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.
- 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.
Anthropic
vendor pricing page ↗| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| Claude Opus 5claude-opus-5 | 2026-07-24 | 1M | $5.00 | $25.00 | $0.50 | $0.01 | models.dev · LiteLLM |
| Claude Sonnet 5claude-sonnet-5 | 2026-06-29 | 1M | $2.00 | $10.00 | $0.20 | $0.01 | models.dev · LiteLLM |
| Claude Fable 5claude-fable-5 | 2026-06-07 | 1M | $10.00 | $50.00 | $1.00 | $0.01 | models.dev · LiteLLM |
| Claude Opus 4.8claude-opus-4-8 | 2026-05-28 | 1M | $5.00 | $25.00 | $0.50 | $0.01 | models.dev · LiteLLM |
| Claude Opus 4.7claude-opus-4-7 | 2026-04-14 | 1M | $5.00 | $25.00 | $0.50 | $0.01 | models.dev · LiteLLM |
| Claude Sonnet 4.6claude-sonnet-4-6 | 2026-02-17 | 1M | $3.00 | $15.00 | $0.30 | $0.01 | models.dev · LiteLLM |
| Claude Opus 4.6claude-opus-4-6 | 2026-02-04 | 1M | $5.00 | $25.00 | $0.50 | $0.01 | models.dev · LiteLLM |
| Claude Opus 4.5claude-opus-4-5-20251101 | 2025-11-24 | 200K | $5.00 | $25.00 | $0.50 | $0.01 | models.dev · LiteLLM |
| Claude Opus 4.5 (latest)claude-opus-4-5 | 2025-11-24 | 200K | $5.00 | $25.00 | $0.50 | $0.01 | models.dev · LiteLLM |
| Claude Haiku 4.5 (latest)claude-haiku-4-5 | 2025-10-15 | 200K | $1.00 | $5.00 | $0.10 | — | models.dev |
| Claude Haiku 4.5claude-haiku-4-5-20251001 | 2025-10-15 | 200K | $1.00 | $5.00 | $0.10 | — | models.dev |
| Claude Sonnet 4.5 (latest)claude-sonnet-4-5above 200K tokens: $6.00 in | 2025-09-29 | 1M | $3.00 | $15.00 | $0.30 | $0.01 | models.dev · LiteLLM |
| Claude Sonnet 4.5claude-sonnet-4-5-20250929above 200K tokens: $6.00 in | 2025-09-29 | 1M | $3.00 | $15.00 | $0.30 | $0.01 | models.dev · LiteLLM |
| Claude Opus 4.1 (latest)claude-opus-4-1 | 2025-08-05 | 200K | $15.00 | $75.00 | $1.50 | $0.01 | models.dev · LiteLLM |
| Claude Opus 4.1claude-opus-4-1-20250805 | 2025-08-05 | 200K | $15.00 | $75.00 | $1.50 | $0.01 | models.dev · LiteLLM |
OpenAI
vendor pricing page ↗| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| GPT-5.6 Solgpt-5.6-solabove 272K tokens: $10.00 in | 2026-07-09 | 1.1M | $5.00 | $30.00 | $0.50 | — | models.dev |
| GPT-5.6 Lunagpt-5.6-lunaabove 272K tokens: $0.40 in | 2026-07-09 | 1.1M | $0.20 | $1.20 | $0.02 | — | hand-verified |
| GPT-5.6gpt-5.6above 272K tokens: $10.00 in | 2026-07-09 | 1.1M | $5.00 | $30.00 | $0.50 | — | models.dev |
| GPT-5.6 Terragpt-5.6-terraabove 272K tokens: $4.00 in | 2026-07-09 | 1.1M | $2.00 | $12.00 | $0.20 | — | hand-verified |
| GPT-Realtime-2.1gpt-realtime-2.1 | 2026-07-06 | 128K | $4.00 | $24.00 | $0.40 | — | models.dev |
| GPT-5.5 Progpt-5.5-proabove 272K tokens: $60.00 in | 2026-04-23 | 1.1M | $30.00 | $180.00 | — | — | models.dev |
| GPT-5.5gpt-5.5above 272K tokens: $10.00 in | 2026-04-23 | 1.1M | $5.00 | $30.00 | $0.50 | — | models.dev |
| gpt-image-2gpt-image-2 | 2026-04-21 | 0 | $5.00 | $30.00 | $1.25 | — | models.dev |
| GPT-5.4 nanogpt-5.4-nano | 2026-03-17 | 400K | $0.20 | $1.25 | $0.02 | — | models.dev |
| GPT-5.4 minigpt-5.4-mini | 2026-03-17 | 400K | $0.75 | $4.50 | $0.07 | — | models.dev |
| GPT-5.4 Progpt-5.4-proabove 272K tokens: $60.00 in | 2026-03-05 | 1.1M | $30.00 | $180.00 | — | — | models.dev |
| GPT-5.4gpt-5.4above 272K tokens: $5.00 in | 2026-03-05 | 1.1M | $2.50 | $15.00 | $0.25 | — | models.dev |
| GPT-5.3 Chat (latest)gpt-5.3-chat-latest | 2026-03-03 | 128K | $1.75 | $14.00 | $0.17 | — | models.dev |
