Model pricing · change log
AI model price changes
Every API rate that moved in our snapshots of OpenRouter's public model price list between 12 September 2026 and 9 November 2026: 439 rate changes, 8 billing unit changes, 66 new charges and 58 dropped ones, on 134 models. Newest first, in US dollars as listed.
Snapshots of , , , · Urbano DX
Read this first
- For a model served by several providers, OpenRouter lists one provider's price, and which one can change between snapshots. A change here can mean a different provider, not a new price from the developer.
- A model name ending in "Latest" follows the developer's newest model, so its rates change when the name moves to a new model.
- On 11 October OpenRouter moved most speech-to-text rates from per minute or per hour to per second. Those rows say "Same price" when the hourly cost did not change.
- Conditional rates (long-context prices above a token threshold, and time-of-day prices in UTC windows) that appear or vanish together show as one row per model.
- We check the list on the dates above, not every day: a price that changed and changed back between two snapshots is not here.
Changes by
Compared with the snapshot of : 202 rate changes, 0 unit changes, 21 new and 26 dropped charges on 85 models.
| Model | Charge | Before | After | Change |
|---|---|---|---|---|
| ClefCloudflare | Text input | $0.042 per 1M tokens | $0.24 per 1M tokens | +471% |
| Clef FlashCloudflare | Text input | $0.021 per 1M tokens | $0.038 per 1M tokens | +81% |
| DeepSeek Flash LatestDeepSeek | Text input | $0.0202 per 1M tokens | $0.006 per 1M tokens | -70% |
| Text output | $0.891 per 1M tokens | $0.50 per 1M tokens | -44% | |
| Cache read | $0.0054 per 1M tokens | $0.005 per 1M tokens | -7% | |
| DeepSeek Pro LatestDeepSeek | Text input | $0.225 per 1M tokens | $0.0999 per 1M tokens | -56% |
| Cache read | $0.23 per 1M tokens | $0.0999 per 1M tokens | -57% | |
| DeepSeek V3.2DeepSeek | Text input | $0.259 per 1M tokens | $0.26 per 1M tokens | +0.4% |
| Text output | $0.80 per 1M tokens | $0.38 per 1M tokens | -52% | |
| Cache read | $0.14 per 1M tokens | $0.13 per 1M tokens | -7% | |
| DeepSeek V4 Flash 0731DeepSeek | Text input | $0.016 per 1M tokens | $0.0434 per 1M tokens | +171% |
| Text output | $0.64 per 1M tokens | $0.30 per 1M tokens | -53% | |
| Cache read | $0.016 per 1M tokens | $0.035 per 1M tokens | +119% | |
| DeepSeek V4 Flash LatestDeepSeek | Text input | $0.0144 per 1M tokens | $0.0434 per 1M tokens | +201% |
| Text output | $0.576 per 1M tokens | $0.30 per 1M tokens | -48% | |
| Cache read | $0.0108 per 1M tokens | $0.035 per 1M tokens | +224% | |
| DeepSeek V4 Flash Vision ExpDeepSeek | Text input | $0.2156 per 1M tokens | $0.44 per 1M tokens | +104% |
| Text output | $0.6468 per 1M tokens | $1.32 per 1M tokens | +104% | |
| Cache read | $0.00686 per 1M tokens | $0.014 per 1M tokens | +104% | |
| DeepSeek V4 Pro 0423DeepSeek | Text input | $0.9553 per 1M tokens | $0.894 per 1M tokens | -6% |
| Text output | $1.911 per 1M tokens | $1.788 per 1M tokens | -6% | |
| Cache read | $0.0796 per 1M tokens | $0.0745 per 1M tokens | -6% | |
| DeepSeek V4 Pro 0813DeepSeek | Text input | $0.66 per 1M tokens | $0.111 per 1M tokens | -83% |
| Text output | $1.98 per 1M tokens | $4.44 per 1M tokens | +124% | |
| Cache read | $0.022 per 1M tokens | $0.097 per 1M tokens | +341% | |
| 3 long-context rates (above 0 input tokens) | Listed | Not listed | No longer listed | |
| 15 time-of-day rates (5 UTC windows) | Listed | Not listed | No longer listed | |
| DeepSeek V4.1 FlashDeepSeek | Text input | $0.0202 per 1M tokens | $0.051 per 1M tokens | +153% |
| Text output | $0.891 per 1M tokens | $0.567 per 1M tokens | -36% | |
| Cache read | $0.0054 per 1M tokens | $0.018 per 1M tokens | +233% | |
