llmkit · pricing

LLM API Pricing

A free reference to the providers’ own API pricing — not llmkit’s (llmkit is free and open source). Input, output, and cache rates for every major provider, in USD per million tokens. Cheapest model first — lower is better.

Updated 2026-10-21 · 270 models · source: llm-pricing feed

mistrallabs-devstral-small-2512$0.00$0.00—256K
mistrallabs-leanstral-1-5-1$0.00$0.00—262K
googlelyria-3-clip-preview$0.00$0.00—1M
googlelyria-3-pro-preview$0.00$0.00—1M
groqallam-2-7b$0.00$0.00—4K
togetherailiquidai/lfm2-24b-a2b$0.03$0.12—32K
groqmeta-llama/llama-prompt-guard-2-22m$0.03$0.03—0K
groqmeta-llama/llama-prompt-guard-2-86m$0.04$0.04—0K
openaigpt-5-nano$0.05$0.40$0.01400K
togetheraiopenai/gpt-oss-20b$0.05$0.20—131K
fireworks-aiaccounts/fireworks/models/nemotron-lightning-3p5-30b-a3b$0.05$0.20$0.01262K
groqllama-3.1-8b-instant$0.05$0.08—131K
togetheraigoogle/gemma-3n-e4b-it$0.06$0.12—32K
fireworks-aiaccounts/fireworks/models/gpt-oss-20b$0.07$0.30$0.04131K
googlegemini-2.0-flash-lite$0.07$0.30—1M
groqopenai/gpt-oss-safeguard-20b$0.07$0.30$0.04131K
groqopenai/gpt-oss-20b$0.07$0.30$0.04131K
openaigpt-6-luna$0.10$0.50$0.011M
openaigpt-4.1-nano$0.10$0.40$0.031M
mistraldevstral-small-2507$0.10$0.30—128K
mistralvoxtral-small-2507$0.10$0.40—32K
mistraldevstral-small-2505$0.10$0.30—128K
mistralmistral-small-2506$0.10$0.30—128K
mistralministral-3b-2512$0.10$0.10$0.01131K
mistralvoxtral-small-latest$0.10$0.40—32K
mistralministral-3b-latest$0.10$0.10$0.01131K
googlegemini-2.5-flash-lite$0.10$0.40$0.011M
googlegemini-2.0-flash$0.10$0.40$0.031M
anthropicclaude-haiku-5-5$0.10$0.50$0.011M
groqmeta-llama/llama-4-scout-17b-16e-instruct$0.11$0.34—131K
togetheraideepseek-ai/deepseek-v4-flash-0731$0.14$0.28$0.031M
togetheraimeta-llama/meta-llama-3-8b-instruct-lite$0.14$0.14—8K
fireworks-aiaccounts/fireworks/models/deepseek-v4-flash$0.14$0.28$0.031M
deepseekdeepseek-reasoner$0.14$0.28$0.001M
deepseekdeepseek-chat$0.14$0.28$0.001M
openaigpt-4o-mini$0.15$0.60$0.07128K
togetheraiopenai/gpt-oss-120b$0.15$0.60—131K
togetherainvidia/nvidia-nemotron-3.5-super-vl$0.15$0.50$0.02262K
togetheraizai-org/glm-5.3-flash$0.15$0.50$0.031M
togetheraiessentialai/rnj-1-instruct$0.15$0.15—32K
mistralministral-8b-latest$0.15$0.15$0.01262K
mistralpixtral-12b$0.15$0.15—128K
mistralopen-mistral-nemo$0.15$0.15—128K
mistralmistral-small-latest$0.15$0.60$0.01262K
mistralmistral-nemo$0.15$0.15—128K
mistralmistral-small-2603$0.15$0.60$0.01262K
mistralministral-8b-2512$0.15$0.15$0.01262K
fireworks-aiaccounts/fireworks/routers/glm-flash-latest$0.15$0.50$0.031M
fireworks-aiaccounts/fireworks/models/glm-5p3-flash$0.15$0.50$0.031M
fireworks-aiaccounts/fireworks/models/gpt-oss-120b$0.15$0.60$0.01131K
deepseekdeepseek-flash$0.15$0.60$0.001M