| GPT-5.3 Codex Sparkgpt-5.3-codex-spark | 2026-02-05 | 128K | $1.75 | $14.00 | $0.17 | — | models.dev |
| GPT-5.3 Codexgpt-5.3-codex | 2026-02-05 | 400K | $1.75 | $14.00 | $0.17 | — | models.dev |
| chatgpt-image-latestchatgpt-image-latest | 2025-12-16 | 0 | $5.00 | — | — | — | LiteLLM |
| GPT-5.2 Progpt-5.2-pro | 2025-12-11 | 400K | $21.00 | $168.00 | — | — | models.dev |
| GPT-5.2 Chatgpt-5.2-chat-latest | 2025-12-11 | 128K | $1.75 | $14.00 | $0.17 | — | models.dev |
| GPT-5.2gpt-5.2 | 2025-12-11 | 400K | $1.75 | $14.00 | $0.17 | — | models.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. | 2025-11-25 | 0 | — | — | — | — | — |
| GPT-5.1gpt-5.1 | 2025-11-13 | 400K | $1.25 | $10.00 | $0.13 | — | models.dev |
| GPT-5 Progpt-5-pro | 2025-10-06 | 400K | $15.00 | $120.00 | — | — | models.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. | 2025-09-26 | 0 | — | — | — | — | — |
| GPT-5gpt-5 | 2025-08-07 | 400K | $1.25 | $10.00 | $0.13 | — | models.dev |
| GPT-5 Minigpt-5-mini | 2025-08-07 | 400K | $0.25 | $2.00 | $0.03 | — | models.dev |
| GPT-5 Nanogpt-5-nano | 2025-08-07 | 400K | $0.05 | $0.40 | $0.005 | — | models.dev |
| o3-proo3-pro | 2025-06-10 | 200K | $20.00 | $80.00 | — | — | models.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. | 2025-04-24 | 0 | — | — | — | — | — |
| o3o3 | 2025-04-16 | 200K | $2.00 | $8.00 | $0.50 | — | models.dev |
| o4-minio4-mini | 2025-04-16 | 200K | $1.10 | $4.40 | $0.28 | — | models.dev |
| GPT-4.1 minigpt-4.1-mini | 2025-04-14 | 1.0M | $0.40 | $1.60 | $0.10 | — | models.dev |
| GPT-4.1 nanogpt-4.1-nano | 2025-04-14 | 1.0M | $0.10 | $0.40 | $0.03 | — | models.dev |
| GPT-4.1gpt-4.1 | 2025-04-14 | 1.0M | $2.00 | $8.00 | $0.50 | — | models.dev |
| o1-proo1-pro | 2025-03-19 | 200K | $150.00 | $600.00 | — | — | models.dev |
| o3-minio3-mini | 2024-12-20 | 200K | $1.10 | $4.40 | $0.55 | — | models.dev |
| o1o1 | 2024-12-05 | 200K | $15.00 | $60.00 | $7.50 | — | models.dev |
| GPT-4o (2024-11-20)gpt-4o-2024-11-20 | 2024-11-20 | 128K | $2.50 | $10.00 | $1.25 | — | models.dev |
| GPT-4o (2024-08-06)gpt-4o-2024-08-06 | 2024-08-06 | 128K | $2.50 | $10.00 | $1.25 | — | models.dev |
| GPT-4o minigpt-4o-mini | 2024-07-18 | 128K | $0.15 | $0.60 | $0.07 | — | models.dev |
| GPT-4ogpt-4o | 2024-05-13 | 128K | $2.50 | $10.00 | $1.25 | $0.01 | models.dev · hand-verified |
| GPT-4o (2024-05-13)gpt-4o-2024-05-13 | 2024-05-13 | 128K | $5.00 | $15.00 | — | — | models.dev |
| text-embedding-3-largetext-embedding-3-large | 2024-01-25 | 8K | $0.13 | free | — | — | models.dev |
| text-embedding-3-smalltext-embedding-3-small | 2024-01-25 | 8K | $0.02 | free | — | — | models.dev |
| GPT-4 Turbogpt-4-turbo | 2023-11-06 | 128K | $10.00 | $30.00 | — | — | models.dev |
| GPT-4gpt-4 | 2023-11-06 | 8K | $30.00 | $60.00 | — | — | models.dev |
| GPT-3.5-turbogpt-3.5-turbo | 2023-03-01 | 16K | $0.50 | $1.50 | free | — | models.dev |
| text-embedding-ada-002text-embedding-ada-002 | 2022-12-15 | 8K | $0.10 | free | — | — | models.dev |
| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash Litegemini-3.5-flash-lite | 2026-07-21 | 1.0M | $0.30 | $2.50 | $0.03 | $0.01 | models.dev · LiteLLM |
| Gemini 3.6 Flashgemini-3.6-flash | 2026-07-21 | 1.0M | $1.50 | $7.50 | $0.15 | $0.01 | models.dev · LiteLLM |
| Gemini Omni Flash Previewgemini-omni-flash-preview | 2026-06-30 | 131K | $1.50 | $17.50 | — | — | models.dev |
