Skip to content
The Price of Intelligence

What an AI answer really costs

First-party list prices, published by the labs themselves — with the server-side web-search fees that get charged on top of tokens and that no vendor prints beside the token rate. No reseller rates, no gateway markups, no averaged numbers.

Last verified
  • models.dev 2026-07-31 00:08 UTC
  • litellm 2026-07-31 00:08 UTC
  • openrouter 2026-07-31 00:08 UTC

First-party only

Only prices set by the lab that made the model. Resellers quote the same model at their own margin — one gateway lists Claude Sonnet 4.6 at $3.60/$18.00 where Anthropic charges $3.00/$15.00.

Tool fees included

A grounded answer is billed twice: once for tokens, once per server-side search. That second charge is missing from every price table we could find.

Dated, not asserted

Each source carries the moment it was last confirmed. Where two sources disagree we show the first-party figure and say so rather than averaging them away.

ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
Claude Opus 5claude-opus-52026-07-241M$5.00$25.00$0.50$0.01models.dev · LiteLLM
Claude Sonnet 5claude-sonnet-52026-06-291M$2.00$10.00$0.20$0.01models.dev · LiteLLM
Claude Fable 5claude-fable-52026-06-071M$10.00$50.00$1.00$0.01models.dev · LiteLLM
Claude Opus 4.8claude-opus-4-82026-05-281M$5.00$25.00$0.50$0.01models.dev · LiteLLM
Claude Opus 4.7claude-opus-4-72026-04-141M$5.00$25.00$0.50$0.01models.dev · LiteLLM
Claude Sonnet 4.6claude-sonnet-4-62026-02-171M$3.00$15.00$0.30$0.01models.dev · LiteLLM
Claude Opus 4.6claude-opus-4-62026-02-041M$5.00$25.00$0.50$0.01models.dev · LiteLLM
Claude Opus 4.5claude-opus-4-5-202511012025-11-24200K$5.00$25.00$0.50$0.01models.dev · LiteLLM
Claude Opus 4.5 (latest)claude-opus-4-52025-11-24200K$5.00$25.00$0.50$0.01models.dev · LiteLLM
Claude Haiku 4.5 (latest)claude-haiku-4-52025-10-15200K$1.00$5.00$0.10models.dev
Claude Haiku 4.5claude-haiku-4-5-202510012025-10-15200K$1.00$5.00$0.10models.dev
Claude Sonnet 4.5 (latest)claude-sonnet-4-5above 200K tokens: $6.00 in2025-09-291M$3.00$15.00$0.30$0.01models.dev · LiteLLM
Claude Sonnet 4.5claude-sonnet-4-5-20250929above 200K tokens: $6.00 in2025-09-291M$3.00$15.00$0.30$0.01models.dev · LiteLLM
Claude Opus 4.1 (latest)claude-opus-4-12025-08-05200K$15.00$75.00$1.50$0.01models.dev · LiteLLM
Claude Opus 4.1claude-opus-4-1-202508052025-08-05200K$15.00$75.00$1.50$0.01models.dev · LiteLLM
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
GPT-5.6 Solgpt-5.6-solabove 272K tokens: $10.00 in2026-07-091.1M$5.00$30.00$0.50models.dev
GPT-5.6 Lunagpt-5.6-lunaabove 272K tokens: $0.40 in2026-07-091.1M$0.20$1.20$0.02hand-verified
GPT-5.6gpt-5.6above 272K tokens: $10.00 in2026-07-091.1M$5.00$30.00$0.50models.dev
GPT-5.6 Terragpt-5.6-terraabove 272K tokens: $4.00 in2026-07-091.1M$2.00$12.00$0.20hand-verified