deepseekdeepseek-v4-flash$0.15$0.60$0.001M
deepseekdeepseek-v4-flash-vision-exp$0.15$0.60$0.001M
groqopenai/gpt-oss-120b$0.15$0.60$0.07131K
togetheraiqwen/qwen3.5-9b$0.17$0.25—262K
openaigpt-5.4-nano$0.20$1.25$0.02400K
openaigpt-5.6-luna$0.20$1.20$0.021M
togetheraiqwen/qwen3-235b-a22b-instruct-2507-tput$0.20$0.60—262K
mistralministral-14b-2512$0.20$0.20$0.02262K
googlegemini-embedding-2$0.20$0.00—8K
openaigpt-5-mini$0.25$2.00$0.03400K
openaigpt-5.1-codex-mini$0.25$2.00$0.03400K
mistralopen-mistral-7b$0.25$0.25—8K
googlegemini-3.1-flash-lite$0.25$1.50$0.031M
googlegemini-3.1-flash-lite-image$0.25$30.00—65K
googlegemini-3.1-flash-lite-preview$0.25$1.50$0.031M
anthropicclaude-3-haiku-20240307$0.25$1.25$0.03200K
togetheraipearl-ai/gemma-4-31b-it$0.28$0.86—32K
groqqwen/qwen3-32b$0.29$0.59—131K
togetheraiqwen/qwen2.5-7b-instruct-turbo$0.30$0.30—32K
togetheraideepseek-ai/deepseek-v4.1-flash$0.30$1.20$0.011M
togetheraiminimaxai/minimax-m2.7$0.30$1.20$0.06196K
togetheraiminimaxai/minimax-m2.5$0.30$1.20$0.06204K
togetheraiminimaxai/minimax-m3$0.30$1.20$0.06524K
mistralcodestral-latest$0.30$0.90$0.03256K
mistralcodestral-2508$0.30$0.90$0.03256K
fireworks-aiaccounts/fireworks/routers/deepseek-flash-latest$0.30$1.20$0.011M
fireworks-aiaccounts/fireworks/routers/minimax-latest$0.30$1.20$0.06512K
fireworks-aiaccounts/fireworks/models/minimax-m3$0.30$1.20$0.06512K
fireworks-aiaccounts/fireworks/models/minimax-m2p7$0.30$1.20$0.06196K
fireworks-aiaccounts/fireworks/models/deepseek-v4p1-flash-1017$0.30$1.20$0.011M
fireworks-aiaccounts/fireworks/models/deepseek-v4p1-flash$0.30$1.20$0.011M
googlegemini-2.5-flash-image$0.30$30.00$0.0732K
googlegemini-2.5-flash$0.30$2.50$0.031M
googlegemini-flash-lite-latest$0.30$2.50$0.031M
googlegemini-3.5-flash-lite$0.30$2.50$0.031M
togetheraigoogle/gemma-4-31b-it$0.39$0.97—262K
openaigpt-4.1-mini$0.40$1.60$0.101M
togetheraireflection/beam-1.0-501b-a23b$0.40$1.20$0.041M
mistralmistral-medium-2505$0.40$2.00—131K
mistraldevstral-medium-2507$0.40$2.00—128K
mistraldevstral-medium-latest$0.40$2.00—262K
mistraldevstral-latest$0.40$2.00—262K
mistralmistral-medium-2508$0.40$2.00—262K
mistraldevstral-2512$0.40$2.00—262K
fireworks-aiaccounts/fireworks/models/qwen3p7-plus$0.40$1.60$0.08262K
openaigpt-3.5-turbo$0.50$1.50—16K
togetheraiqwen/qwen3-coder-next-fp8$0.50$1.20—262K
togetheraiqwen/qwen3.6-plus$0.50$3.00—1M
togetheraimoonshotai/kimi-k2.5$0.50$2.80—262K
mistralmagistral-small$0.50$1.50—128K
mistralmistral-large-2512$0.50$1.50$0.05262K
mistralmistral-large-latest$0.50$1.50$0.05262K
googlegemini-3.1-flash-image$0.50$60.00—131K
googlegemini-3.1-flash-image-preview$0.50$60.00—65K
googlegemini-3-flash-preview$0.50$3.00$0.051M
googlegemini-2.5-flash-preview-tts$0.50$10.00—8K