| Nano Banana 2 Litegemini-3.1-flash-lite-image | 2026-06-30 | 66K | $0.25 | $30.00 | — | — | models.dev |
| Gemini 3.5 Live Translate Previewgemini-3.5-live-translate-preview | 2026-06-09 | 16K | $3.50 | $21.00 | — | — | models.dev |
| Nano Banana 2gemini-3.1-flash-image | 2026-05-28 | 66K | $0.50 | $60.00 | — | $0.01 | models.dev · LiteLLM |
| Nano Banana Progemini-3-pro-image | 2026-05-28 | 131K | $2.00 | $120.00 | — | $0.01 | models.dev · LiteLLM |
| Gemini Flash Latestgemini-flash-latest | 2026-05-19 | 1.0M | $1.50 | $9.00 | $0.15 | $0.04 | models.dev · LiteLLM |
| Gemini 3.5 Flashgemini-3.5-flash | 2026-05-19 | 1.0M | $1.50 | $9.00 | $0.15 | $0.01 | models.dev · LiteLLM |
| Gemini 3.1 Flash Litegemini-3.1-flash-lite | 2026-05-07 | 1.0M | $0.25 | $1.50 | $0.03 | $0.01 | models.dev · LiteLLM |
| Gemini Flash-Lite Latestgemini-flash-lite-latest | 2026-05-07 | 1.0M | $0.25 | $1.50 | $0.03 | $0.04 | models.dev · LiteLLM |
| Gemini Embedding 2gemini-embedding-2 | 2026-04-22 | 8K | $0.20 | free | — | — | models.dev |
| Deep Research Preview (Apr-21-2026)deep-research-preview-04-2026above 200K tokens: $4.00 in | 2026-04-21 | 131K | $2.00 | $12.00 | $0.20 | — | models.dev |
| Deep Research Max Preview (Apr-21-2026)deep-research-max-preview-04-2026above 200K tokens: $4.00 in | 2026-04-21 | 131K | $2.00 | $12.00 | $0.20 | — | models.dev |
| Gemini 3.1 Flash TTS Previewgemini-3.1-flash-tts-preview | 2026-04-15 | 8K | $1.00 | $20.00 | — | — | models.dev |
| Gemini Robotics-ER 1.6 Previewgemini-robotics-er-1.6-preview | 2026-04-14 | 131K | $1.00 | $5.00 | — | — | models.dev |
| Gemma 4 26B A4B ITgemma-4-26b-a4b-it | 2026-04-02 | 262K | — | — | — | — | — |
| Gemma 4 31B ITgemma-4-31b-it | 2026-04-02 | 262K | — | — | — | — | — |
| Veo 3.1 liteveo-3.1-lite-generate-preview | 2026-03-31 | 480 | — | — | — | — | — |
| Gemini 3.1 Flash Live Previewgemini-3.1-flash-live-preview | 2026-03-26 | 131K | $0.75 | $4.50 | — | — | models.dev |
| Lyria 3 Pro Previewlyria-3-pro-preview | 2026-03-25 | 1.0M | free | free | — | — | models.dev |
| Lyria 3 Clip Previewlyria-3-clip-preview | 2026-03-25 | 1.0M | free | free | — | — | models.dev |
| Gemini 3.1 Flash Lite Previewgemini-3.1-flash-lite-preview | 2026-03-03 | 1.0M | $0.25 | $1.50 | $0.03 | $0.01 | models.dev · LiteLLM |
| Nano Banana 2gemini-3.1-flash-image-preview | 2026-02-26 | 66K | $0.50 | $60.00 | — | $0.01 | models.dev · LiteLLM |
| Gemini 3.1 Pro Preview Custom Toolsgemini-3.1-pro-preview-customtoolsabove 200K tokens: $4.00 in | 2026-02-19 | 1.0M | $2.00 | $12.00 | $0.20 | $0.01 | models.dev · LiteLLM |
| Gemini 3.1 Pro Previewgemini-3.1-pro-previewabove 200K tokens: $4.00 in | 2026-02-19 | 1.0M | $2.00 | $12.00 | $0.20 | $0.01 | models.dev · LiteLLM |
| Gemini 3 Flash Previewgemini-3-flash-preview | 2025-12-17 | 1.0M | $0.50 | $3.00 | $0.05 | $0.01 | models.dev · LiteLLM |
| Nano Banana Progemini-3-pro-image-preview | 2025-11-20 | 131K | $2.00 | $120.00 | — | $0.01 | models.dev · LiteLLM |
| Gemini 3 Pro Previewgemini-3-pro-previewabove 200K tokens: $4.00 in | 2025-11-18 | 1.0M | $2.00 | $12.00 | $0.20 | $0.01 | models.dev · LiteLLM |
| Veo 3.1veo-3.1-generate-preview | 2025-10-15 | 480 | — | — | — | — | — |
| Veo 3.1 fastveo-3.1-fast-generate-preview | 2025-10-15 | 480 | — | — | — | — | — |
| Gemini 2.5 Computer Use Preview 10-2025gemini-2.5-computer-use-preview-10-2025above 200K tokens: $2.50 in | 2025-10-07 | 131K | $1.25 | $10.00 | — | — | models.dev |