GPT-Realtime-2.1gpt-realtime-2.12026-07-06128K$4.00$24.00$0.40models.dev
GPT-5.5 Progpt-5.5-proabove 272K tokens: $60.00 in2026-04-231.1M$30.00$180.00models.dev
GPT-5.5gpt-5.5above 272K tokens: $10.00 in2026-04-231.1M$5.00$30.00$0.50models.dev
gpt-image-2gpt-image-22026-04-210$5.00$30.00$1.25models.dev
GPT-5.4 nanogpt-5.4-nano2026-03-17400K$0.20$1.25$0.02models.dev
GPT-5.4 minigpt-5.4-mini2026-03-17400K$0.75$4.50$0.07models.dev
GPT-5.4 Progpt-5.4-proabove 272K tokens: $60.00 in2026-03-051.1M$30.00$180.00models.dev
GPT-5.4gpt-5.4above 272K tokens: $5.00 in2026-03-051.1M$2.50$15.00$0.25models.dev
GPT-5.3 Chat (latest)gpt-5.3-chat-latest2026-03-03128K$1.75$14.00$0.17models.dev
GPT-5.3 Codex Sparkgpt-5.3-codex-spark2026-02-05128K$1.75$14.00$0.17models.dev
GPT-5.3 Codexgpt-5.3-codex2026-02-05400K$1.75$14.00$0.17models.dev
chatgpt-image-latestchatgpt-image-latest2025-12-160$5.00LiteLLM
GPT-5.2 Progpt-5.2-pro2025-12-11400K$21.00$168.00models.dev
GPT-5.2 Chatgpt-5.2-chat-latest2025-12-11128K$1.75$14.00$0.17models.dev
GPT-5.2gpt-5.22025-12-11400K$1.75$14.00$0.17models.dev
gpt-image-1.5gpt-image-1.5LiteLLM lists more than one entry for this model at different prices; token cost is models.dev's and the tool fee is omitted.2025-11-250
GPT-5.1gpt-5.12025-11-13400K$1.25$10.00$0.13models.dev
GPT-5 Progpt-5-pro2025-10-06400K$15.00$120.00models.dev
gpt-image-1-minigpt-image-1-miniLiteLLM lists more than one entry for this model at different prices; token cost is models.dev's and the tool fee is omitted.2025-09-260
GPT-5gpt-52025-08-07400K$1.25$10.00$0.13models.dev
GPT-5 Minigpt-5-mini2025-08-07400K$0.25$2.00$0.03models.dev
GPT-5 Nanogpt-5-nano2025-08-07400K$0.05$0.40$0.005models.dev
o3-proo3-pro2025-06-10200K$20.00$80.00models.dev
gpt-image-1gpt-image-1LiteLLM lists more than one entry for this model at different prices; token cost is models.dev's and the tool fee is omitted.2025-04-240
o3o32025-04-16200K$2.00$8.00$0.50models.dev
o4-minio4-mini2025-04-16200K$1.10$4.40$0.28models.dev
GPT-4.1 minigpt-4.1-mini2025-04-141.0M$0.40$1.60$0.10models.dev
GPT-4.1 nanogpt-4.1-nano2025-04-141.0M$0.10$0.40$0.03models.dev
GPT-4.1gpt-4.12025-04-141.0M$2.00$8.00$0.50models.dev
o1-proo1-pro2025-03-19200K$150.00$600.00models.dev
o3-minio3-mini2024-12-20200K$1.10$4.40$0.55models.dev
o1o12024-12-05200K$15.00$60.00$7.50models.dev
GPT-4o (2024-11-20)gpt-4o-2024-11-202024-11-20128K$2.50$10.00$1.25models.dev
GPT-4o (2024-08-06)gpt-4o-2024-08-062024-08-06128K$2.50$10.00$1.25models.dev
GPT-4o minigpt-4o-mini2024-07-18128K$0.15$0.60$0.07models.dev
GPT-4ogpt-4o2024-05-13128K$2.50$10.00$1.25$0.01models.dev · hand-verified
GPT-4o (2024-05-13)gpt-4o-2024-05-132024-05-13128K$5.00$15.00models.dev
text-embedding-3-largetext-embedding-3-large2024-01-258K$0.13freemodels.dev
text-embedding-3-smalltext-embedding-3-small2024-01-258K$0.02freemodels.dev
