Models

Models & live prices

Every model Flow AI routes to, with the live clearing price vs the published rate. Prices float within a floor↔ceiling band as supply and demand move (↓ = getting cheaper). Pass model: "auto" and Flow AI serves the cheapest model that can do the job — or pin any model below.

ModelClearing $/M (in / out)Live range (in $/M)Published $/MSavings
deepseek-v4-flashpinnable$0.14 / $0.28 $0.14 – $0.14$0.14 / $0.28
minimax-m2.7pinnable$0.03 / $0.10 $0.03 – $0.25$0.25 / $1.0090% off
minimax-m3pinnable$0.04 / $0.13 $0.03 – $0.30$0.30 / $1.2088.7% off
deepseek-v4-propinnable$0.43 / $0.87 $0.43 – $0.43$0.43 / $0.87
qwen3.7-plus$0.45 / $1.80 $0.45 – $0.45$0.45 / $1.80
claude-opus-4.8pinnable$15.00 / $75.00 $15.00 – $15.00$15.00 / $75.00
nemotron-3-ultrapinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
kimi-k2pinnable$0.58 / $2.29 $0.58 – $0.58$0.58 / $2.29
qwen3-27bpinnable$0.20 / $0.80 $0.20 – $0.20$0.20 / $0.80
gpt-oss-120bself-hostpinnable$0.03 / $0.06 $0.03 – $0.04$0.04 / $0.1756.5% off
gpt-4o-minipinnable$0.07 / $0.30 $0.07 – $0.15$0.15 / $0.6050% off
gpt-4opinnable$2.50 / $10.00 $2.50 – $2.50$2.50 / $10.00
gpt-4o-mini-onlinepinnable$0.15 / $0.60 $0.15 – $0.15$0.15 / $0.60
glm-4.7-searchpinnable$0.60 / $2.20 $0.60 – $0.60$0.60 / $2.20
kimi-k2.6-searchpinnable$0.60 / $2.50 $0.60 – $0.60$0.60 / $2.50
sonarpinnable$1.00 / $1.00 $1.00 – $1.00$1.00 / $1.00
gemini-2.5-flashpinnable$0.30 / $2.50 $0.30 – $0.30$0.30 / $2.50
claude-sonnet-4.6pinnable$3.00 / $15.00 $3.00 – $3.00$3.00 / $15.00
mimo-v2.5pinnable$0.07 / $0.25 $0.06 – $0.30$0.30 / $1.2078.7% off
mimo-v2.5-propinnable$0.60 / $2.40 $0.60 – $0.60$0.60 / $2.40
qwen3-8bself-hostpinnable$0.08 / $0.16 $0.08 – $0.08$0.08 / $0.16
qwen3-14bself-host$0.10 / $0.20 $0.10 – $0.10$0.10 / $0.20
qwen3.8-27bself-host$0.15 / $0.30 $0.04 – $0.15$0.15 / $0.30
qwen3-32bself-host$0.15 / $0.30 $0.15 – $0.15$0.15 / $0.30
mistral-smallself-hostpinnable$0.05 / $0.08 $0.05 – $0.05$0.05 / $0.08
qwen2.5-7bself-hostpinnable$0.12 / $0.24 $0.12 – $0.12$0.12 / $0.24
llama3.3-70bself-hostpinnable$0.10 / $0.32 $0.10 – $0.10$0.10 / $0.32
qwen2.5-coder-7bself-host$0.08 / $0.16 $0.08 – $0.08$0.08 / $0.16
qwen2.5-coder-14bself-host$0.10 / $0.20 $0.10 – $0.10$0.10 / $0.20
qwen2.5-coder-32bself-hostpinnable$0.08 / $0.28 $0.08 – $0.08$0.08 / $0.28
devstralself-host$0.12 / $0.24 $0.12 – $0.12$0.12 / $0.24
gemma3-4bself-hostpinnable$0.05 / $0.10 $0.05 – $0.05$0.05 / $0.10
phi-4-miniself-hostpinnable$0.07 / $0.14 $0.07 – $0.07$0.07 / $0.14
qwen2.5-3bself-host$0.05 / $0.10 $0.05 – $0.05$0.05 / $0.10
llama3.2-3bself-host$0.05 / $0.10 $0.05 – $0.05$0.05 / $0.10
gemma2-2bself-host$0.04 / $0.08 $0.04 – $0.04$0.04 / $0.08
or:meta-llama/llama-3.2-1b-instructpinnable$0.03 / $0.20 $0.03 – $0.03$0.03 / $0.20
or:poolside/laguna-s-2.1pinnable$0.09 / $0.18 $0.09 – $0.09$0.09 / $0.18
or:thinkingmachines/inkling:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:meituan/longcat-2.0pinnable$0.30 / $1.20 $0.30 – $0.30$0.30 / $1.20
or:ibm-granite/granite-4.2-8bpinnable$0.10 / $0.15 $0.10 – $0.10$0.10 / $0.15
or:openai/gpt-5.6-terra-pro:batchpinnable$1.00 / $6.00 $1.00 – $1.00$1.00 / $6.00
or:google/gemini-3.7-flash:batchpinnable$0.38 / $1.88 $0.38 – $0.38$0.38 / $1.88
or:nvidia/nemotron-3.5-lightningpinnable$0.08 / $0.20 $0.08 – $0.08$0.08 / $0.20
or:google/gemma-3-27b-itpinnable$0.08 / $0.45 $0.08 – $0.08$0.08 / $0.45
or:z-ai/glm-flash-latestpinnable$0.07 / $0.25 $0.07 – $0.07$0.07 / $0.25
or:google/gemma-4-31b-itpinnable$0.09 / $0.34 $0.09 – $0.09$0.09 / $0.34
or:nvidia/nemotron-3-ultra-550b-a55b:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:mistralai/mistral-medium-3-5:batchpinnable$0.75 / $3.75 $0.75 – $0.75$0.75 / $3.75