| Nano Bananagemini-2.5-flash-image | 2025-08-26 | 33K | $0.30 | $30.00 | $0.07 | $0.04 | models.dev · LiteLLM |
| Gemini 2.5 Flashgemini-2.5-flash | 2025-06-17 | 1.0M | $0.30 | $2.50 | $0.03 | $0.04 | models.dev · LiteLLM |
| Gemini 2.5 Progemini-2.5-proabove 200K tokens: $2.50 in | 2025-06-17 | 1.0M | $1.25 | $10.00 | $0.13 | $0.04 | models.dev · LiteLLM |
| Gemini 2.5 Flash-Litegemini-2.5-flash-lite | 2025-06-17 | 1.0M | $0.10 | $0.40 | $0.01 | $0.04 | models.dev · LiteLLM |
| Gemini Embedding 001gemini-embedding-001 | 2025-05-20 | 2K | $0.15 | free | — | — | models.dev |
| Gemini 2.5 Flash Preview TTSgemini-2.5-flash-preview-tts | 2025-05-01 | 8K | $0.50 | $10.00 | — | — | models.dev |
| Gemini 2.5 Pro Preview TTSgemini-2.5-pro-preview-ttsabove 200K tokens: $2.50 in | 2025-05-01 | 8K | $1.00 | $20.00 | — | $0.04 | models.dev · LiteLLM |
| Gemini 2.0 Flashgemini-2.0-flash | 2024-12-11 | 1.0M | $0.10 | $0.40 | $0.03 | $0.04 | models.dev · LiteLLM |
| Gemini 2.0 Flash-Litegemini-2.0-flash-lite | 2024-12-11 | 1.0M | $0.07 | $0.30 | — | $0.04 | models.dev · LiteLLM |
| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| Grok 4.5grok-4.5above 200K tokens: $4.00 in | 2026-07-08 | 500K | $2.00 | $6.00 | $0.30 | $0.005 | models.dev · hand-verified |
| Grok Imagine Video 1.5grok-imagine-video-1.5 | 2026-05-30 | 1K | — | — | — | — | — |
| Grok 4.3grok-4.3above 200K tokens: $2.50 in | 2026-04-17 | 1M | $1.25 | $2.50 | $0.20 | $0.005 | models.dev · hand-verified |
| Grok Build 0.1grok-build-0.1above 200K tokens: $2.00 in | 2026-04-16 | 256K | $1.00 | $2.00 | $0.20 | $0.005 | models.dev · hand-verified |
| Grok Imagine Image Qualitygrok-imagine-image-quality | 2026-04-03 | 8K | — | — | — | — | — |
| Grok 4.20 (Non-Reasoning)grok-4.20-0309-non-reasoningabove 200K tokens: $2.50 in | 2026-03-09 | 1M | $1.25 | $2.50 | $0.20 | $0.005 | models.dev · hand-verified |
| Grok 4.20 Multi-Agentgrok-4.20-multi-agent-0309above 200K tokens: $2.50 in | 2026-03-09 | 1M | $1.25 | $2.50 | $0.20 | — | models.dev |
| Grok 4.20 (Reasoning)grok-4.20-0309-reasoningabove 200K tokens: $2.50 in | 2026-03-09 | 1M | $1.25 | $2.50 | $0.20 | $0.005 | models.dev · hand-verified |
| Grok Imagine Videogrok-imagine-video | 2026-01-28 | 1K | — | — | — | — | — |
| Grok Imagine Imagegrok-imagine-image | 2026-01-28 | 8K | — | — | — | — | — |
| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| Muse Spark 1.1muse-spark-1.1 | 2026-04-08 | 1M | $1.25 | $4.25 | $0.15 | — | models.dev |
Mistral
vendor pricing page ↗| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| Mistral Medium (latest)mistral-medium-latest | 2026-04-29 | 262K | $1.50 | $7.50 | — | — | models.dev |
| Mistral Medium 3.5mistral-medium-2604 | 2026-04-29 | 262K | $1.50 | $7.50 | — | — | models.dev |
| Mistral Small (latest)mistral-small-latest | 2026-03-16 | 256K | $0.15 | $0.60 | — | — | models.dev |
| Mistral Small 4mistral-small-2603 | 2026-03-16 | 256K | $0.15 | $0.60 | — | — | models.dev |
| Devstral Small 2labs-devstral-small-2512 | 2025-12-09 | 256K | free | free | — | — | models.dev |
| Devstral 2devstral-latest | 2025-12-09 | 262K | $0.40 | $2.00 | — | — | models.dev |
| Devstral 2devstral-2512 | 2025-12-09 | 262K | $0.40 | $2.00 | — | — | models.dev |
| Devstral 2 (latest)devstral-medium-latest | 2025-12-02 | 262K | $0.40 | $2.00 | — | — | models.dev |
| Mistral Medium 3.1mistral-medium-2508 | 2025-08-12 | 262K | $0.40 | $2.00 | — | — | models.dev |