groqllama-3.3-70b-versatile$0.59$0.79—131K
togetheraiqwen/qwen3.5-397b-a17b$0.60$3.60$0.35262K
togetherainvidia/nemotron-3-ultra-550b-a55b$0.60$3.60$0.20512K
togetheraideepseek-ai/deepseek-v3-1$0.60$1.70—131K
fireworks-aiaccounts/fireworks/models/nemotron-3-ultra-nvfp4$0.60$2.40$0.12262K
groqqwen/qwen3.6-27b$0.60$3.00$0.30131K
deepseekdeepseek-v4-pro$0.66$1.98$0.021M
mistralmistral-large-4$0.68$2.09$0.071M
mistralopen-mixtral-8x7b$0.70$0.70—32K
openaigpt-5.4-mini$0.75$4.50$0.07400K
googlegemini-3.7-flash$0.75$3.75$0.071M
googlegemini-3.6-flash$0.75$3.75$0.071M
googlegemini-flash-latest$0.75$3.75$0.071M
googlegemini-3.1-flash-live-preview$0.75$4.50—131K
googlegemini-3.8-flash$0.75$3.75$0.071M
anthropicclaude-3-5-haiku-20241022$0.80$4.00$0.08200K
anthropicclaude-3-5-haiku-latest$0.80$4.00$0.08200K
groqqwen/qwen3.8-27b$0.80$4.00—131K
togetheraimoonshotai/kimi-k2.7-code$0.95$4.00$0.19262K
fireworks-aiaccounts/fireworks/models/kimi-k2p7-code$0.95$4.00$0.19262K
fireworks-aiaccounts/fireworks/models/kimi-k2p6$0.95$4.00$0.16262K
togetheraizai-org/glm-5$1.00$3.20—202K
togetheraithinkingmachines/inkling$1.00$4.05$0.17524K
fireworks-aiaccounts/fireworks/models/inkling$1.00$4.05$0.171M
xaigrok-build-0.1$1.00$2.00$0.20256K
googlegemini-2.5-pro-preview-tts$1.00$20.00—8K
googlegemini-3.1-flash-tts-preview$1.00$20.00—8K
anthropicclaude-haiku-4-5$1.00$5.00$0.10200K
anthropicclaude-haiku-4-5-20251001$1.00$5.00$0.10200K
togetheraimeta-llama/llama-3.3-70b-instruct-turbo$1.04$1.04—131K
openaio3-mini$1.10$4.40$0.55200K
openaio4-mini$1.10$4.40$0.28200K
togetheraimoonshotai/kimi-k2.6$1.20$4.50$0.20262K
openaigpt-5-chat-latest$1.25$10.00$0.12400K
openaigpt-5$1.25$10.00$0.12400K
openaigpt-5.1-codex$1.25$10.00$0.12400K
openaigpt-5.1$1.25$10.00$0.12400K
openaigpt-5.1-codex-max$1.25$10.00$0.12400K
openaigpt-5-codex$1.25$10.00$0.12400K
openaigpt-5.1-chat-latest$1.25$10.00$0.12128K
togetheraideepseek-ai/deepseek-v3$1.25$1.25—131K
togetheraideepcogito/cogito-v2-1-671b$1.25$1.25—163K
togetheraimeta-models/muse-spark-open-816b-a42b$1.25$4.25$0.151M
fireworks-aiaccounts/fireworks/models/muse-spark-open$1.25$4.25$0.151M
xaigrok-4.20-multi-agent-0309$1.25$2.50$0.201M
xaigrok-4.20-0309-reasoning$1.25$2.50$0.201M
xaigrok-4.20-0309-non-reasoning$1.25$2.50$0.201M
xaigrok-4.3$1.25$2.50$0.201M
googlegemini-2.5-computer-use-preview-10-2025$1.25$10.00—128K
googlegemini-2.5-pro$1.25$10.00$0.121M
togetheraideepseek-ai/deepseek-v4-pro-0813$1.32$3.96$0.131M
togetheraizai-org/glm-5.3$1.40$4.40$0.261M
togetheraizai-org/glm-5.1$1.40$4.40$0.26202K
togetheraizai-org/glm-5.2$1.40$4.40$0.261M
mistralglm-5-2$1.40$4.40$0.141M
mistralzai-glm-5-2$1.40$4.40$0.141M
mistralzai-glm-5-3$1.40$4.40$0.141M
fireworks-aiaccounts/fireworks/routers/glm-latest$1.40$4.40$0.261M