or:inception/mercury-2.5-previewpinnable$0.04 / $0.15 $0.04 – $0.04$0.04 / $0.15
or:moonshotai/kimi-k2.7-codepinnable$0.66 / $3.40 $0.66 – $0.66$0.66 / $3.40
or:google/gemma-4-31b-it:batchpinnable$0.39 / $0.97 $0.39 – $0.39$0.39 / $0.97
or:inclusionai/ring-2.6-1tpinnable$0.07 / $0.63 $0.07 – $0.07$0.07 / $0.63
or:google/gemini-flash-latestpinnable$0.75 / $3.75 $0.75 – $0.75$0.75 / $3.75
or:qwen/qwen3.5-plus-20260420pinnable$0.30 / $1.80 $0.30 – $0.30$0.30 / $1.80
or:~anthropic/claude-haiku-latestpinnable$1.00 / $5.00 $1.00 – $1.00$1.00 / $5.00
or:~openai/gpt-mini-latestpinnable$0.75 / $4.50 $0.75 – $0.75$0.75 / $4.50
or:thedrummer/skyfall-36b-v2pinnable$0.55 / $0.80 $0.55 – $0.55$0.55 / $0.80
or:aion-labs/aion-rp-llama-3.1-8bpinnable$0.80 / $1.60 $0.80 – $0.80$0.80 / $1.60
or:openai/gpt-5.6-terra:batchpinnable$1.00 / $6.00 $1.00 – $1.00$1.00 / $6.00
or:poolside/laguna-m.1pinnable$0.20 / $0.40 $0.20 – $0.20$0.20 / $0.40
or:qwen/qwen3.6-flashpinnable$0.19 / $1.13 $0.19 – $0.19$0.19 / $1.13
or:poolside/laguna-m.1:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:inception/mercury-2pinnable$0.25 / $0.75 $0.25 – $0.25$0.25 / $0.75
or:z-ai/glm-5.1pinnable$0.97 / $3.04 $0.97 – $0.97$0.97 / $3.04
or:google/gemini-3.1-flash-lite-previewpinnable$0.25 / $1.50 $0.25 – $0.25$0.25 / $1.50
or:bytedance-seed/seed-2.0-minipinnable$0.10 / $0.40 $0.10 – $0.10$0.10 / $0.40
or:qwen/qwen3.5-35b-a3bpinnable$0.08 / $0.75 $0.08 – $0.08$0.08 / $0.75
or:z-ai/glm-4.5vpinnable$0.60 / $1.80 $0.60 – $0.60$0.60 / $1.80
or:openai/o3-mini:batchpinnable$0.55 / $2.20 $0.55 – $0.55$0.55 / $2.20
or:mistralai/mistral-small-24b-instruct-2501pinnable$0.05 / $0.08 $0.05 – $0.05$0.05 / $0.08
or:xiaomi/mimo-v2.5pinnable$0.14 / $0.28 $0.14 – $0.14$0.14 / $0.28
or:qwen/qwen3.5-27bpinnable$0.20 / $1.56 $0.20 – $0.20$0.20 / $1.56
or:qwen/qwen3.5-flash-02-23pinnable$0.07 / $0.26 $0.07 – $0.07$0.07 / $0.26
or:inclusionai/ling-2.6-flashpinnable$0.01 / $0.03 $0.01 – $0.01$0.01 / $0.03
or:nvidia/nemotron-3-nano-30b-a3bpinnable$0.05 / $0.20 $0.05 – $0.05$0.05 / $0.20
or:z-ai/glm-4.7-flashpinnable$0.06 / $0.40 $0.06 – $0.06$0.06 / $0.40
or:openai/gpt-5.2:batchpinnable$0.88 / $7.00 $0.88 – $0.88$0.88 / $7.00
or:qwen/qwen3-235b-a22b-2507pinnable$0.09 / $0.55 $0.09 – $0.09$0.09 / $0.55
or:z-ai/glm-4.7pinnable$0.40 / $1.75 $0.40 – $0.40$0.40 / $1.75
or:deepseek/deepseek-chat-v3-0324pinnable$0.25 / $1.00 $0.25 – $0.25$0.25 / $1.00
or:qwen/qwen-2.5-72b-instructpinnable$0.36 / $0.40 $0.36 – $0.36$0.36 / $0.40
or:openai/gpt-audio-minipinnable$0.60 / $2.40 $0.60 – $0.60$0.60 / $2.40
or:minimax/minimax-m3:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:nvidia/nemotron-3-super-120b-a12bpinnable$0.09 / $0.40 $0.09 – $0.09$0.09 / $0.40
or:qwen/qwen3-max-thinkingpinnable$0.78 / $3.90 $0.78 – $0.78$0.78 / $3.90
or:minimax/minimax-m2-herpinnable$0.30 / $1.20 $0.30 – $0.30$0.30 / $1.20
or:qwen/qwen3.6-pluspinnable$0.33 / $1.95 $0.33 – $0.33$0.33 / $1.95
or:kwaipilot/kat-coder-pro-v2pinnable$0.30 / $1.20 $0.30 – $0.30$0.30 / $1.20
or:mistralai/mistral-small-2603pinnable$0.15 / $0.60 $0.15 – $0.15$0.15 / $0.60
or:relace/relace-searchpinnable$1.00 / $3.00 $1.00 – $1.00$1.00 / $3.00
or:z-ai/glm-4.6vpinnable$0.30 / $0.90 $0.30 – $0.30$0.30 / $0.90
or:stepfun/step-3.5-flashpinnable$0.10 / $0.30 $0.10 – $0.10$0.10 / $0.30
or:meta/muse-spark-1.3-contributorpinnable$0.10 / $0.20 $0.10 – $0.10$0.10 / $0.20
or:moonshotai/kimi-k2.5pinnable$0.45 / $2.25 $0.45 – $0.45$0.45 / $2.25
or:qwen/qwen3-coder-nextpinnable$0.12 / $0.80 $0.12 – $0.12$0.12 / $0.80
or:qwen/qwen3.8-flashpinnable$0.15 / $0.47 $0.15 – $0.15$0.15 / $0.47