| Eleven Flash v2ElevenLabs | Text input | $20.00 per 1M characters | $40.00 per 1M characters | +100% |
| Eleven Flash v2.5ElevenLabs | Text input | $20.00 per 1M characters | $40.00 per 1M characters | +100% |
| Eleven Multilingual v2ElevenLabs | Text input | $40.00 per 1M characters | $80.00 per 1M characters | +100% |
| Eleven Turbo v2ElevenLabs | Text input | $20.00 per 1M characters | $40.00 per 1M characters | +100% |
| Eleven Turbo v2.5ElevenLabs | Text input | $20.00 per 1M characters | $40.00 per 1M characters | +100% |
| Eleven v3ElevenLabs | Text input | $40.00 per 1M characters | $80.00 per 1M characters | +100% |
| Eleven v3 ConversationalElevenLabs | Text input | $20.00 per 1M characters | $40.00 per 1M characters | +100% |
| Eleven v4ElevenLabs | Text input | $40.00 per 1M characters | $80.00 per 1M characters | +100% |
| Eleven v4 TurboElevenLabs | Text input | $20.00 per 1M characters | $40.00 per 1M characters | +100% |
| FLUX 3 VideoBlack Forest Labs | cents per second output 2k | Not listed | $0.28 per second | New charge |
| cents per second output 4k | Not listed | $0.41 per second | New charge | |
| cents per second video continuation 2k | Not listed | $0.31 per second | New charge | |
| cents per second video continuation 4k | Not listed | $0.45 per second | New charge | |
| FLUX Video UpscaleBlack Forest Labs | cents per megapixel second precise | $0.075 per megapixel second | $0.035 per megapixel second | -53% |
| cents per megapixel second creative | $0.105 per megapixel second | $0.05 per megapixel second | -52% | |
| Gemini 3.8 FlashGoogle | Text input | $0.75 per 1M tokens | $0.825 per 1M tokens | +10% |
| Text output | $3.75 per 1M tokens | $4.125 per 1M tokens | +10% | |
| Cache read | $0.075 per 1M tokens | $0.0825 per 1M tokens | +10% | |
| Audio input | $0.75 per 1M tokens | $0.825 per 1M tokens | +10% | |
| Cached audio input | $0.075 per 1M tokens | $0.0825 per 1M tokens | +10% | |
| Gemini Pro LatestGoogle | Text output | $12.00 per 1M tokens | $10.00 per 1M tokens | -17% |
| Cache read | $0.20 per 1M tokens | $0.10 per 1M tokens | -50% | |
| Cache write | $0.375 per 1M tokens | $0.1875 per 1M tokens | -50% | |
| Cached audio input | $0.20 per 1M tokens | $0.10 per 1M tokens | -50% | |
| 5 long-context rates (above 200,000 input tokens) | Listed | Not listed | No longer listed | |
| Gemma 4 31BGoogle | Text input | $0.09 per 1M tokens | $0.20 per 1M tokens | +122% |
| Text output | $0.34 per 1M tokens | $0.40 per 1M tokens | +18% | |
| Cache read | $0.05 per 1M tokens | Not listed | No longer listed | |
| GLM 4.5 AirZ.ai | Text input | $0.13 per 1M tokens | $0.20 per 1M tokens | +54% |
| Text output | $0.85 per 1M tokens | $1.10 per 1M tokens | +29% | |
| Cache read | $0.025 per 1M tokens | $0.03 per 1M tokens | +20% | |
| GLM 5Z.ai | Text input | $0.60 per 1M tokens | $1.00 per 1M tokens | +67% |
| Text output | $1.92 per 1M tokens | $3.20 per 1M tokens | +67% | |
| Cache read | $0.12 per 1M tokens | $0.20 per 1M tokens | +67% | |
| GLM 5.1Z.ai | Text input | $1.33 per 1M tokens | $1.40 per 1M tokens | +5% |
| Text output | $4.18 per 1M tokens | $4.40 per 1M tokens | +5% | |
| Cache read | $0.247 per 1M tokens | $0.26 per 1M tokens | +5% | |
| GLM 5.2Z.ai | Text input | $0.05 per 1M tokens | $0.006 per 1M tokens | -88% |
| Text output | $7.00 per 1M tokens | $6.80 per 1M tokens | -3% | |
| Cache read | $0.049 per 1M tokens | $0.005 per 1M tokens | -90% | |
| GLM 5.3Z.ai | Text input | $0.079 per 1M tokens | $0.0699 per 1M tokens | -12% |
| Text output | $4.80 per 1M tokens | $1.40 per 1M tokens | -71% | |
| Cache read | $0.059 per 1M tokens | $0.0689 per 1M tokens | +17% | |
| GLM 5.3 FlashZ.ai | Text input | $0.036 per 1M tokens | $0.0335 per 1M tokens | -7% |
| Text output | $0.90 per 1M tokens | $0.083 per 1M tokens | -91% | |