| Devstral Smalldevstral-small-2507 | 2025-07-10 | 128K | $0.10 | $0.30 | — | — | models.dev |
| Devstral Mediumdevstral-medium-2507 | 2025-07-10 | 128K | $0.40 | $2.00 | — | — | models.dev |
| Mistral Small 3.2mistral-small-2506 | 2025-06-20 | 128K | $0.10 | $0.30 | — | — | models.dev |
| Mistral Medium 3mistral-medium-2505 | 2025-05-07 | 131K | $0.40 | $2.00 | — | — | models.dev |
| Devstral Small 2505devstral-small-2505 | 2025-05-07 | 128K | $0.10 | $0.30 | — | — | models.dev |
| Magistral Medium (latest)magistral-medium-latest | 2025-03-17 | 128K | $2.00 | $5.00 | — | — | models.dev |
| Magistral Smallmagistral-small | 2025-03-17 | 128K | $0.50 | $1.50 | — | — | models.dev |
| Mistral Large 2.1mistral-large-2411 | 2024-11-18 | 131K | $2.00 | $6.00 | — | — | models.dev |
| Pixtral Large (latest)pixtral-large-latest | 2024-11-01 | 128K | $2.00 | $6.00 | — | — | models.dev |
| Mistral Large (latest)mistral-large-latest | 2024-11-01 | 262K | $0.50 | $1.50 | — | — | models.dev |
| Mistral Large 3mistral-large-2512 | 2024-11-01 | 262K | $0.50 | $1.50 | — | — | models.dev |
| Ministral 3B (latest)ministral-3b-latest | 2024-10-01 | 128K | $0.04 | $0.04 | — | — | models.dev |
| Ministral 8B (latest)ministral-8b-latest | 2024-10-01 | 128K | $0.10 | $0.10 | — | — | models.dev |
| Pixtral 12Bpixtral-12b | 2024-09-01 | 128K | $0.15 | $0.15 | — | — | models.dev |
| Mistral Nemomistral-nemo | 2024-07-01 | 128K | $0.15 | $0.15 | — | — | models.dev |
| Open Mistral Nemoopen-mistral-nemo | 2024-07-01 | 128K | $0.15 | $0.15 | — | — | models.dev |
| Codestral (latest)codestral-latest | 2024-05-29 | 256K | $0.30 | $0.90 | — | — | models.dev |
| Mixtral 8x22Bopen-mixtral-8x22b | 2024-04-17 | 64K | $2.00 | $6.00 | — | — | models.dev |
| Mixtral 8x7Bopen-mixtral-8x7b | 2023-12-11 | 32K | $0.70 | $0.70 | — | — | models.dev |
| Mistral Embedmistral-embed | 2023-12-11 | 8K | $0.10 | free | — | — | models.dev |
| Mistral 7Bopen-mistral-7b | 2023-09-27 | 8K | $0.25 | $0.25 | — | — | models.dev |
DeepSeek
vendor pricing page ↗| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flashdeepseek-v4-flash | 2026-04-24 | 1M | $0.14 | $0.28 | $0.0028 | — | models.dev |
| DeepSeek V4 Prodeepseek-v4-pro | 2026-04-24 | 1M | $0.43 | $0.87 | $0.0036 | — | models.dev |
| DeepSeek Chatdeepseek-chat | 2025-12-01 | 1M | $0.14 | $0.28 | $0.0028 | — | models.dev |
| DeepSeek Reasonerdeepseek-reasoner | 2025-12-01 | 1M | $0.14 | $0.28 | $0.0028 | — | models.dev |
Cohere
vendor pricing page ↗| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| North Mini Codenorth-mini-code-1-0 | 2026-06-09 | 256K | free | free | — | — | models.dev |
| Command A Pluscommand-a-plus-05-2026 | 2026-05-20 | 128K | $2.50 | $10.00 | — | — | models.dev |
| Command A Translatecommand-a-translate-08-2025 | 2025-08-28 | 8K | $2.50 | $10.00 | — | — | models.dev |
| Command A Reasoningcommand-a-reasoning-08-2025 | 2025-08-21 | 256K | $2.50 | $10.00 | — | — | models.dev |
| Command A Visioncommand-a-vision-07-2025 | 2025-07-31 | 128K | $2.50 | $10.00 | — | — | models.dev |
| Command Acommand-a-03-2025 | 2025-03-13 | 256K | $2.50 | $10.00 | — | — | models.dev |
| Aya Vision 32Bc4ai-aya-vision-32b | 2025-03-04 | 16K | — | — | — | — | — |
| Aya Vision 8Bc4ai-aya-vision-8b | 2025-03-04 | 16K | — | — | — | — | — |
| Command R7B Arabiccommand-r7b-arabic-02-2025 | 2025-02-27 | 128K | $0.04 | $0.15 | — | — | models.dev |