or:bytedance-seed/seed-1.6pinnable$0.25 / $2.00 $0.25 – $0.25$0.25 / $2.00
or:minimax/minimax-m2.1pinnable$0.30 / $1.20 $0.30 – $0.30$0.30 / $1.20
or:mistralai/devstral-2512pinnable$0.40 / $2.00 $0.40 – $0.40$0.40 / $2.00
or:amazon/nova-2-lite-v1pinnable$0.30 / $2.50 $0.30 – $0.30$0.30 / $2.50
or:mistralai/ministral-3b-2512pinnable$0.10 / $0.10 $0.10 – $0.10$0.10 / $0.10
or:google/gemini-3.8-flashpinnable$0.75 / $3.75 $0.75 – $0.75$0.75 / $3.75
or:google/gemini-3.8-flash:batchpinnable$0.38 / $1.88 $0.38 – $0.38$0.38 / $1.88
or:nvidia/nemotron-nano-12b-v2-vl:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:openai/gpt-oss-20b:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:deepseek/deepseek-v3.2pinnable$0.27 / $0.40 $0.27 – $0.27$0.27 / $0.40
or:minimax/minimax-m2.7:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:mistralai/ministral-14b-2512pinnable$0.20 / $0.20 $0.20 – $0.20$0.20 / $0.20
or:rekaai/reka-edgepinnable$0.10 / $0.10 $0.10 – $0.10$0.10 / $0.10
or:mistralai/ministral-8b-2512pinnable$0.15 / $0.15 $0.15 – $0.15$0.15 / $0.15
or:meta-llama/llama-3.2-3b-instructpinnable$0.05 / $0.33 $0.05 – $0.05$0.05 / $0.33
or:mistralai/ministral-8b-2512:batchpinnable$0.15 / $0.15 $0.15 – $0.15$0.15 / $0.15
or:z-ai/glm-5.3-flashpinnable$0.07 / $0.25 $0.07 – $0.07$0.07 / $0.25
or:allenai/olmo-3-32b-thinkpinnable$0.15 / $0.50 $0.15 – $0.15$0.15 / $0.50
or:thedrummer/cydonia-24b-v4.1pinnable$0.30 / $0.50 $0.30 – $0.30$0.30 / $0.50
or:relace/relace-apply-3pinnable$0.85 / $1.25 $0.85 – $0.85$0.85 / $1.25
or:inclusionai/ling-3.0-flash-fin:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:z-ai/glm-5.2:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:stealth/ox-alphapinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:qwen/qwen3-30b-a3b-thinking-2507pinnable$0.20 / $2.40 $0.20 – $0.20$0.20 / $2.40
or:minimax/minimax-m2.7pinnable$0.30 / $1.20 $0.30 – $0.30$0.30 / $1.20
or:cohere/north-mini-code:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:nvidia/nemotron-nano-9b-v2:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:openai/gpt-oss-120bpinnable$0.04 / $0.17 $0.04 – $0.04$0.04 / $0.17
or:openai/gpt-5.1-codex-minipinnable$0.25 / $2.00 $0.25 – $0.25$0.25 / $2.00
or:moonshotai/kimi-k2-0905pinnable$0.60 / $2.50 $0.60 – $0.60$0.60 / $2.50
or:mistralai/mistral-large-2512:batchpinnable$0.50 / $1.50 $0.50 – $0.50$0.50 / $1.50
or:inclusionai/ling-3.0-flash-finpinnable$0.06 / $0.18 $0.06 – $0.06$0.06 / $0.18
or:x-ai/grok-4.3:batchpinnable$1.00 / $2.00 $1.00 – $1.00$1.00 / $2.00
or:qwen/qwen3-30b-a3b-instruct-2507pinnable$0.05 / $0.19 $0.05 – $0.05$0.05 / $0.19
or:z-ai/glm-4.5-airpinnable$0.13 / $0.85 $0.13 – $0.13$0.13 / $0.85
or:tencent/hy4-previewpinnable$0.83 / $2.50 $0.83 – $0.83$0.83 / $2.50
or:z-ai/glm-4.5pinnable$0.60 / $2.20 $0.60 – $0.60$0.60 / $2.20
or:qwen/qwen3-coderpinnable$0.30 / $1.00 $0.30 – $0.30$0.30 / $1.00
or:inclusionai/ling-3.0-flash-sante:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:tencent/hy-mt2-30b-a3bpinnable$0.07 / $0.29 $0.07 – $0.07$0.07 / $0.29
or:liquid/lfm-2.5-2.6b:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:z-ai/glm-5.3-flash:batchpinnable$0.15 / $0.50 $0.15 – $0.15$0.15 / $0.50
or:google/gemma-3n-e4b-itpinnable$0.06 / $0.12 $0.06 – $0.06$0.06 / $0.12
or:tencent/hy-mt2-1.8bpinnable$0.04 / $0.18 $0.04 – $0.04$0.04 / $0.18
or:z-ai/glm-latestpinnable$0.84 / $3.14 $0.84 – $0.84$0.84 / $3.14
or:mistralai/mistral-small-3.2-24b-instructpinnable$0.07 / $0.20 $0.07 – $0.07$0.07 / $0.20
or:arcee-ai/virtuoso-largepinnable$0.75 / $1.20 $0.75 – $0.75$0.75 / $1.20
or:minimax/minimax-m1pinnable$0.55 / $2.20 $0.55 – $0.55$0.55 / $2.20