GPT-4 Turbogpt-4-turbo2023-11-06128K$10.00$30.00models.dev
GPT-4gpt-42023-11-068K$30.00$60.00models.dev
GPT-3.5-turbogpt-3.5-turbo2023-03-0116K$0.50$1.50freemodels.dev
text-embedding-ada-002text-embedding-ada-0022022-12-158K$0.10freemodels.dev
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
Gemini 3.5 Flash Litegemini-3.5-flash-lite2026-07-211.0M$0.30$2.50$0.03$0.01models.dev · LiteLLM
Gemini 3.6 Flashgemini-3.6-flash2026-07-211.0M$1.50$7.50$0.15$0.01models.dev · LiteLLM
Gemini Omni Flash Previewgemini-omni-flash-preview2026-06-30131K$1.50$17.50models.dev
Nano Banana 2 Litegemini-3.1-flash-lite-image2026-06-3066K$0.25$30.00models.dev
Gemini 3.5 Live Translate Previewgemini-3.5-live-translate-preview2026-06-0916K$3.50$21.00models.dev
Nano Banana 2gemini-3.1-flash-image2026-05-2866K$0.50$60.00$0.01models.dev · LiteLLM
Nano Banana Progemini-3-pro-image2026-05-28131K$2.00$120.00$0.01models.dev · LiteLLM
Gemini Flash Latestgemini-flash-latest2026-05-191.0M$1.50$9.00$0.15$0.04models.dev · LiteLLM
Gemini 3.5 Flashgemini-3.5-flash2026-05-191.0M$1.50$9.00$0.15$0.01models.dev · LiteLLM
Gemini 3.1 Flash Litegemini-3.1-flash-lite2026-05-071.0M$0.25$1.50$0.03$0.01models.dev · LiteLLM
Gemini Flash-Lite Latestgemini-flash-lite-latest2026-05-071.0M$0.25$1.50$0.03$0.04models.dev · LiteLLM
Gemini Embedding 2gemini-embedding-22026-04-228K$0.20freemodels.dev
Deep Research Preview (Apr-21-2026)deep-research-preview-04-2026above 200K tokens: $4.00 in2026-04-21131K$2.00$12.00$0.20models.dev
Deep Research Max Preview (Apr-21-2026)deep-research-max-preview-04-2026above 200K tokens: $4.00 in2026-04-21131K$2.00$12.00$0.20models.dev
Gemini 3.1 Flash TTS Previewgemini-3.1-flash-tts-preview2026-04-158K$1.00$20.00models.dev
Gemini Robotics-ER 1.6 Previewgemini-robotics-er-1.6-preview2026-04-14131K$1.00$5.00models.dev
Gemma 4 26B A4B ITgemma-4-26b-a4b-it2026-04-02262K
Gemma 4 31B ITgemma-4-31b-it2026-04-02262K
Veo 3.1 liteveo-3.1-lite-generate-preview2026-03-31480
Gemini 3.1 Flash Live Previewgemini-3.1-flash-live-preview2026-03-26131K$0.75$4.50models.dev
Lyria 3 Pro Previewlyria-3-pro-preview2026-03-251.0Mfreefreemodels.dev
Lyria 3 Clip Previewlyria-3-clip-preview2026-03-251.0Mfreefreemodels.dev
Gemini 3.1 Flash Lite Previewgemini-3.1-flash-lite-preview2026-03-031.0M$0.25$1.50$0.03$0.01models.dev · LiteLLM
Nano Banana 2gemini-3.1-flash-image-preview2026-02-2666K$0.50$60.00$0.01models.dev · LiteLLM
Gemini 3.1 Pro Preview Custom Toolsgemini-3.1-pro-preview-customtoolsabove 200K tokens: $4.00 in2026-02-191.0M$2.00$12.00$0.20$0.01models.dev · LiteLLM
Gemini 3.1 Pro Previewgemini-3.1-pro-previewabove 200K tokens: $4.00 in2026-02-191.0M$2.00$12.00$0.20$0.01models.dev · LiteLLM
Gemini 3 Flash Previewgemini-3-flash-preview2025-12-171.0M$0.50$3.00$0.05$0.01models.dev · LiteLLM
Nano Banana Progemini-3-pro-image-preview2025-11-20131K$2.00$120.00$0.01models.dev · LiteLLM