| Cache read | $0.0108 per 1M tokens | $0.03 per 1M tokens | +178% | |
| GLM 5.3 Flash (batch)Z.ai | Text input | $0.06 per 1M tokens | $0.043 per 1M tokens | -28% |
| Text output | $0.20 per 1M tokens | $0.087 per 1M tokens | -56% | |
| Cache read | $0.012 per 1M tokens | $0.018 per 1M tokens | +50% | |
| GLM 5.3 FlashXZ.ai | Cache read | $0.09 per 1M tokens | $0.075 per 1M tokens | -17% |
| GLM Flash LatestZ.ai | Text input | $0.036 per 1M tokens | $0.0335 per 1M tokens | -7% |
| Text output | $0.90 per 1M tokens | $0.083 per 1M tokens | -91% | |
| Cache read | $0.0108 per 1M tokens | $0.03 per 1M tokens | +178% | |
| GLM LatestZ.ai | Text input | $0.0576 per 1M tokens | $0.0699 per 1M tokens | +21% |
| Text output | $4.40 per 1M tokens | $1.40 per 1M tokens | -68% | |
| Cache read | $0.0536 per 1M tokens | $0.0689 per 1M tokens | +29% | |
| GPT Terra LatestOpenAI | Text input | $2.00 per 1M tokens | $1.00 per 1M tokens | -50% |
| Text output | $12.00 per 1M tokens | $5.00 per 1M tokens | -58% | |
| Cache read | $0.20 per 1M tokens | $0.05 per 1M tokens | -75% | |
| Cache write | $2.50 per 1M tokens | $1.25 per 1M tokens | -50% | |
| Text input, above 272,000 input tokens | $4.00 per 1M tokens | $2.00 per 1M tokens | -50% | |
| Text output, above 272,000 input tokens | $18.00 per 1M tokens | $7.50 per 1M tokens | -58% | |
| Cache read, above 272,000 input tokens | $0.40 per 1M tokens | $0.10 per 1M tokens | -75% | |
| Cache write, above 272,000 input tokens | $5.00 per 1M tokens | $2.50 per 1M tokens | -50% | |
| GPT-4.1 NanoOpenAI | Cache read | $0.025 per 1M tokens | $0.03 per 1M tokens | +20% |
| GPT-5.6 SolOpenAI | Text input | $2.00 per 1M tokens | $4.00 per 1M tokens | +100% |
| Text output | $10.00 per 1M tokens | $20.00 per 1M tokens | +100% | |
| Cache read | $0.20 per 1M tokens | $0.40 per 1M tokens | +100% | |
| Cache write | $2.50 per 1M tokens | $5.00 per 1M tokens | +100% | |
| Text input, above 272,000 input tokens | $4.00 per 1M tokens | $8.00 per 1M tokens | +100% | |
| Text output, above 272,000 input tokens | $15.00 per 1M tokens | $30.00 per 1M tokens | +100% | |
| Cache read, above 272,000 input tokens | $0.40 per 1M tokens | $0.80 per 1M tokens | +100% | |
| Cache write, above 272,000 input tokens | $5.00 per 1M tokens | $10.00 per 1M tokens | +100% | |
| GPT-5.6 Sol (batch)OpenAI | Text input | $1.00 per 1M tokens | $2.00 per 1M tokens | +100% |
| Text output | $5.00 per 1M tokens | $10.00 per 1M tokens | +100% | |
| Cache read | $0.10 per 1M tokens | $0.20 per 1M tokens | +100% | |
| Cache write | $1.25 per 1M tokens | $2.50 per 1M tokens | +100% | |
| Text input, above 272,000 input tokens | $2.00 per 1M tokens | $4.00 per 1M tokens | +100% | |
| Text output, above 272,000 input tokens | $7.50 per 1M tokens | $15.00 per 1M tokens | +100% | |
| Cache read, above 272,000 input tokens | $0.20 per 1M tokens | $0.40 per 1M tokens | +100% | |
| Cache write, above 272,000 input tokens | $2.50 per 1M tokens | $5.00 per 1M tokens | +100% | |
| GPT-5.6 Sol ProOpenAI | Text input | $2.00 per 1M tokens | $4.00 per 1M tokens | +100% |
| Text output | $10.00 per 1M tokens | $20.00 per 1M tokens | +100% | |
| Cache read | $0.20 per 1M tokens | $0.40 per 1M tokens | +100% | |
| Cache write | $2.50 per 1M tokens | $5.00 per 1M tokens | +100% | |
| Text input, above 272,000 input tokens | $4.00 per 1M tokens | $8.00 per 1M tokens | +100% | |
| Text output, above 272,000 input tokens | $15.00 per 1M tokens | $30.00 per 1M tokens | +100% | |
| Cache read, above 272,000 input tokens | $0.40 per 1M tokens | $0.80 per 1M tokens | +100% | |
| Cache write, above 272,000 input tokens | $5.00 per 1M tokens | $10.00 per 1M tokens | +100% | |
| GPT-5.6 Sol Pro (batch)OpenAI | Text input | $1.00 per 1M tokens | $2.00 per 1M tokens | +100% |