or:google/gemma-3-4b-itpinnable$0.05 / $0.10 $0.05 – $0.05$0.05 / $0.10
or:meta/muse-glimmer-30bpinnable$0.30 / $1.10 $0.30 – $0.30$0.30 / $1.10
or:meta/muse-glimmer-30b:batchpinnable$0.35 / $1.50 $0.35 – $0.35$0.35 / $1.50
or:moonshotai/kimi-k2-thinkingpinnable$0.60 / $2.50 $0.60 – $0.60$0.60 / $2.50
or:openai/gpt-4.1-nanopinnable$0.10 / $0.40 $0.10 – $0.10$0.10 / $0.40
or:meta-llama/llama-4-maverickpinnable$0.20 / $0.70 $0.20 – $0.20$0.20 / $0.70
or:openai/gpt-4o-mini-search-previewpinnable$0.15 / $0.60 $0.15 – $0.15$0.15 / $0.60
or:google/gemini-3.5-flash-litepinnable$0.30 / $2.50 $0.30 – $0.30$0.30 / $2.50
or:perplexity/sonarpinnable$1.00 / $1.00 $1.00 – $1.00$1.00 / $1.00
or:microsoft/phi-4pinnable$0.07 / $0.14 $0.07 – $0.07$0.07 / $0.14
or:deepseek/deepseek-r1pinnable$0.70 / $2.50 $0.70 – $0.70$0.70 / $2.50
or:thinkingmachines/inkling-small:batchpinnable$0.50 / $1.20 $0.50 – $0.50$0.50 / $1.20
or:poolside/laguna-s-2.1:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:thedrummer/rocinante-12bpinnable$0.25 / $0.50 $0.25 – $0.25$0.25 / $0.50
or:nousresearch/hermes-3-llama-3.1-405bpinnable$1.00 / $1.00 $1.00 – $1.00$1.00 / $1.00
or:sao10k/l3-lunaris-8bpinnable$0.04 / $0.05 $0.04 – $0.04$0.04 / $0.05
or:meta-llama/llama-3.1-70b-instructpinnable$0.40 / $0.40 $0.40 – $0.40$0.40 / $0.40
or:meta-llama/llama-3.1-8b-instructpinnable$0.05 / $0.08 $0.05 – $0.05$0.05 / $0.08
or:thinkingmachines/inkling:batchpinnable$1.00 / $4.05 $1.00 – $1.00$1.00 / $4.05
or:mistralai/voxtral-small-24b-2507pinnable$0.10 / $0.30 $0.10 – $0.10$0.10 / $0.30
or:qwen/qwen-2.5-7b-instructpinnable$0.10 / $0.20 $0.10 – $0.10$0.10 / $0.20
or:kwaipilot/kat-coder-pro-v2.5pinnable$0.74 / $2.96 $0.74 – $0.74$0.74 / $2.96
or:nex-agi/nex-n2-minipinnable$0.03 / $0.10 $0.03 – $0.03$0.03 / $0.10
or:minimax/minimax-m2pinnable$0.26 / $1.02 $0.26 – $0.26$0.26 / $1.02
or:openai/gpt-4o-minipinnable$0.15 / $0.60 $0.15 – $0.15$0.15 / $0.60
or:kwaipilot/kat-coder-air-v2.5pinnable$0.15 / $0.60 $0.15 – $0.15$0.15 / $0.60
or:thinkingmachines/inklingpinnable$1.00 / $4.05 $1.00 – $1.00$1.00 / $4.05
or:inclusionai/ling-3.0-flash:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:openai/gpt-5.6-luna-propinnable$0.20 / $1.20 $0.20 – $0.20$0.20 / $1.20
or:openai/gpt-5.6-lunapinnable$0.20 / $1.20 $0.20 – $0.20$0.20 / $1.20
or:anthropic/claude-haiku-latestpinnable$1.00 / $5.00 $1.00 – $1.00$1.00 / $5.00
or:xiaomi/mimo-v2.5-propinnable$0.43 / $0.87 $0.43 – $0.43$0.43 / $0.87
or:upstage/solar-pro-3pinnable$0.15 / $0.60 $0.15 – $0.15$0.15 / $0.60
or:anthropic/claude-haiku-4.5pinnable$1.00 / $5.00 $1.00 – $1.00$1.00 / $5.00
or:anthropic/claude-haiku-4.5:batchpinnable$0.50 / $2.50 $0.50 – $0.50$0.50 / $2.50
or:bytedance-seed/seed-1.6-flashpinnable$0.07 / $0.30 $0.07 – $0.07$0.07 / $0.30
or:google/gemma-4-26b-a4b-itpinnable$0.07 / $0.34 $0.07 – $0.07$0.07 / $0.34
or:openai/gpt-5.4-nanopinnable$0.20 / $1.25 $0.20 – $0.20$0.20 / $1.25
or:morph/morph-v3-fastpinnable$0.80 / $1.20 $0.80 – $0.80$0.80 / $1.20
or:deepseek/deepseek-r1-0528pinnable$0.50 / $2.15 $0.50 – $0.50$0.50 / $2.15
or:aion-labs/aion-3.0-minipinnable$0.70 / $1.40 $0.70 – $0.70$0.70 / $1.40
or:mistralai/mistral-large-2512pinnable$0.50 / $1.50 $0.50 – $0.50$0.50 / $1.50
or:qwen/qwen3-235b-a22b-thinking-2507pinnable$0.23 / $2.30 $0.23 – $0.23$0.23 / $2.30
or:qwen/qwen-plus-2025-07-28:thinkingpinnable$0.26 / $0.78 $0.26 – $0.26$0.26 / $0.78
or:tencent/hy3pinnable$0.13 / $0.53 $0.13 – $0.13$0.13 / $0.53
or:qwen/qwen3.5-122b-a10bpinnable$0.29 / $2.40 $0.29 – $0.29$0.29 / $2.40
or:google/gemini-3-flash-previewpinnable$0.50 / $3.00 $0.50 – $0.50$0.50 / $3.00
