32,768	69,244	207,732	360
ricursiveAI/Ripple-65B-Previewricursiveai/ripple-65b-preview	Tool callingJSON output	1,048,576	69,244	207,732	360
Cydonia 24B V4.1thedrummer/cydonia-24b-v4.1	JSON output	131,072	103,866	173,110	360
UnslopNemo 12Bthedrummer/unslopnemo-12b	JSON output	1,024,000	138,488	138,488	360
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp	Image inputTool callingReasoningJSON output	1,048,576	74,645	223,935	388
Gemini 3.1 Flash LiteBatchgoogle/gemini-3.1-flash-lite:batch	Image inputTool callingReasoningJSON output	1,048,576	43,277	259,665	394
Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instruct	Image inputTool callingJSON output	128,000	121,523	192,152	408
Qwen3 Coder Nextqwen/qwen3-coder-next	Tool callingJSON output	262,144	41,546	276,975	414
Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507	Tool callingJSON output	262,144	48,471	276,975	423
GLM 4.5 Airz-ai/glm-4.5-air	Tool callingReasoning	131,072	45,009	294,286	441

Showing the first 120. For finer filters see the full catalogue .

See this category ranked by real usage →