| Text output | $5.00 per 1M tokens | $10.00 per 1M tokens | +100% | |
| Cache read | $0.10 per 1M tokens | $0.20 per 1M tokens | +100% | |
| Cache write | $1.25 per 1M tokens | $2.50 per 1M tokens | +100% | |
| Text input, above 272,000 input tokens | $2.00 per 1M tokens | $4.00 per 1M tokens | +100% | |
| Text output, above 272,000 input tokens | $7.50 per 1M tokens | $15.00 per 1M tokens | +100% | |
| Cache read, above 272,000 input tokens | $0.20 per 1M tokens | $0.40 per 1M tokens | +100% | |
| Cache write, above 272,000 input tokens | $2.50 per 1M tokens | $5.00 per 1M tokens | +100% | |
| gpt-oss-120bOpenAI | Text input | $0.037 per 1M tokens | $0.15 per 1M tokens | +305% |
| Text output | $0.17 per 1M tokens | $0.60 per 1M tokens | +253% | |
| Cache read | Not listed | $0.075 per 1M tokens | New charge | |
| gpt-oss-20bOpenAI | Text input | $0.018 per 1M tokens | $0.03 per 1M tokens | +67% |
| Text output | $0.09 per 1M tokens | $0.13 per 1M tokens | +44% | |
| Cache read | $0.009 per 1M tokens | $0.03 per 1M tokens | +233% | |
| Grok LatestSpaceXAI | Cache write | Not listed | $0 per 1M tokens | New charge |
| Web search | $0.005 per search | $0.01 per search | +100% | |
| 1 long-context rates (above 200,000 input tokens) | Not listed | Listed | New charge | |
| Web search, above 200,000 input tokens | $0.005 per search | $0.01 per search | +100% | |
| Hermes 4 405BNous | Cache read | Not listed | $0.20 per 1M tokens | New charge |
| HeyGen VideoHeyGen | duration seconds 1080p | Not listed | $0.10 per second | New charge |
| long duration seconds 2k | Not listed | $0.105 per second | New charge | |
| long duration seconds 480p | Not listed | $0.045 per second | New charge | |
| long duration seconds 768p | Not listed | $0.075 per second | New charge | |
| long duration seconds 1080p | Not listed | $0.105 per second | New charge | |
| reference duration seconds 1080p | Not listed | $0.18 per second | New charge | |
| HeyGen Voice TurboHeyGen | Text input | $7.50 per 1M characters | $4.00 per 1M characters | -47% |
| Hy3Tencent | Text input | $0.132 per 1M tokens | $0.0825 per 1M tokens | -37% |
| Text output | $0.528 per 1M tokens | $0.33 per 1M tokens | -37% | |
| Cache read | $0.033 per 1M tokens | $0.0206 per 1M tokens | -37% | |
| Hy4 previewTencent | Text input | $0.834 per 1M tokens | $0.7506 per 1M tokens | -10% |
| Text output | $2.501 per 1M tokens | $2.251 per 1M tokens | -10% | |
| Cache read | $0.042 per 1M tokens | $0.0378 per 1M tokens | -10% | |
| Kimi K2.5MoonshotAI | Text input | $0.50 per 1M tokens | $0.532 per 1M tokens | +6% |
| Text output | $2.50 per 1M tokens | $3.325 per 1M tokens | +33% | |
| Cache read | $0.15 per 1M tokens | $0.209 per 1M tokens | +39% | |
| Kimi K2.7 CodeMoonshotAI | Text input | $0.6712 per 1M tokens | $0.60 per 1M tokens | -11% |
| Text output | $3.35 per 1M tokens | $3.50 per 1M tokens | +4% | |
| Cache read | $0.18 per 1M tokens | $0.16 per 1M tokens | -11% | |
| Kimi K3MoonshotAI | Text input | $0.62 per 1M tokens | $0.192 per 1M tokens | -69% |
| Text output | $15.00 per 1M tokens | $16.00 per 1M tokens | +7% | |
| Cache read | $0.32 per 1M tokens | $0.182 per 1M tokens | -43% | |
| Kimi LatestMoonshotAI | Text input | $0.496 per 1M tokens | $0.1824 per 1M tokens | -63% |
| Text output | $14.00 per 1M tokens | $9.747 per 1M tokens | -30% | |
| Cache read | $0.30 per 1M tokens | $0.18 per 1M tokens | -40% | |
| Ling 3.1 FlashinclusionAI | Text input | $0.075 per 1M tokens | $0.045 per 1M tokens | -40% |
| Text output | $0.225 per 1M tokens | $0.135 per 1M tokens | -40% | |
| Cache read | $0.015 per 1M tokens | $0.009 per 1M tokens | -40% | |
| Llama 3.1 70B InstructMeta | Text input | $0.40 per 1M tokens | $0.72 per 1M tokens | +80% |
| Text output | $0.40 per 1M tokens | $0.72 per 1M tokens | +80% | |