or:qwen/qwen3-vl-30b-a3b-thinkingpinnable$0.20 / $2.40 $0.20 – $0.20$0.20 / $2.40
or:openai/gpt-4.1-minipinnable$0.40 / $1.60 $0.40 – $0.40$0.40 / $1.60
or:mistralai/mistral-sabapinnable$0.20 / $0.60 $0.20 – $0.20$0.20 / $0.60
or:nvidia/nemotron-3-nano-30b-a3b:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:google/gemini-3.5-flash-lite:batchpinnable$0.15 / $1.25 $0.15 – $0.15$0.15 / $1.25
or:arcee-ai/trinity-large-thinkingpinnable$0.25 / $0.80 $0.25 – $0.25$0.25 / $0.80
or:nvidia/nemotron-3-ultra-550b-a55bpinnable$0.63 / $3.13 $0.63 – $0.63$0.63 / $3.13
or:qwen/qwen3-vl-235b-a22b-thinkingpinnable$0.40 / $4.00 $0.40 – $0.40$0.40 / $4.00
or:deepseek/deepseek-r1-distill-llama-70bpinnable$0.80 / $0.80 $0.80 – $0.80$0.80 / $0.80
or:qwen/qwen3.7-flashpinnable$0.03 / $0.13 $0.03 – $0.03$0.03 / $0.13
or:google/gemini-3.6-flash:batchpinnable$0.38 / $1.88 $0.38 – $0.38$0.38 / $1.88
or:qwen/qwen3.7-pluspinnable$0.32 / $1.28 $0.32 – $0.32$0.32 / $1.28
or:google/gemini-3.1-pro-preview:batchpinnable$1.00 / $6.00 $1.00 – $1.00$1.00 / $6.00
or:google/gemini-3-flash-preview:batchpinnable$0.25 / $1.50 $0.25 – $0.25$0.25 / $1.50
or:minimax/minimax-m3pinnable$0.30 / $1.20 $0.30 – $0.30$0.30 / $1.20
or:minimax/minimax-m3:batchpinnable$0.30 / $1.20 $0.30 – $0.30$0.30 / $1.20
or:openai/gpt-5.1:batchpinnable$0.63 / $5.00 $0.63 – $0.63$0.63 / $5.00
or:openai/gpt-5.4-nano:batchpinnable$0.10 / $0.63 $0.10 – $0.10$0.10 / $0.63
or:openai/gpt-5.4-mini:batchpinnable$0.38 / $2.25 $0.38 – $0.38$0.38 / $2.25
or:x-ai/grok-build-0.1pinnable$1.00 / $2.00 $1.00 – $1.00$1.00 / $2.00
or:openai/gpt-5-nano:batchpinnable$0.03 / $0.20 $0.03 – $0.03$0.03 / $0.20
or:google/gemini-2.5-flash-lite:batchpinnable$0.05 / $0.20 $0.05 – $0.05$0.05 / $0.20
or:deepseek/deepseek-v4-flash-0731pinnable$0.07 / $0.18 $0.07 – $0.07$0.07 / $0.18
or:z-ai/glm-4.6pinnable$0.55 / $2.20 $0.55 – $0.55$0.55 / $2.20
or:anthropic/claude-sonnet-5:batchpinnable$1.00 / $5.00 $1.00 – $1.00$1.00 / $5.00
or:stepfun/step-3.7-flashpinnable$0.20 / $1.15 $0.20 – $0.20$0.20 / $1.15
or:openai/gpt-5-mini:batchpinnable$0.13 / $1.00 $0.13 – $0.13$0.13 / $1.00
or:google/gemini-2.5-flash:batchpinnable$0.15 / $1.25 $0.15 – $0.15$0.15 / $1.25
or:deepseek/deepseek-v4-flash-latestpinnable$0.05 / $0.10 $0.05 – $0.05$0.05 / $0.10
or:openai/gpt-5.6-terra-propinnable$1.00 / $6.00 $1.00 – $1.00$1.00 / $6.00
or:openai/gpt-5.6-terrapinnable$1.00 / $6.00 $1.00 – $1.00$1.00 / $6.00
or:thinkingmachines/inkling-smallpinnable$0.45 / $1.20 $0.45 – $0.45$0.45 / $1.20
or:deepseek/deepseek-v3.2-exppinnable$0.27 / $0.41 $0.27 – $0.27$0.27 / $0.41
or:mancer/weaverpinnable$0.40 / $0.75 $0.40 – $0.40$0.40 / $0.75
or:undi95/remm-slerp-l2-13bpinnable$0.35 / $0.65 $0.35 – $0.35$0.35 / $0.65
or:inclusionai/ling-3.0-tiny:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:inclusionai/ling-3.0-flashpinnable$0.02 / $0.06 $0.02 – $0.02$0.02 / $0.06
or:z-ai/glm-5.2pinnable$0.97 / $3.04 $0.97 – $0.97$0.97 / $3.04
or:qwen/qwen3-vl-235b-a22b-instructpinnable$0.21 / $1.90 $0.21 – $0.21$0.21 / $1.90
or:nvidia/nemotron-3-ultra-550b-a55b:batchpinnable$0.60 / $3.60 $0.60 – $0.60$0.60 / $3.60
or:openai/gpt-5-codex:batchpinnable$0.63 / $5.00 $0.63 – $0.63$0.63 / $5.00
or:openai/o3:batchpinnable$1.00 / $4.00 $1.00 – $1.00$1.00 / $4.00
or:openai/o4-mini-high:batchpinnable$0.55 / $2.20 $0.55 – $0.55$0.55 / $2.20
or:z-ai/glm-5.2:batchpinnable$0.70 / $2.20 $0.70 – $0.70$0.70 / $2.20
or:openai/o4-mini:batchpinnable$0.55 / $2.20 $0.55 – $0.55$0.55 / $2.20
or:openai/gpt-5.6-luna:batchpinnable$0.10 / $0.60 $0.10 – $0.10$0.10 / $0.60
or:google/gemini-3.5-flash:batchpinnable$0.75 / $4.50 $0.75 – $0.75$0.75 / $4.50
or:openai/gpt-5.6-luna-pro:batchpinnable$0.10 / $0.60 $0.10 – $0.10$0.10 / $0.60