fireworks-aiaccounts/fireworks/models/glm-5p1$1.40$4.40$0.26202K
fireworks-aiaccounts/fireworks/models/glm-5p2$1.40$4.40$0.141M
fireworks-aiaccounts/fireworks/models/glm-5p3$1.40$4.40$0.261M
mistralmistral-medium-latest$1.50$7.50$0.15262K
mistralmistral-medium-2604$1.50$7.50$0.15262K
googlegemini-3.5-flash$1.50$9.00$0.151M
googlegemini-omni-flash-preview$1.50$17.50—131K
togetheraideepseek-ai/deepseek-v4-pro$1.74$3.48$0.20512K
fireworks-aiaccounts/fireworks/models/deepseek-v4-pro$1.74$3.48$0.141M
openaigpt-5.2-chat-latest$1.75$14.00$0.17128K
openaigpt-5.3-chat-latest$1.75$14.00$0.17128K
openaigpt-5.2-codex$1.75$14.00$0.17400K
openaigpt-5.3-codex$1.75$14.00$0.17400K
openaigpt-5.3-codex-spark$1.75$14.00$0.17128K
openaigpt-5.2$1.75$14.00$0.17400K
fireworks-aiaccounts/fireworks/routers/kimi-k2p7-code-fast$1.90$8.00$0.38262K
openaigpt-4.1$2.00$8.00$0.501M
openaigpt-6.1-sol$2.00$10.00$0.101M
openaigpt-6-sol$2.00$10.00$0.201M
openaigpt-5.6-terra$2.00$12.00$0.201M
openaio4-mini-deep-research$2.00$8.00$0.50200K
openaio3$2.00$8.00$0.50200K
togetheraiqwen/qwen3-coder-480b-a35b-instruct-fp8$2.00$2.00—262K
mistralmistral-large-2411$2.00$6.00—131K
mistralmagistral-medium-latest$2.00$5.00—262K
mistralpixtral-large-latest$2.00$6.00—128K
mistralopen-mixtral-8x22b$2.00$6.00—64K
fireworks-aiaccounts/fireworks/routers/kimi-k2p6-fast$2.00$8.00$0.30262K
fireworks-aiaccounts/fireworks/routers/qwen-max-latest$2.00$6.00$0.25262K
fireworks-aiaccounts/fireworks/routers/kimi-k2p6-turbo$2.00$8.00$0.30262K
fireworks-aiaccounts/fireworks/models/qwen3p8-2p4t-a95b$2.00$6.00$0.25262K
fireworks-aiaccounts/fireworks/models/qwen3p8-max$2.00$6.00$0.25262K
xaigrok-4.7$2.00$6.00$0.50500K
xaigrok-4.6$2.00$6.00$0.50500K
xaigrok-4.5$2.00$6.00$0.30500K
googlegemini-3.1-pro-preview$2.00$12.00$0.201M
googlegemini-3-pro-image$2.00$120.00—65K
googledeep-research-preview-04-2026$2.00$12.00$0.20131K
googlegemini-pro-latest$2.00$12.00$0.201M
googlegemini-3-pro-image-preview$2.00$120.00—131K
googlegemini-3.1-pro-preview-customtools$2.00$12.00$0.201M
googlegemini-3-pro-preview$2.00$12.00$0.201M
googledeep-research-max-preview-04-2026$2.00$12.00$0.20131K
googlegemini-4-argon$2.00$10.00$0.101M
anthropicclaude-sonnet-5$2.00$10.00$0.201M
anthropicclaude-sonnet-5-5$2.00$10.00$0.101M
fireworks-aiaccounts/fireworks/routers/glm-5p3-fast$2.10$6.60$0.391M
fireworks-aiaccounts/fireworks/routers/glm-fast-latest$2.10$6.60$0.391M
fireworks-aiaccounts/fireworks/routers/glm-5p2-fast$2.10$6.60$0.211M
openaigpt-4o$2.50$10.00$1.25128K
openaigpt-5.4$2.50$15.00$0.251M
openaigpt-4o-2024-08-06$2.50$10.00$1.25128K
openaigpt-4o-2024-11-20$2.50$10.00$1.25128K
togetheraiqwen/qwen3.7-max$2.50$7.50$0.501M