| Llama 3.1 8B InstructMeta | Text input | $0.05 per 1M tokens | $0.02 per 1M tokens | -60% |
| Text output | $0.08 per 1M tokens | $0.04 per 1M tokens | -50% | |
| Cache read | $0.025 per 1M tokens | Not listed | No longer listed | |
| Llama 4 MaverickMeta | Text input | $0.1875 per 1M tokens | $0.35 per 1M tokens | +87% |
| Text output | $0.6525 per 1M tokens | $1.00 per 1M tokens | +53% | |
| Cache read | $0.05 per 1M tokens | $0.17 per 1M tokens | +240% | |
| Llama 4 ScoutMeta | Text input | $0.18 per 1M tokens | $0.10 per 1M tokens | -44% |
| Text output | $0.59 per 1M tokens | $0.30 per 1M tokens | -49% | |
| Magnum v4 72Banthracite-org | Cache read | Not listed | $2.50 per 1M tokens | New charge |
| MiMo-V2.5Xiaomi | Text input | $0.14 per 1M tokens | $0.40 per 1M tokens | +186% |
| Text output | $0.28 per 1M tokens | $2.00 per 1M tokens | +614% | |
| Cache read | $0.0028 per 1M tokens | $0.08 per 1M tokens | +2,757% | |
| MiMo-V2.5-ProXiaomi | Text input | $0.435 per 1M tokens | $0.48 per 1M tokens | +10% |
| Text output | $0.87 per 1M tokens | $1.80 per 1M tokens | +107% | |
| Cache read | $0.0036 per 1M tokens | $0.096 per 1M tokens | +2,567% | |
| MiniMax M2.5MiniMax | Text input | $0.27 per 1M tokens | $0.30 per 1M tokens | +11% |
| Text output | $1.08 per 1M tokens | $1.20 per 1M tokens | +11% | |
| Cache read | $0.027 per 1M tokens | $0.06 per 1M tokens | +122% | |
| MiniMax M2.7MiniMax | Text input | $0.30 per 1M tokens | $0.21 per 1M tokens | -30% |
| Text output | $1.20 per 1M tokens | $0.84 per 1M tokens | -30% | |
| Cache read | $0.06 per 1M tokens | $0.042 per 1M tokens | -30% | |
| Mistral Large 4Mistral | Text input | $0.68 per 1M tokens | $0.70 per 1M tokens | +3% |
| Text output | $2.09 per 1M tokens | $2.10 per 1M tokens | +0.5% | |
| Mistral Small 3.2 24BMistral | Text input | $0.0938 per 1M tokens | $0.10 per 1M tokens | +7% |
| Text output | $0.25 per 1M tokens | $0.30 per 1M tokens | +20% | |
| Cache read | Not listed | $0.01 per 1M tokens | New charge | |
| Nemotron 3 Nano 30B A3BNVIDIA | Cache read | Not listed | $0.012 per 1M tokens | New charge |
| Nemotron 3 SuperNVIDIA | Text input | $0.08 per 1M tokens | $0.075 per 1M tokens | -6% |
| Text output | $0.45 per 1M tokens | $0.40 per 1M tokens | -11% | |
| Parakeet TDT 0.6B v3NVIDIA | Audio input | $0.000025 per second | $0.00001667 per second | -33% |
| Pareto Latestunbiased | Text input | $2.50 per 1M tokens | $0.80 per 1M tokens | -68% |
| Text output | $7.50 per 1M tokens | $3.20 per 1M tokens | -57% | |
| Cache read | $0.25 per 1M tokens | $0.03 per 1M tokens | -88% | |
| Qwen3 235B A22B Instruct 2507Qwen | Text input | $0.09 per 1M tokens | $0.14 per 1M tokens | +56% |
| Text output | $0.55 per 1M tokens | $0.80 per 1M tokens | +45% | |
| Cache read | Not listed | $0.05 per 1M tokens | New charge | |
| Qwen3 30B A3B Instruct 2507Qwen | Cache read | Not listed | $0.10 per 1M tokens | New charge |
| Qwen3 Coder 30B A3B InstructQwen | Text input | $0.07 per 1M tokens | $0.15 per 1M tokens | +114% |
| Text output | $0.28 per 1M tokens | $0.60 per 1M tokens | +114% | |
| Qwen3 Next 80B A3B InstructQwen | Text input | $0.10 per 1M tokens | $0.09 per 1M tokens | -10% |
| Cache read | $0.07 per 1M tokens | Not listed | No longer listed | |
| Qwen3.5 397B A17BQwen | Text input | $0.50 per 1M tokens | $0.60 per 1M tokens | +20% |
| Cache read | $0.30 per 1M tokens | $0.12 per 1M tokens | -60% | |
| Qwen3.5-35B-A3BQwen | Text input | $0.15 per 1M tokens | $0.14 per 1M tokens | -7% |
| Qwen3.5-9BQwen | Text input | $0.10 per 1M tokens | $0.17 per 1M tokens | +70% |
| Text output | $0.15 per 1M tokens | $0.25 per 1M tokens | +67% | |
| Qwen3.6 35B A3BQwen | Text output | $0.95 per 1M tokens | $0.90 per 1M tokens | -5% |
| Cache read | $0.10 per 1M tokens | $0.025 per 1M tokens | -75% | |