or:qwen/qwen3-maxpinnable$0.78 / $3.90 $0.78 – $0.78$0.78 / $3.90
or:qwen/qwen3-coder-pluspinnable$0.65 / $3.25 $0.65 – $0.65$0.65 / $3.25
or:qwen/qwen3-30b-a3bpinnable$0.12 / $0.50 $0.12 – $0.12$0.12 / $0.50
or:sakana/sakana-namazupinnable$0.95 / $4.00 $0.95 – $0.95$0.95 / $4.00
or:upstage/solar-pro4pinnable$0.03 / $0.12 $0.03 – $0.03$0.03 / $0.12
or:openai/o3-mini-high:batchpinnable$0.55 / $2.20 $0.55 – $0.55$0.55 / $2.20
or:deepseek/deepseek-v4-flashpinnable$0.09 / $0.17 $0.09 – $0.09$0.09 / $0.17
or:deepseek/deepseek-v3.1-terminuspinnable$0.27 / $1.00 $0.27 – $0.27$0.27 / $1.00
or:qwen/qwen3-32bpinnable$0.08 / $0.28 $0.08 – $0.08$0.08 / $0.28
or:qwen/qwen3-235b-a22bpinnable$0.46 / $1.82 $0.46 – $0.46$0.46 / $1.82
or:bytedance-seed/seed-2.0-codepinnable$0.50 / $3.00 $0.50 – $0.50$0.50 / $3.00
or:perceptron/perceptron-mk1pinnable$0.15 / $1.50 $0.15 – $0.15$0.15 / $1.50
or:openai/gpt-mini-latestpinnable$0.75 / $4.50 $0.75 – $0.75$0.75 / $4.50
or:inclusionai/ling-2.6-1tpinnable$0.07 / $0.63 $0.07 – $0.07$0.07 / $0.63
or:google/gemini-3.7-flashpinnable$0.75 / $3.75 $0.75 – $0.75$0.75 / $3.75
or:nvidia/nemotron-3.5-lightning:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:deepseek/deepseek-v4-pro-0813pinnable$0.66 / $1.98 $0.66 – $0.66$0.66 / $1.98
or:qwen/qwen3-next-80b-a3b-thinkingpinnable$0.15 / $1.20 $0.15 – $0.15$0.15 / $1.20
or:tencent/hy3-previewpinnable$0.18 / $0.60 $0.18 – $0.18$0.18 / $0.60
or:bytedance-seed/seed-2-1-turbopinnable$0.50 / $2.50 $0.50 – $0.50$0.50 / $2.50
or:qwen/qwen3-14bpinnable$0.12 / $0.24 $0.12 – $0.12$0.12 / $0.24
or:google/gemma-4-31b-it:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:qwen/qwen3-coder-flashpinnable$0.20 / $0.97 $0.20 – $0.20$0.20 / $0.97
or:google/gemini-3.1-flash-litepinnable$0.25 / $1.50 $0.25 – $0.25$0.25 / $1.50
or:ibm-granite/granite-4.1-8bpinnable$0.05 / $0.10 $0.05 – $0.05$0.05 / $0.10
or:google/gemini-3.1-flash-lite:batchpinnable$0.13 / $0.75 $0.13 – $0.13$0.13 / $0.75
or:moonshotai/kimi-k2.7-code:batchpinnable$0.95 / $4.00 $0.95 – $0.95$0.95 / $4.00
or:dots-studio/dots-3-note-preview:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:qwen/qwen3.8-27bpinnable$0.42 / $3.00 $0.42 – $0.42$0.42 / $3.00
or:google/gemini-3.6-flashpinnable$0.75 / $3.75 $0.75 – $0.75$0.75 / $3.75
or:meta/muse-spark-1.2-contributorpinnable$0.10 / $0.20 $0.10 – $0.10$0.10 / $0.20
or:deepseek/deepseek-v4-flash-vision-exppinnable$0.22 / $0.66 $0.22 – $0.22$0.22 / $0.66
or:mistralai/ministral-8bpinnable$0.11 / $0.11 $0.11 – $0.11$0.11 / $0.11
or:nex-agi/nex-n2-propinnable$0.25 / $1.00 $0.25 – $0.25$0.25 / $1.00
or:qwen/qwen3-next-80b-a3b-instructpinnable$0.10 / $1.10 $0.10 – $0.10$0.10 / $1.10
or:openai/gpt-5.6-sol-pro:batchpinnable$1.00 / $5.00 $1.00 – $1.00$1.00 / $5.00
or:qwen/qwen-plus-2025-07-28pinnable$0.26 / $0.78 $0.26 – $0.26$0.26 / $0.78
or:thinkingmachines/inkling-small:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:qwen/qwen3.6-35b-a3bpinnable$0.10 / $0.90 $0.10 – $0.10$0.10 / $0.90
or:writer/palmyra-x5pinnable$0.60 / $6.00 $0.60 – $0.60$0.60 / $6.00
or:rekaai/reka-flash-3pinnable$0.10 / $0.20 $0.10 – $0.10$0.10 / $0.20
or:tencent/hy-mt2-7bpinnable$0.07 / $0.29 $0.07 – $0.07$0.07 / $0.29
or:openai/gpt-5.6-sol:batchpinnable$1.00 / $5.00 $1.00 – $1.00$1.00 / $5.00
or:nousresearch/hermes-4-405bpinnable$1.00 / $3.00 $1.00 – $1.00$1.00 / $3.00
or:moonshotai/kimi-k2.6pinnable$0.95 / $4.00 $0.95 – $0.95$0.95 / $4.00
or:qwen/qwen3-vl-8b-thinkingpinnable$0.18 / $2.10 $0.18 – $0.18$0.18 / $2.10
or:qwen/qwen3-vl-8b-instructpinnable$0.12 / $0.46 $0.12 – $0.12$0.12 / $0.46
or:qwen/qwen3-vl-30b-a3b-instructpinnable$0.15 / $0.60 $0.15 – $0.15$0.15 / $0.60