Gemini 3 Pro Previewgemini-3-pro-previewabove 200K tokens: $4.00 in2025-11-181.0M$2.00$12.00$0.20$0.01models.dev · LiteLLM
Veo 3.1veo-3.1-generate-preview2025-10-15480
Veo 3.1 fastveo-3.1-fast-generate-preview2025-10-15480
Gemini 2.5 Computer Use Preview 10-2025gemini-2.5-computer-use-preview-10-2025above 200K tokens: $2.50 in2025-10-07131K$1.25$10.00models.dev
Nano Bananagemini-2.5-flash-image2025-08-2633K$0.30$30.00$0.07$0.04models.dev · LiteLLM
Gemini 2.5 Flashgemini-2.5-flash2025-06-171.0M$0.30$2.50$0.03$0.04models.dev · LiteLLM
Gemini 2.5 Progemini-2.5-proabove 200K tokens: $2.50 in2025-06-171.0M$1.25$10.00$0.13$0.04models.dev · LiteLLM
Gemini 2.5 Flash-Litegemini-2.5-flash-lite2025-06-171.0M$0.10$0.40$0.01$0.04models.dev · LiteLLM
Gemini Embedding 001gemini-embedding-0012025-05-202K$0.15freemodels.dev
Gemini 2.5 Flash Preview TTSgemini-2.5-flash-preview-tts2025-05-018K$0.50$10.00models.dev
Gemini 2.5 Pro Preview TTSgemini-2.5-pro-preview-ttsabove 200K tokens: $2.50 in2025-05-018K$1.00$20.00$0.04models.dev · LiteLLM
Gemini 2.0 Flashgemini-2.0-flash2024-12-111.0M$0.10$0.40$0.03$0.04models.dev · LiteLLM
Gemini 2.0 Flash-Litegemini-2.0-flash-lite2024-12-111.0M$0.07$0.30$0.04models.dev · LiteLLM
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
Grok 4.5grok-4.5above 200K tokens: $4.00 in2026-07-08500K$2.00$6.00$0.30$0.005models.dev · hand-verified
Grok Imagine Video 1.5grok-imagine-video-1.52026-05-301K
Grok 4.3grok-4.3above 200K tokens: $2.50 in2026-04-171M$1.25$2.50$0.20$0.005models.dev · hand-verified
Grok Build 0.1grok-build-0.1above 200K tokens: $2.00 in2026-04-16256K$1.00$2.00$0.20$0.005models.dev · hand-verified
Grok Imagine Image Qualitygrok-imagine-image-quality2026-04-038K
Grok 4.20 (Non-Reasoning)grok-4.20-0309-non-reasoningabove 200K tokens: $2.50 in2026-03-091M$1.25$2.50$0.20$0.005models.dev · hand-verified
Grok 4.20 Multi-Agentgrok-4.20-multi-agent-0309above 200K tokens: $2.50 in2026-03-091M$1.25$2.50$0.20models.dev
Grok 4.20 (Reasoning)grok-4.20-0309-reasoningabove 200K tokens: $2.50 in2026-03-091M$1.25$2.50$0.20$0.005models.dev · hand-verified
Grok Imagine Videogrok-imagine-video2026-01-281K
Grok Imagine Imagegrok-imagine-image2026-01-288K
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
Muse Spark 1.1muse-spark-1.12026-04-081M$1.25$4.25$0.15models.dev
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
Mistral Medium (latest)mistral-medium-latest2026-04-29262K$1.50$7.50models.dev
Mistral Medium 3.5mistral-medium-26042026-04-29262K$1.50$7.50models.dev
Mistral Small (latest)mistral-small-latest2026-03-16256K$0.15$0.60models.dev
Mistral Small 4mistral-small-26032026-03-16256K$0.15$0.60models.dev
Devstral Small 2labs-devstral-small-25122025-12-09256Kfreefreemodels.dev
Devstral 2devstral-latest2025-12-09262K$0.40$2.00models.dev