| Command R7Bcommand-r7b-12-2024 | 2024-12-02 | 128K | $0.04 | $0.15 | — | — | models.dev |
| Aya Expanse 8Bc4ai-aya-expanse-8b | 2024-10-24 | 8K | — | — | — | — | — |
| Aya Expanse 32Bc4ai-aya-expanse-32b | 2024-10-24 | 128K | — | — | — | — | — |
| Command Rcommand-r-08-2024 | 2024-08-30 | 128K | $0.15 | $0.60 | — | — | models.dev |
| Command R+command-r-plus-08-2024 | 2024-08-30 | 128K | $2.50 | $10.00 | — | — | models.dev |
Perplexity
vendor pricing page ↗| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| Perplexity Sonar Deep Researchsonar-deep-research | 2025-02-01 | 128K | $2.00 | $8.00 | — | $0.005 | models.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. | 2024-01-01 | 128K | $1.00 | $1.00 | — | — | models.dev |
| Sonar Prosonar-pro | 2024-01-01 | 200K | $3.00 | $15.00 | — | $0.01 | models.dev · LiteLLM |
| Sonar Reasoning Prosonar-reasoning-pro | 2024-01-01 | 128K | $2.00 | $8.00 | — | $0.01 | models.dev · LiteLLM |
Alibaba
vendor pricing page ↗| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| 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 in | 2026-06-02 | 1M | $0.50 | $3.00 | $0.05 | — | models.dev |
| Qwen3.7 Maxqwen3.7-maxmodels.dev lists $2.5/Mtok input; OpenRouter lists $1.4750. Shown figure is the first-party one. | 2026-05-21 | 1M | $2.50 | $7.50 | $0.50 | — | models.dev |
| Qwen3.6 Flashqwen3.6-flash | 2026-04-27 | 1M | $0.19 | $1.13 | — | — | models.dev |
| Qwen3.6 27Bqwen3.6-27b | 2026-04-22 | 262K | $0.60 | $3.60 | — | — | models.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. | 2026-04-20 | 262K | $1.30 | $7.80 | $0.13 | — | models.dev |
| Qwen3.6 35B-A3Bqwen3.6-35b-a3b | 2026-04-17 | 262K | $0.25 | $1.49 | — | — | models.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 in | 2026-04-02 | 1M | $0.50 | $3.00 | $0.05 | — | models.dev |
| Qwen3.5 27Bqwen3.5-27b | 2026-02-23 | 262K | $0.30 | $2.40 | — | — | models.dev |
| Qwen3.5 35B-A3Bqwen3.5-35b-a3b | 2026-02-23 | 262K | $0.25 | $2.00 | — | — | models.dev |
| Qwen3.5 122B-A10Bqwen3.5-122b-a10b | 2026-02-23 | 262K | $0.40 | $3.20 | — | — | models.dev |
| Qwen3.5 Plusqwen3.5-plusmodels.dev lists $0.4/Mtok input; OpenRouter lists $0.3000. Shown figure is the first-party one. | 2026-02-16 | 1M | $0.40 | $2.40 | — | — | models.dev |
| Qwen3.5 397B-A17Bqwen3.5-397b-a17b | 2026-02-15 | 262K | $0.60 | $3.60 | — | — | models.dev |
| Qwen3-VL Plusqwen3-vl-plus | 2025-09-23 | 262K | $0.20 | $1.60 | — | — | models.dev |
| Qwen3 Maxqwen3-maxmodels.dev lists $1.2/Mtok input; OpenRouter lists $0.7800. Shown figure is the first-party one. | 2025-09-23 | 262K | $1.20 | $6.00 | — | — | models.dev |
| Qwen3-LiveTranslate Flash Realtimeqwen3-livetranslate-flash-realtime | 2025-09-22 | 53K | $10.00 | $10.00 | — | — | models.dev |
| Qwen3-Omni Flash Realtimeqwen3-omni-flash-realtime | 2025-09-15 | 66K | $0.52 | $1.99 | — | — | models.dev |
| Qwen3-Omni Flashqwen3-omni-flash | 2025-09-15 | 66K | $0.43 | $1.66 | — | — | models.dev |
| Qwen3-ASR Flashqwen3-asr-flash | 2025-09-08 | 53K | $0.04 | $0.04 | — | — | models.dev |
| Qwen3-Next 80B-A3B (Thinking)qwen3-next-80b-a3b-thinking | 2025-09 | 131K | $0.50 | $6.00 | — | — | models.dev |
| Qwen3-Next 80B-A3B Instructqwen3-next-80b-a3b-instruct | 2025-09 | 131K | $0.50 | $2.00 | — | — | models.dev |
| Qwen3 Coder Flashqwen3-coder-flashmodels.dev lists $0.3/Mtok input; OpenRouter lists $0.1950. Shown figure is the first-party one. | 2025-07-28 | 1M | $0.30 | $1.50 | — | — | models.dev |