| Qwen3.8 27BQwen | Text input | $0.04 per 1M tokens | $0.15 per 1M tokens | +275% |
| Text output | $2.30 per 1M tokens | $1.875 per 1M tokens | -18% | |
| Cache read | $0.0198 per 1M tokens | $0.0375 per 1M tokens | +89% | |
| ReMM SLERP 13Bundi95 | Cache read | Not listed | $0.35 per 1M tokens | New charge |
| Scribe v2ElevenLabs | Audio input | $0.00003056 per second | $0.00006111 per second | +100% |
| Scribe v2 MedicalElevenLabs | Audio input | $0.00003056 per second | $0.00006111 per second | +100% |
| Solar Pro 4Upstage | Text input | $0.09 per 1M tokens | $0.15 per 1M tokens | +67% |
| Text output | $0.36 per 1M tokens | $0.60 per 1M tokens | +67% | |
| Cache read | $0.018 per 1M tokens | $0.03 per 1M tokens | +67% | |
| Step 5 PreviewStepFun | Cache read | $0.05 per 1M tokens | $0.10 per 1M tokens | +100% |
| Universal-3.5 ProAssemblyAI | Audio input | $0.000125 per second | $0.00008333 per second | -33% |
| Audio input, prompted | $0.0001389 per second | $0.00009722 per second | -30% | |
| Weaver (alpha)Mancer | Cache read | Not listed | $0.40 per 1M tokens | New charge |
Changes by
Compared with the snapshot of : 79 rate changes, 0 unit changes, 1 new and 0 dropped charges on 30 models.
| Model | Charge | Before | After | Change |
|---|---|---|---|---|
| ClefCloudflare | Text input | $0.24 per 1M tokens | $0.042 per 1M tokens | -83% |
| Clef FlashCloudflare | Text input | $0.038 per 1M tokens | $0.021 per 1M tokens | -45% |
| d1LiquidAI | Text input | $0.04 per 1M tokens | $0.02 per 1M tokens | -50% |
| Cache read | $0.04 per 1M tokens | $0.02 per 1M tokens | -50% | |
| DeepSeek Flash LatestDeepSeek | Text input | $0.0348 per 1M tokens | $0.0202 per 1M tokens | -42% |
| Text output | $0.1392 per 1M tokens | $0.891 per 1M tokens | +540% | |
| Cache read | $0.000696 per 1M tokens | $0.0054 per 1M tokens | +676% | |
| DeepSeek Pro LatestDeepSeek | Text input | $0.2191 per 1M tokens | $0.225 per 1M tokens | +3% |
| Text output | $0.6574 per 1M tokens | $8.00 per 1M tokens | +1,117% | |
| Cache read | $0.006972 per 1M tokens | $0.23 per 1M tokens | +3,199% | |
| DeepSeek V4 Flash 0423DeepSeek | Text input | $0.03 per 1M tokens | $0.091 per 1M tokens | +203% |
| Text output | $1.28 per 1M tokens | $0.182 per 1M tokens | -86% | |
| Cache read | $0.03 per 1M tokens | $0.0182 per 1M tokens | -39% | |
| DeepSeek V4 Flash 0731DeepSeek | Text input | $0.018 per 1M tokens | $0.016 per 1M tokens | -11% |
| Cache read | $0.018 per 1M tokens | $0.016 per 1M tokens | -11% | |
| DeepSeek V4 Flash LatestDeepSeek | Text input | $0.018 per 1M tokens | $0.0144 per 1M tokens | -20% |
| Text output | $0.64 per 1M tokens | $0.576 per 1M tokens | -10% | |
| Cache read | $0.018 per 1M tokens | $0.0108 per 1M tokens | -40% | |
| DeepSeek V4 Pro 0423DeepSeek | Text input | $0.2088 per 1M tokens | $0.9553 per 1M tokens | +358% |
| Text output | $0.4176 per 1M tokens | $1.911 per 1M tokens | +358% | |
| Cache read | $0.0174 per 1M tokens | $0.0796 per 1M tokens | +358% | |
| DeepSeek V4.1 FlashDeepSeek | Text input | $0.30 per 1M tokens | $0.0202 per 1M tokens | -93% |
| Text output | $1.20 per 1M tokens | $0.891 per 1M tokens | -26% | |
| Cache read | $0.006 per 1M tokens | $0.0054 per 1M tokens | -10% | |
| Gemma 4 26B A4B Google | Text input | $0.0675 per 1M tokens | $0.09 per 1M tokens | +33% |
| Text output | $0.225 per 1M tokens | $0.30 per 1M tokens | +33% | |
| Cache read | $0.0375 per 1M tokens | $0.05 per 1M tokens | +33% | |
| GLM 5.1Z.ai | Text input | $0.966 per 1M tokens | $1.33 per 1M tokens | +38% |
| Text output | $3.036 per 1M tokens | $4.18 per 1M tokens | +38% | |
| Cache read | $0.1794 per 1M tokens | $0.247 per 1M tokens | +38% | |
| GLM 5.2Z.ai | Text input | $0.06 per 1M tokens | $0.05 per 1M tokens | -17% |
| Cache read | $0.059 per 1M tokens | $0.049 per 1M tokens | -17% | |