Devstral 2devstral-25122025-12-09262K$0.40$2.00models.dev
Devstral 2 (latest)devstral-medium-latest2025-12-02262K$0.40$2.00models.dev
Mistral Medium 3.1mistral-medium-25082025-08-12262K$0.40$2.00models.dev
Devstral Smalldevstral-small-25072025-07-10128K$0.10$0.30models.dev
Devstral Mediumdevstral-medium-25072025-07-10128K$0.40$2.00models.dev
Mistral Small 3.2mistral-small-25062025-06-20128K$0.10$0.30models.dev
Mistral Medium 3mistral-medium-25052025-05-07131K$0.40$2.00models.dev
Devstral Small 2505devstral-small-25052025-05-07128K$0.10$0.30models.dev
Magistral Medium (latest)magistral-medium-latest2025-03-17128K$2.00$5.00models.dev
Magistral Smallmagistral-small2025-03-17128K$0.50$1.50models.dev
Mistral Large 2.1mistral-large-24112024-11-18131K$2.00$6.00models.dev
Pixtral Large (latest)pixtral-large-latest2024-11-01128K$2.00$6.00models.dev
Mistral Large (latest)mistral-large-latest2024-11-01262K$0.50$1.50models.dev
Mistral Large 3mistral-large-25122024-11-01262K$0.50$1.50models.dev
Ministral 3B (latest)ministral-3b-latest2024-10-01128K$0.04$0.04models.dev
Ministral 8B (latest)ministral-8b-latest2024-10-01128K$0.10$0.10models.dev
Pixtral 12Bpixtral-12b2024-09-01128K$0.15$0.15models.dev
Mistral Nemomistral-nemo2024-07-01128K$0.15$0.15models.dev
Open Mistral Nemoopen-mistral-nemo2024-07-01128K$0.15$0.15models.dev
Codestral (latest)codestral-latest2024-05-29256K$0.30$0.90models.dev
Mixtral 8x22Bopen-mixtral-8x22b2024-04-1764K$2.00$6.00models.dev
Mixtral 8x7Bopen-mixtral-8x7b2023-12-1132K$0.70$0.70models.dev
Mistral Embedmistral-embed2023-12-118K$0.10freemodels.dev
Mistral 7Bopen-mistral-7b2023-09-278K$0.25$0.25models.dev
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
DeepSeek V4 Flashdeepseek-v4-flash2026-04-241M$0.14$0.28$0.0028models.dev
DeepSeek V4 Prodeepseek-v4-pro2026-04-241M$0.43$0.87$0.0036models.dev
DeepSeek Chatdeepseek-chat2025-12-011M$0.14$0.28$0.0028models.dev
DeepSeek Reasonerdeepseek-reasoner2025-12-011M$0.14$0.28$0.0028models.dev
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
North Mini Codenorth-mini-code-1-02026-06-09256Kfreefreemodels.dev
Command A Pluscommand-a-plus-05-20262026-05-20128K$2.50$10.00models.dev
Command A Translatecommand-a-translate-08-20252025-08-288K$2.50$10.00models.dev
Command A Reasoningcommand-a-reasoning-08-20252025-08-21256K$2.50$10.00models.dev
Command A Visioncommand-a-vision-07-20252025-07-31128K$2.50$10.00models.dev
Command Acommand-a-03-20252025-03-13256K$2.50$10.00models.dev
Aya Vision 32Bc4ai-aya-vision-32b2025-03-0416K
Aya Vision 8Bc4ai-aya-vision-8b2025-03-0416K
Command R7B Arabiccommand-r7b-arabic-02-20252025-02-27128K$0.04$0.15models.dev
Command R7Bcommand-r7b-12-20242024-12-02128K$0.04$0.15models.dev
Aya Expanse 8Bc4ai-aya-expanse-8b2024-10-248K
Aya Expanse 32Bc4ai-aya-expanse-32b2024-10-24128K
Command Rcommand-r-08-20242024-08-30128K$0.15$0.60models.dev