| Qwen Flashqwen-flash | 2025-07-28 | 1M | $0.05 | $0.40 | — | — | models.dev |
| Qwen3 Coder Plusqwen3-coder-plus | 2025-07-23 | 1.0M | $1.00 | $5.00 | — | — | models.dev |
| Qwen-Omni Turbo Realtimeqwen-omni-turbo-realtime | 2025-05-08 | 33K | $0.27 | $1.07 | — | — | models.dev |
| Qwen3-Coder 480B-A35B Instructqwen3-coder-480b-a35b-instruct | 2025-04 | 262K | $1.50 | $7.50 | — | — | models.dev |
| Qwen3 32Bqwen3-32b | 2025-04 | 131K | $0.70 | $2.80 | — | — | models.dev |
| Qwen3-Coder 30B-A3B Instructqwen3-coder-30b-a3b-instruct | 2025-04 | 262K | $0.45 | $2.25 | — | — | models.dev |
| Qwen3-VL 235B-A22Bqwen3-vl-235b-a22b | 2025-04 | 131K | $0.70 | $2.80 | — | — | models.dev |
| Qwen3-VL 30B-A3Bqwen3-vl-30b-a3b | 2025-04 | 131K | $0.20 | $0.80 | — | — | models.dev |
| Qwen3 14Bqwen3-14b | 2025-04 | 131K | $0.35 | $1.40 | — | — | models.dev |
| Qwen3 235B-A22Bqwen3-235b-a22b | 2025-04 | 131K | $0.70 | $2.80 | — | — | models.dev |
| Qwen3 8Bqwen3-8b | 2025-04 | 131K | $0.18 | $0.70 | — | — | models.dev |
| QVQ Maxqvq-max | 2025-03-25 | 131K | $1.20 | $4.80 | — | — | models.dev |
| QwQ Plusqwq-plus | 2025-03-05 | 131K | $0.80 | $2.40 | — | — | models.dev |
| Qwen-Omni Turboqwen-omni-turbo | 2025-01-19 | 33K | $0.07 | $0.27 | — | — | models.dev |
| Qwen-MT Plusqwen-mt-plus | 2025-01 | 16K | $2.46 | $7.37 | — | — | models.dev |
| Qwen-MT Turboqwen-mt-turbo | 2025-01 | 16K | $0.16 | $0.49 | — | — | models.dev |
| Qwen2.5-Omni 7Bqwen2-5-omni-7b | 2024-12 | 33K | $0.10 | $0.40 | — | — | models.dev |
| Qwen Turboqwen-turbo | 2024-11-01 | 1M | $0.05 | $0.20 | — | — | models.dev |
| Qwen-VL OCRqwen-vl-ocr | 2024-10-28 | 34K | $0.72 | $0.72 | — | — | models.dev |
| Qwen2.5-VL 72B Instructqwen2-5-vl-72b-instruct | 2024-09 | 131K | $2.80 | $8.40 | — | — | models.dev |
| Qwen2.5 72B Instructqwen2-5-72b-instruct | 2024-09 | 131K | $1.40 | $5.60 | — | — | models.dev |
| Qwen2.5-VL 7B Instructqwen2-5-vl-7b-instruct | 2024-09 | 131K | $0.35 | $1.05 | — | — | models.dev |
| Qwen2.5 32B Instructqwen2-5-32b-instruct | 2024-09 | 131K | $0.70 | $2.80 | — | — | models.dev |
| Qwen2.5 14B Instructqwen2-5-14b-instruct | 2024-09 | 131K | $0.35 | $1.40 | — | — | models.dev |
| Qwen2.5 7B Instructqwen2-5-7b-instruct | 2024-09 | 131K | $0.17 | $0.70 | — | — | models.dev |
| Qwen-VL Maxqwen-vl-max | 2024-04-08 | 131K | $0.80 | $3.20 | — | — | models.dev |
| Qwen Maxqwen-max | 2024-04-03 | 33K | $1.60 | $6.40 | — | — | models.dev |
| Qwen Plusqwen-plusmodels.dev lists $0.4/Mtok input; OpenRouter lists $0.2600. Shown figure is the first-party one. | 2024-01-25 | 1M | $0.40 | $1.20 | — | — | models.dev |
| Qwen-VL Plusqwen-vl-plus | 2024-01-25 | 131K | $0.21 | $0.63 | — | — | models.dev |
| Qwen Plus Character (Japanese)qwen-plus-character-ja | 2024-01 | 8K | $0.50 | $1.40 | — | — | models.dev |
Moonshot AI
vendor pricing page ↗| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| Kimi K3kimi-k3 | 2026-07-16 | 1.0M | $3.00 | $15.00 | $0.30 | — | models.dev |
| Kimi K2.7 Code HighSpeedkimi-k2.7-code-highspeed | 2026-06-12 | 262K | $1.90 | $8.00 | $0.38 | — | models.dev |
| Kimi K2.7 Codekimi-k2.7-code | 2026-06-12 | 262K | $0.95 | $4.00 | $0.19 | — | models.dev |
| Kimi K2.6kimi-k2.6 | 2026-04-21 | 262K | $0.95 | $4.00 | $0.16 | — | models.dev |
| Kimi K2.5kimi-k2.5 | 2026-01 | 262K | $0.60 | $3.00 | $0.10 | — | models.dev |