or:google/gemma-4-26b-a4b-it:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:qwen/qwen3.6-27bpinnable$0.30 / $2.00 $0.30 – $0.30$0.30 / $2.00
or:deepseek/deepseek-v4-propinnable$0.97 / $1.94 $0.97 – $0.97$0.97 / $1.94
or:nousresearch/hermes-4-70bpinnable$0.13 / $0.40 $0.13 – $0.13$0.13 / $0.40
or:mistralai/mistral-small-2603:batchpinnable$0.15 / $0.60 $0.15 – $0.15$0.15 / $0.60
or:qwen/qwen3.5-9bpinnable$0.10 / $0.15 $0.10 – $0.10$0.10 / $0.15
or:qwen/qwen3.5-9b:batchpinnable$0.17 / $0.25 $0.17 – $0.17$0.17 / $0.25
or:openai/gpt-5.4-minipinnable$0.75 / $4.50 $0.75 – $0.75$0.75 / $4.50
or:bytedance-seed/seed-2.0-litepinnable$0.25 / $2.00 $0.25 – $0.25$0.25 / $2.00
or:qwen/qwen3.5-397b-a17bpinnable$0.55 / $3.50 $0.55 – $0.55$0.55 / $3.50
or:minimax/minimax-m2.5pinnable$0.27 / $1.08 $0.27 – $0.27$0.27 / $1.08
or:z-ai/glm-5pinnable$0.60 / $1.92 $0.60 – $0.60$0.60 / $1.92
or:deepseek/deepseek-v4-flash-0731:batchpinnable$0.14 / $0.28 $0.14 – $0.14$0.14 / $0.28
or:poolside/laguna-xs-2.1pinnable$0.06 / $0.12 $0.06 – $0.06$0.06 / $0.12
or:qwen/qwen3.5-plus-02-15pinnable$0.26 / $1.56 $0.26 – $0.26$0.26 / $1.56
or:poolside/laguna-xs-2.1:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:baidu/ernie-4.5-vl-424b-a47bpinnable$0.42 / $1.25 $0.42 – $0.42$0.42 / $1.25
or:qwen/qwen-pluspinnable$0.26 / $0.78 $0.26 – $0.26$0.26 / $0.78
or:thedrummer/unslopnemo-12bpinnable$0.40 / $0.40 $0.40 – $0.40$0.40 / $0.40
or:aion-labs/aion-2.0pinnable$0.80 / $1.60 $0.80 – $0.80$0.80 / $1.60
or:deepseek/deepseek-chat-v3.1pinnable$0.55 / $1.65 $0.55 – $0.55$0.55 / $1.65
or:mistralai/mistral-medium-3.1pinnable$0.40 / $2.00 $0.40 – $0.40$0.40 / $2.00
or:nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:nvidia/nemotron-3-super-120b-a12b:freepinnable$0.00 / $0.00 $0.00 – $0.00$0.00 / $0.00
or:qwen/qwen3-vl-32b-instructpinnable$0.10 / $0.42 $0.10 – $0.10$0.10 / $0.42
or:ibm-granite/granite-4.0-h-micropinnable$0.02 / $0.11 $0.02 – $0.02$0.02 / $0.11
or:mistralai/mistral-medium-3.1:batchpinnable$0.40 / $2.00 $0.40 – $0.40$0.40 / $2.00
or:mistralai/codestral-2508:batchpinnable$0.30 / $0.90 $0.30 – $0.30$0.30 / $0.90
or:openai/gpt-oss-120b:batchpinnable$0.15 / $0.60 $0.15 – $0.15$0.15 / $0.60
or:openai/gpt-oss-20bpinnable$0.03 / $0.13 $0.03 – $0.03$0.03 / $0.13
or:openai/gpt-oss-20b:batchpinnable$0.05 / $0.20 $0.05 – $0.05$0.05 / $0.20
or:mistralai/codestral-2508pinnable$0.30 / $0.90 $0.30 – $0.30$0.30 / $0.90
or:qwen/qwen3-coder-30b-a3b-instructpinnable$0.07 / $0.28 $0.07 – $0.07$0.07 / $0.28
or:bytedance/ui-tars-1.5-7bpinnable$0.10 / $0.20 $0.10 – $0.10$0.10 / $0.20
or:google/gemini-2.5-flash-litepinnable$0.10 / $0.40 $0.10 – $0.10$0.10 / $0.40
or:openai/gpt-5:batchpinnable$0.63 / $5.00 $0.63 – $0.63$0.63 / $5.00
or:openai/gpt-5-minipinnable$0.25 / $2.00 $0.25 – $0.25$0.25 / $2.00
or:openai/gpt-5-nanopinnable$0.05 / $0.40 $0.05 – $0.05$0.05 / $0.40
or:morph/morph-v3-largepinnable$0.90 / $1.90 $0.90 – $0.90$0.90 / $1.90
or:google/gemini-2.5-flashpinnable$0.30 / $2.50 $0.30 – $0.30$0.30 / $2.50
or:google/gemini-2.5-pro:batchpinnable$0.63 / $5.00 $0.63 – $0.63$0.63 / $5.00
or:mistralai/mistral-medium-3pinnable$0.40 / $2.00 $0.40 – $0.40$0.40 / $2.00
or:qwen/qwen3-8bpinnable$0.12 / $0.46 $0.12 – $0.12$0.12 / $0.46
or:openai/gpt-4.1:batchpinnable$1.00 / $4.00 $1.00 – $1.00$1.00 / $4.00
or:openai/gpt-4.1-mini:batchpinnable$0.20 / $0.80 $0.20 – $0.20$0.20 / $0.80
or:openai/gpt-4.1-nano:batchpinnable$0.05 / $0.20 $0.05 – $0.05$0.05 / $0.20
or:meta-llama/llama-4-scoutpinnable$0.10 / $0.30 $0.10 – $0.10$0.10 / $0.30
or:moonshotai/kimi-k2pinnable$0.57 / $2.30 $0.57 – $0.57$0.57 / $2.30