Command R+command-r-plus-08-20242024-08-30128K$2.50$10.00models.dev
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
Perplexity Sonar Deep Researchsonar-deep-research2025-02-01128K$2.00$8.00$0.005models.dev · LiteLLM
SonarsonarLiteLLM lists more than one entry for this model at different prices; token cost is models.dev's and the tool fee is omitted.2024-01-01128K$1.00$1.00models.dev
Sonar Prosonar-pro2024-01-01200K$3.00$15.00$0.01models.dev · LiteLLM
Sonar Reasoning Prosonar-reasoning-pro2024-01-01128K$2.00$8.00$0.01models.dev · LiteLLM
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
Qwen3.7 Plusqwen3.7-plusmodels.dev lists $0.5/Mtok input; OpenRouter lists $0.3200. Shown figure is the first-party one.above 256K tokens: $2.00 in2026-06-021M$0.50$3.00$0.05models.dev
Qwen3.7 Maxqwen3.7-maxmodels.dev lists $2.5/Mtok input; OpenRouter lists $1.4750. Shown figure is the first-party one.2026-05-211M$2.50$7.50$0.50models.dev
Qwen3.6 Flashqwen3.6-flash2026-04-271M$0.19$1.13models.dev
Qwen3.6 27Bqwen3.6-27b2026-04-22262K$0.60$3.60models.dev
Qwen3.6 Max Previewqwen3.6-max-previewmodels.dev lists $1.3/Mtok input; OpenRouter lists $1.0270. Shown figure is the first-party one.2026-04-20262K$1.30$7.80$0.13models.dev
Qwen3.6 35B-A3Bqwen3.6-35b-a3b2026-04-17262K$0.25$1.49models.dev
Qwen3.6 Plusqwen3.6-plusmodels.dev lists $0.5/Mtok input; OpenRouter lists $0.3250. Shown figure is the first-party one.above 256K tokens: $2.00 in2026-04-021M$0.50$3.00$0.05models.dev
Qwen3.5 27Bqwen3.5-27b2026-02-23262K$0.30$2.40models.dev
Qwen3.5 35B-A3Bqwen3.5-35b-a3b2026-02-23262K$0.25$2.00models.dev
Qwen3.5 122B-A10Bqwen3.5-122b-a10b2026-02-23262K$0.40$3.20models.dev
Qwen3.5 Plusqwen3.5-plusmodels.dev lists $0.4/Mtok input; OpenRouter lists $0.3000. Shown figure is the first-party one.2026-02-161M$0.40$2.40models.dev
Qwen3.5 397B-A17Bqwen3.5-397b-a17b2026-02-15262K$0.60$3.60models.dev
Qwen3-VL Plusqwen3-vl-plus2025-09-23262K$0.20$1.60models.dev
Qwen3 Maxqwen3-maxmodels.dev lists $1.2/Mtok input; OpenRouter lists $0.7800. Shown figure is the first-party one.2025-09-23262K$1.20$6.00models.dev
Qwen3-LiveTranslate Flash Realtimeqwen3-livetranslate-flash-realtime2025-09-2253K$10.00$10.00models.dev
Qwen3-Omni Flash Realtimeqwen3-omni-flash-realtime2025-09-1566K$0.52$1.99models.dev
Qwen3-Omni Flashqwen3-omni-flash2025-09-1566K$0.43$1.66models.dev
Qwen3-ASR Flashqwen3-asr-flash2025-09-0853K$0.04$0.04models.dev
Qwen3-Next 80B-A3B (Thinking)qwen3-next-80b-a3b-thinking2025-09131K$0.50$6.00models.dev
Qwen3-Next 80B-A3B Instructqwen3-next-80b-a3b-instruct2025-09131K$0.50$2.00models.dev
Qwen3 Coder Flashqwen3-coder-flashmodels.dev lists $0.3/Mtok input; OpenRouter lists $0.1950. Shown figure is the first-party one.2025-07-281M$0.30$1.50models.dev
Qwen Flashqwen-flash2025-07-281M$0.05$0.40models.dev