| GLM 5.3Z.ai | Text input | $0.07 per 1M tokens | $0.079 per 1M tokens | +13% |
| Cache read | $0.05 per 1M tokens | $0.059 per 1M tokens | +18% | |
| GLM 5.3 FlashZ.ai | Text input | $0.15 per 1M tokens | $0.036 per 1M tokens | -76% |
| Text output | $0.50 per 1M tokens | $0.90 per 1M tokens | +80% | |
| Cache read | $0.03 per 1M tokens | $0.0108 per 1M tokens | -64% | |
| GLM Flash LatestZ.ai | Text input | $0.04 per 1M tokens | $0.036 per 1M tokens | -10% |
| Text output | $0.50 per 1M tokens | $0.90 per 1M tokens | +80% | |
| Cache read | $0.0125 per 1M tokens | $0.0108 per 1M tokens | -14% | |
| GLM LatestZ.ai | Text input | $0.07 per 1M tokens | $0.0576 per 1M tokens | -18% |
| Text output | $4.80 per 1M tokens | $4.40 per 1M tokens | -8% | |
| Cache read | $0.05 per 1M tokens | $0.0536 per 1M tokens | +7% | |
| HeyGen VideoHeyGen | duration seconds 2k | $0.09 per second | $0.10 per second | +11% |
| duration seconds 768p | $0.03 per second | $0.036 per second | +20% | |
| reference duration seconds 480p | $0.04 per second | $0.07 per second | +75% | |
| reference duration seconds 768p | $0.06 per second | $0.10 per second | +67% | |
| Hy3Tencent | Text input | $0.0825 per 1M tokens | $0.132 per 1M tokens | +60% |
| Text output | $0.33 per 1M tokens | $0.528 per 1M tokens | +60% | |
| Cache read | $0.0206 per 1M tokens | $0.033 per 1M tokens | +60% | |
| Hy4 previewTencent | Text input | $0.7506 per 1M tokens | $0.834 per 1M tokens | +11% |
| Text output | $2.251 per 1M tokens | $2.501 per 1M tokens | +11% | |
| Cache read | $0.0378 per 1M tokens | $0.042 per 1M tokens | +11% | |
| Kimi K3MoonshotAI | Text input | $0.80 per 1M tokens | $0.62 per 1M tokens | -22% |
| Text output | $13.50 per 1M tokens | $15.00 per 1M tokens | +11% | |
| Cache read | $0.55 per 1M tokens | $0.32 per 1M tokens | -42% | |
| Kimi LatestMoonshotAI | Text input | $0.74 per 1M tokens | $0.496 per 1M tokens | -33% |
| Text output | $15.00 per 1M tokens | $14.00 per 1M tokens | -7% | |
| Ling 3.0 Flash VLinclusionAI | Text input | $0.021 per 1M tokens | $0.06 per 1M tokens | +186% |
| Text output | $0.0616 per 1M tokens | $0.18 per 1M tokens | +192% | |
| Cache read | $0.0042 per 1M tokens | $0.012 per 1M tokens | +186% | |
| Ling 3.1 FlashinclusionAI | Text input | $0 per 1M tokens | $0.075 per 1M tokens | Was free |
| Text output | $0 per 1M tokens | $0.225 per 1M tokens | Was free | |
| Cache read | Not listed | $0.015 per 1M tokens | New charge | |
| Llama 3.3 70B InstructMeta | Text input | $0.22 per 1M tokens | $0.59 per 1M tokens | +168% |
| Text output | $0.50 per 1M tokens | $0.79 per 1M tokens | +58% | |
| Cache read | $0.11 per 1M tokens | $0.295 per 1M tokens | +168% | |
| Llama 4 ScoutMeta | Text input | $0.10 per 1M tokens | $0.18 per 1M tokens | +80% |
| Text output | $0.30 per 1M tokens | $0.59 per 1M tokens | +97% | |
| MiniMax M2 | Text input | $0.30 per 1M tokens | $0.255 per 1M tokens | -15% |
| Text output | $1.20 per 1M tokens | $1.02 per 1M tokens | -15% | |
| MiniMax M2.7MiniMax | Text input | $0.21 per 1M tokens | $0.30 per 1M tokens | +43% |
| Text output | $0.84 per 1M tokens | $1.20 per 1M tokens | +43% | |
| Cache read | $0.042 per 1M tokens | $0.06 per 1M tokens | +43% | |
| Qwen3.5 397B A17BQwen | Text input | $0.55 per 1M tokens | $0.50 per 1M tokens | -9% |
| Text output | $3.50 per 1M tokens | $3.60 per 1M tokens | +3% | |
| Cache read | $0.225 per 1M tokens | $0.30 per 1M tokens | +33% | |
| Qwen3.5-35B-A3BQwen | Text input | $0.08 per 1M tokens | $0.15 per 1M tokens | +87% |
| Text output | $0.75 per 1M tokens | $1.00 per 1M tokens | +33% | |
| Cache read | $0.04 per 1M tokens | $0.05 per 1M tokens | +25% |
Changes by
Compared with the snapshot of : 158 rate changes, 8 unit changes, 44 new and 32 dropped charges on 79 models.