or:cognitivecomputations/dolphin-mistral-24b-venice-editionpinnable$0.20 / $0.90 $0.20 – $0.20$0.20 / $0.90
or:tencent/hunyuan-a13b-instructpinnable$0.14 / $0.57 $0.14 – $0.14$0.14 / $0.57
or:minimax/minimax-01pinnable$0.20 / $1.10 $0.20 – $0.20$0.20 / $1.10
or:deepseek/deepseek-chatpinnable$0.32 / $0.89 $0.32 – $0.32$0.32 / $0.89
or:sao10k/l3.3-euryale-70bpinnable$0.65 / $0.75 $0.65 – $0.65$0.65 / $0.75
or:cohere/command-r7b-12-2024pinnable$0.04 / $0.15 $0.04 – $0.04$0.04 / $0.15
or:meta-llama/llama-3.3-70b-instructpinnable$0.10 / $0.32 $0.10 – $0.10$0.10 / $0.32
or:amazon/nova-lite-v1pinnable$0.06 / $0.24 $0.06 – $0.06$0.06 / $0.24
or:amazon/nova-micro-v1pinnable$0.04 / $0.14 $0.04 – $0.04$0.04 / $0.14
or:amazon/nova-pro-v1pinnable$0.80 / $3.20 $0.80 – $0.80$0.80 / $3.20
or:qwen/qwen-2.5-coder-32b-instructpinnable$0.66 / $1.00 $0.66 – $0.66$0.66 / $1.00
or:mistralai/mistral-small-3.1-24b-instructpinnable$0.35 / $0.56 $0.35 – $0.35$0.35 / $0.56
or:google/gemma-3-12b-itpinnable$0.05 / $0.15 $0.05 – $0.05$0.05 / $0.15
or:qwen/qwen2.5-vl-72b-instructpinnable$0.80 / $1.00 $0.80 – $0.80$0.80 / $1.00
or:mistralai/mistral-nemopinnable$0.02 / $0.03 $0.02 – $0.02$0.02 / $0.03
or:openai/gpt-4o-mini-2024-07-18pinnable$0.15 / $0.60 $0.15 – $0.15$0.15 / $0.60
or:openai/gpt-4o-mini:batchpinnable$0.07 / $0.30 $0.07 – $0.07$0.07 / $0.30
or:google/gemma-2-27b-itpinnable$0.65 / $0.65 $0.65 – $0.65$0.65 / $0.65
or:microsoft/wizardlm-2-8x22bpinnable$0.62 / $0.62 $0.62 – $0.62$0.62 / $0.62
or:anthropic/claude-3-haikupinnable$0.25 / $1.25 $0.25 – $0.25$0.25 / $1.25
or:openai/gpt-3.5-turbo-0613pinnable$1.00 / $2.00 $1.00 – $1.00$1.00 / $2.00
or:gryphe/mythomax-l2-13bpinnable$0.06 / $0.06 $0.06 – $0.06$0.06 / $0.06
or:openai/gpt-3.5-turbopinnable$0.50 / $1.50 $0.50 – $0.50$0.50 / $1.50
or:cohere/command-r-08-2024pinnable$0.15 / $0.60 $0.15 – $0.15$0.15 / $0.60
or:sao10k/l3.1-euryale-70bpinnable$0.85 / $0.85 $0.85 – $0.85$0.85 / $0.85
or:nousresearch/hermes-3-llama-3.1-70bpinnable$0.70 / $0.70 $0.70 – $0.70$0.70 / $0.70
or:openai/gpt-3.5-turbo:batchpinnable$0.25 / $0.75 $0.25 – $0.25$0.25 / $0.75
glm-4.6$0.60 / $2.20 $0.60 – $0.60$0.60 / $2.20
glm-4.7$0.35 / $1.10 $0.35 – $1.40$1.40 / $4.4075% off
glm-5.1$0.35 / $1.10 $0.35 – $1.40$1.40 / $4.4075% off
glm-5.2$0.35 / $1.10 $0.35 – $1.40$1.40 / $4.4075% off
kimi-for-coding$0.18 / $0.90 $0.18 – $0.60$0.60 / $3.0070% off
gpt-5.5$4.50 / $27.00 $4.50 – $5.00$5.00 / $30.0010% off
minimax-m2$0.05 / $0.20 $0.05 – $0.25$0.25 / $1.0080% off
minimax-m2.1$0.06 / $0.19 $0.06 – $0.29$0.29 / $0.9580% off
minimax-m2.1-highspeed$0.06 / $0.19 $0.06 – $0.29$0.29 / $0.9580% off
minimax-m2.5$0.03 / $0.23 $0.03 – $0.15$0.15 / $1.1580% off
minimax-m2.5-highspeed$0.04 / $0.34 $0.04 – $0.15$0.15 / $1.1570% off
qwen3.8-max / /
grok-4.6 / / 97% off
qwen3.8-flash / /
gpt-5-mini / / 60% off
gpt-5-nano / / 50% off
o4-mini / / 40% off
gpt-5.5-mini / / 55% off
gpt-5.1-codex-mini / / 55% off
gpt-5.5-codex / / 30% off
gpt-5.3-codex-spark / / 10% off
codex-mini-latest / / 40% off
gpt-4.1-mini / / 50% off
gpt-5-codex / / 30% off

Panel Mode — need a specific model?

Smart routing is the default — but judge ensembles, cross-model evals, and reproducible research need exact models. Models tagged pinnable can be pinned strictly (model: "pin:gpt-4o-mini") or queried as a panel — one prompt across up to 10 models in a single POST /v1/panel call, each answer labeled with the model that really served it, never a silent substitution. Enable it per key in the dashboard. Panel Mode docs →

Prices are per million tokens and update live as supply changes. See the docs to get started, or compare Flow AI to OpenRouter.