Qwen3 Coder Plusqwen3-coder-plus2025-07-231.0M$1.00$5.00models.dev
Qwen-Omni Turbo Realtimeqwen-omni-turbo-realtime2025-05-0833K$0.27$1.07models.dev
Qwen3-Coder 480B-A35B Instructqwen3-coder-480b-a35b-instruct2025-04262K$1.50$7.50models.dev
Qwen3 32Bqwen3-32b2025-04131K$0.70$2.80models.dev
Qwen3-Coder 30B-A3B Instructqwen3-coder-30b-a3b-instruct2025-04262K$0.45$2.25models.dev
Qwen3-VL 235B-A22Bqwen3-vl-235b-a22b2025-04131K$0.70$2.80models.dev
Qwen3-VL 30B-A3Bqwen3-vl-30b-a3b2025-04131K$0.20$0.80models.dev
Qwen3 14Bqwen3-14b2025-04131K$0.35$1.40models.dev
Qwen3 235B-A22Bqwen3-235b-a22b2025-04131K$0.70$2.80models.dev
Qwen3 8Bqwen3-8b2025-04131K$0.18$0.70models.dev
QVQ Maxqvq-max2025-03-25131K$1.20$4.80models.dev
QwQ Plusqwq-plus2025-03-05131K$0.80$2.40models.dev
Qwen-Omni Turboqwen-omni-turbo2025-01-1933K$0.07$0.27models.dev
Qwen-MT Plusqwen-mt-plus2025-0116K$2.46$7.37models.dev
Qwen-MT Turboqwen-mt-turbo2025-0116K$0.16$0.49models.dev
Qwen2.5-Omni 7Bqwen2-5-omni-7b2024-1233K$0.10$0.40models.dev
Qwen Turboqwen-turbo2024-11-011M$0.05$0.20models.dev
Qwen-VL OCRqwen-vl-ocr2024-10-2834K$0.72$0.72models.dev
Qwen2.5-VL 72B Instructqwen2-5-vl-72b-instruct2024-09131K$2.80$8.40models.dev
Qwen2.5 72B Instructqwen2-5-72b-instruct2024-09131K$1.40$5.60models.dev
Qwen2.5-VL 7B Instructqwen2-5-vl-7b-instruct2024-09131K$0.35$1.05models.dev
Qwen2.5 32B Instructqwen2-5-32b-instruct2024-09131K$0.70$2.80models.dev
Qwen2.5 14B Instructqwen2-5-14b-instruct2024-09131K$0.35$1.40models.dev
Qwen2.5 7B Instructqwen2-5-7b-instruct2024-09131K$0.17$0.70models.dev
Qwen-VL Maxqwen-vl-max2024-04-08131K$0.80$3.20models.dev
Qwen Maxqwen-max2024-04-0333K$1.60$6.40models.dev
Qwen Plusqwen-plusmodels.dev lists $0.4/Mtok input; OpenRouter lists $0.2600. Shown figure is the first-party one.2024-01-251M$0.40$1.20models.dev
Qwen-VL Plusqwen-vl-plus2024-01-25131K$0.21$0.63models.dev
Qwen Plus Character (Japanese)qwen-plus-character-ja2024-018K$0.50$1.40models.dev
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
Kimi K3kimi-k32026-07-161.0M$3.00$15.00$0.30models.dev
Kimi K2.7 Code HighSpeedkimi-k2.7-code-highspeed2026-06-12262K$1.90$8.00$0.38models.dev
Kimi K2.7 Codekimi-k2.7-code2026-06-12262K$0.95$4.00$0.19models.dev
Kimi K2.6kimi-k2.62026-04-21262K$0.95$4.00$0.16models.dev
Kimi K2.5kimi-k2.52026-01262K$0.60$3.00$0.10models.dev
Kimi K2 Thinking Turbokimi-k2-thinking-turbo2025-11-06262K$1.15$8.00$0.15models.dev
Kimi K2 Thinkingkimi-k2-thinking2025-11-06262K$0.60$2.50$0.15models.dev
Kimi K2 Turbokimi-k2-turbo-preview2025-09-05262K$2.40$10.00$0.60models.dev
Kimi K2 0905kimi-k2-0905-preview2025-09-05262K$0.60$2.50$0.15models.dev
Kimi K2 0711kimi-k2-0711-preview2025-07-14131K$0.60$2.50$0.15models.dev
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
GLM-5.2glm-5.2models.dev lists $1.4/Mtok input; OpenRouter lists $0.9660. Shown figure is the first-party one.2026-06-131M$1.40$4.40$0.26models.dev