fireworks-aiaccounts/fireworks/routers/glm-5p1-fast$2.80$8.80$0.52202K
togetheraimoonshotai/kimi-k3$3.00$15.00$0.301M
togetheraideepseek-ai/deepseek-r1$3.00$7.00—163K
fireworks-aiaccounts/fireworks/routers/kimi-latest$3.00$15.00$0.301M
fireworks-aiaccounts/fireworks/models/kimi-k3$3.00$15.00$0.301M
fireworks-aiaccounts/fireworks/models/ember-1$3.00$15.00$0.301M
anthropicclaude-sonnet-4-6$3.00$15.00$0.301M
anthropicclaude-3-sonnet-20240229$3.00$15.00$0.30200K
anthropicclaude-3-5-sonnet-20241022$3.00$15.00$0.30200K
anthropicclaude-sonnet-4-5$3.00$15.00$0.30200K
anthropicclaude-sonnet-4-0$3.00$15.00$0.30200K
anthropicclaude-3-7-sonnet-20250219$3.00$15.00$0.30200K
anthropicclaude-3-5-sonnet-20240620$3.00$15.00$0.30200K
anthropicclaude-sonnet-4-20250514$3.00$15.00$0.30200K
anthropicclaude-sonnet-4-5-20250929$3.00$15.00$0.30200K
googlegemini-3.5-live-translate-preview$3.50$21.00—16K
openaigpt-5.6-sol$4.00$20.00$0.401M
openaigpt-realtime-2.1$4.00$24.00$0.40128K
openaigpt-5.6$4.00$20.00$0.401M
openaigpt-daybreak-blue-latest$4.00$20.00$0.401M
anthropicclaude-opus-5-5$4.00$20.00$0.201M
fireworks-aiaccounts/fireworks/routers/kimi-fast-latest$4.50$22.50$0.451M
fireworks-aiaccounts/fireworks/routers/kimi-k3-fast$4.50$22.50$0.451M
openaigpt-image-2$5.00$30.00$1.25—
openaigpt-5.5$5.00$30.00$0.501M
openaigpt-4o-2024-05-13$5.00$15.00—128K
anthropicclaude-opus-4-8$5.00$25.00$0.501M
anthropicclaude-opus-4-7$5.00$25.00$0.501M
anthropicclaude-opus-4-6$5.00$25.00$0.501M
anthropicclaude-opus-4-5$5.00$25.00$0.50200K
anthropicclaude-opus-5$5.00$25.00$0.501M
anthropicclaude-opus-4-5-20251101$5.00$25.00$0.50200K
openaigpt-4-turbo$10.00$30.00—128K
openaio3-deep-research$10.00$40.00$2.50200K
openaigpt-6-astra$10.00$50.00$1.001M
anthropicclaude-fable-5$10.00$50.00$1.001M
anthropicclaude-fable-5-1$10.00$50.00$0.251M
openaigpt-daybreak-red-latest$12.50$75.00$1.25400K
openaio1$15.00$60.00$7.50200K
openaigpt-5-pro$15.00$120.00—400K
anthropicclaude-opus-4-1-20250805$15.00$75.00$1.50200K
anthropicclaude-opus-4-1$15.00$75.00$1.50200K
anthropicclaude-opus-4-0$15.00$75.00$1.50200K
anthropicclaude-3-opus-20240229$15.00$75.00$1.50200K
anthropicclaude-opus-4-20250514$15.00$75.00$1.50200K
openaio3-pro$20.00$80.00—200K
openaigpt-5.2-pro$21.00$168.00—400K
openaigpt-4$30.00$60.00—8K
openaigpt-5.4-pro$30.00$180.00—1M
openaigpt-5.5-pro$30.00$180.00—1M
openaio1-pro$150.00$600.00—200K

Prices are in USD per million tokens. — means the provider does not publish that rate. Cache read is the discounted rate for cached input tokens. Figures may lag provider changes — verify against the provider before relying on them for billing.

Pricing data from models.dev, used under the MIT License, via the llm-pricing feed. First-party provider pages are cited per record in the feed.