| Kimi K2 Thinking Turbokimi-k2-thinking-turbo | 2025-11-06 | 262K | $1.15 | $8.00 | $0.15 | — | models.dev |
| Kimi K2 Thinkingkimi-k2-thinking | 2025-11-06 | 262K | $0.60 | $2.50 | $0.15 | — | models.dev |
| Kimi K2 Turbokimi-k2-turbo-preview | 2025-09-05 | 262K | $2.40 | $10.00 | $0.60 | — | models.dev |
| Kimi K2 0905kimi-k2-0905-preview | 2025-09-05 | 262K | $0.60 | $2.50 | $0.15 | — | models.dev |
| Kimi K2 0711kimi-k2-0711-preview | 2025-07-14 | 131K | $0.60 | $2.50 | $0.15 | — | models.dev |
Zhipu AI
vendor pricing page ↗| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| GLM-5.2glm-5.2models.dev lists $1.4/Mtok input; OpenRouter lists $0.9660. Shown figure is the first-party one. | 2026-06-13 | 1M | $1.40 | $4.40 | $0.26 | — | models.dev |
| GLM-5V-Turboglm-5v-turbomodels.dev lists $5/Mtok input; OpenRouter lists $1.2000. Shown figure is the first-party one. | 2026-04-01 | 200K | $5.00 | $22.00 | $1.20 | — | models.dev |
| GLM-5.1glm-5.1models.dev lists $1.4/Mtok input; OpenRouter lists $0.9660. Shown figure is the first-party one. | 2026-03-27 | 200K | $1.40 | $4.40 | $0.26 | — | models.dev |
| GLM-5glm-5 | 2026-02-11 | 205K | $1.00 | $3.20 | $0.20 | — | models.dev |
| GLM-4.7-FlashXglm-4.7-flashx | 2026-01-19 | 200K | $0.07 | $0.40 | $0.01 | — | models.dev |
| GLM-4.7-Flashglm-4.7-flash | 2026-01-19 | 200K | free | free | free | — | models.dev |
| GLM-4.7glm-4.7 | 2025-12-22 | 205K | $0.60 | $2.20 | $0.11 | — | models.dev |
| GLM-4.6Vglm-4.6v | 2025-12-08 | 128K | $0.30 | $0.90 | — | — | models.dev |
| GLM-4.6glm-4.6 | 2025-09-30 | 205K | $0.60 | $2.20 | $0.11 | — | models.dev |
| GLM-4.5Vglm-4.5v | 2025-08-11 | 64K | $0.60 | $1.80 | — | — | models.dev |
| GLM-4.5-Flashglm-4.5-flash | 2025-07-28 | 131K | free | free | free | — | models.dev |
| GLM-4.5glm-4.5 | 2025-07-28 | 131K | $0.60 | $2.20 | $0.11 | — | models.dev |
| GLM-4.5-Airglm-4.5-air | 2025-07-28 | 131K | $0.20 | $1.10 | $0.03 | — | models.dev |
MiniMax
vendor pricing page ↗| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| MiniMax-M3MiniMax-M3above 512K tokens: $0.60 in | 2026-06-01 | 1M | $0.30 | $1.20 | $0.06 | — | models.dev |
| MiniMax-M2.7MiniMax-M2.7 | 2026-03-18 | 205K | $0.30 | $1.20 | $0.06 | — | models.dev |
| MiniMax-M2.7-highspeedMiniMax-M2.7-highspeed | 2026-03-18 | 205K | $0.60 | $2.40 | $0.06 | — | models.dev |
| MiniMax-M2.5-highspeedMiniMax-M2.5-highspeed | 2026-02-13 | 205K | $0.60 | $2.40 | $0.06 | — | models.dev |
| MiniMax-M2.5MiniMax-M2.5 | 2026-02-12 | 205K | $0.30 | $1.20 | $0.03 | — | models.dev |
| MiniMax-M2.1MiniMax-M2.1 | 2025-12-23 | 205K | $0.30 | $1.20 | — | — | models.dev |
| MiniMax-M2MiniMax-M2 | 2025-10-27 | 197K | $0.30 | $1.20 | — | — | models.dev |
Inception
vendor pricing page ↗| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| Mercury Edit 2mercury-edit-2 | 2026-03-30 | 128K | $0.25 | $0.75 | $0.03 | — | models.dev |
| Mercury 2mercury-2 | 2026-02-24 | 128K | $0.25 | $0.75 | $0.03 | — | models.dev |
| Model | Released | Context | In / Mtok | Out / Mtok | Cached in | Web search | Source |
|---|---|---|---|---|---|---|---|
| Morph v3 Largemorph-v3-large | 2024-08-15 | 32K | $0.90 | $1.90 | — | — | models.dev |
| Morph v3 Fastmorph-v3-fast | 2024-08-15 | 16K | $0.80 | $1.20 | — | — | models.dev |
| Autoauto | 2024-06-01 | 32K | $0.85 | $1.55 | — | — | models.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.