GLM-5V-Turboglm-5v-turbomodels.dev lists $5/Mtok input; OpenRouter lists $1.2000. Shown figure is the first-party one.2026-04-01200K$5.00$22.00$1.20models.dev
GLM-5.1glm-5.1models.dev lists $1.4/Mtok input; OpenRouter lists $0.9660. Shown figure is the first-party one.2026-03-27200K$1.40$4.40$0.26models.dev
GLM-5glm-52026-02-11205K$1.00$3.20$0.20models.dev
GLM-4.7-FlashXglm-4.7-flashx2026-01-19200K$0.07$0.40$0.01models.dev
GLM-4.7-Flashglm-4.7-flash2026-01-19200Kfreefreefreemodels.dev
GLM-4.7glm-4.72025-12-22205K$0.60$2.20$0.11models.dev
GLM-4.6Vglm-4.6v2025-12-08128K$0.30$0.90models.dev
GLM-4.6glm-4.62025-09-30205K$0.60$2.20$0.11models.dev
GLM-4.5Vglm-4.5v2025-08-1164K$0.60$1.80models.dev
GLM-4.5-Flashglm-4.5-flash2025-07-28131Kfreefreefreemodels.dev
GLM-4.5glm-4.52025-07-28131K$0.60$2.20$0.11models.dev
GLM-4.5-Airglm-4.5-air2025-07-28131K$0.20$1.10$0.03models.dev
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
MiniMax-M3MiniMax-M3above 512K tokens: $0.60 in2026-06-011M$0.30$1.20$0.06models.dev
MiniMax-M2.7MiniMax-M2.72026-03-18205K$0.30$1.20$0.06models.dev
MiniMax-M2.7-highspeedMiniMax-M2.7-highspeed2026-03-18205K$0.60$2.40$0.06models.dev
MiniMax-M2.5-highspeedMiniMax-M2.5-highspeed2026-02-13205K$0.60$2.40$0.06models.dev
MiniMax-M2.5MiniMax-M2.52026-02-12205K$0.30$1.20$0.03models.dev
MiniMax-M2.1MiniMax-M2.12025-12-23205K$0.30$1.20models.dev
MiniMax-M2MiniMax-M22025-10-27197K$0.30$1.20models.dev
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
Mercury Edit 2mercury-edit-22026-03-30128K$0.25$0.75$0.03models.dev
Mercury 2mercury-22026-02-24128K$0.25$0.75$0.03models.dev
ModelReleasedContextIn / MtokOut / MtokCached inWeb searchSource
Morph v3 Largemorph-v3-large2024-08-1532K$0.90$1.90models.dev
Morph v3 Fastmorph-v3-fast2024-08-1516K$0.80$1.20models.dev
Autoauto2024-06-0132K$0.85$1.55models.dev

How this is built

Model identity, release dates and token rates come from models.dev, filtered to labs that publish their own prices. Server-side search fees and long-context tiers come from LiteLLM. A third feed is consulted only to detect disagreement, never as a source of record. Figures no feed publishes are read off the vendor’s own page by hand and dated.

What this does not cover

  • Batch, enterprise, committed-use and negotiated rates.
  • Reseller and gateway pricing — deliberately excluded.
  • Open-weight models hosted by third parties, whose prices differ legitimately from the lab’s own.
  • Anything a lab does not publish. We do not estimate.

Reuse

The prices are facts and we claim no ownership of them — go and check them against the vendors, that is the point. The merged table, the tool-fee column and the verification timestamps are ours; ask before republishing those wholesale.

Same data as JSON, free, via the Stork MCP server stork_llm_prices.