| Model | Charge | Before | After | Change |
|---|---|---|---|---|
| Chirp 3Google | Audio input | $0.016 per minute | $0.0002667 per second | Same price |
| Claude Haiku LatestAnthropic | Text input | $1.00 per 1M tokens | $0.10 per 1M tokens | -90% |
| Text output | $5.00 per 1M tokens | $0.50 per 1M tokens | -90% | |
| Cache read | $0.10 per 1M tokens | $0.01 per 1M tokens | -90% | |
| Cache write | $1.25 per 1M tokens | $0.125 per 1M tokens | -90% | |
| Cache write (1 hour) | $2.00 per 1M tokens | $0.20 per 1M tokens | -90% | |
| 6 long-context rates (above 100,000 input tokens) | Not listed | Listed | New charge | |
| Claude Opus LatestAnthropic | Text input | $5.00 per 1M tokens | $4.00 per 1M tokens | -20% |
| Text output | $25.00 per 1M tokens | $20.00 per 1M tokens | -20% | |
| Cache read | $0.50 per 1M tokens | $0.20 per 1M tokens | -60% | |
| Cache write | $6.25 per 1M tokens | $5.00 per 1M tokens | -20% | |
| Cache write (1 hour) | $10.00 per 1M tokens | $8.00 per 1M tokens | -20% | |
| Claude Sonnet LatestAnthropic | Cache read | $0.20 per 1M tokens | $0.10 per 1M tokens | -50% |
| DeepSeek V3DeepSeek | Text input | $0.2574 per 1M tokens | $0.32 per 1M tokens | +24% |
| Text output | $1.029 per 1M tokens | $0.89 per 1M tokens | -13% | |
| DeepSeek V3 0324DeepSeek | Text input | $0.25 per 1M tokens | $0.29 per 1M tokens | +16% |
| Text output | $1.00 per 1M tokens | $1.14 per 1M tokens | +14% | |
| Cache read | Not listed | $0.11 per 1M tokens | New charge | |
| DeepSeek V3.1 TerminusDeepSeek | Cache read | $0.135 per 1M tokens | Not listed | No longer listed |
| DeepSeek V3.2DeepSeek | Text input | $0.269 per 1M tokens | $0.259 per 1M tokens | -4% |
| Text output | $0.40 per 1M tokens | $0.80 per 1M tokens | +100% | |
| Cache read | $0.1345 per 1M tokens | $0.14 per 1M tokens | +4% | |
| DeepSeek V4 Flash 0423DeepSeek | Text input | $0.0659 per 1M tokens | $0.03 per 1M tokens | -55% |
| Text output | $0.1319 per 1M tokens | $1.28 per 1M tokens | +871% | |
| Cache read | $0.0132 per 1M tokens | $0.03 per 1M tokens | +127% | |
| DeepSeek V4 Flash 0731DeepSeek | Text input | $0.04 per 1M tokens | $0.018 per 1M tokens | -55% |
| Text output | $0.08 per 1M tokens | $0.64 per 1M tokens | +700% | |
| Cache read | $0.008 per 1M tokens | $0.018 per 1M tokens | +125% | |
| DeepSeek V4 Flash LatestDeepSeek | Text input | $0.03 per 1M tokens | $0.018 per 1M tokens | -40% |
| Text output | $0.07 per 1M tokens | $0.64 per 1M tokens | +814% | |
| Cache read | $0.003 per 1M tokens | $0.018 per 1M tokens | +500% | |
| DeepSeek V4 Flash Vision ExpDeepSeek | Text input | $0.22 per 1M tokens | $0.2156 per 1M tokens | -2% |
| Text output | $0.66 per 1M tokens | $0.6468 per 1M tokens | -2% | |
| Cache read | $0.007 per 1M tokens | $0.00686 per 1M tokens | -2% | |
| DeepSeek V4 Pro 0423DeepSeek | Text input | $1.60 per 1M tokens | $0.2088 per 1M tokens | -87% |
| Text output | $3.20 per 1M tokens | $0.4176 per 1M tokens | -87% | |
| Cache read | $0.135 per 1M tokens | $0.0174 per 1M tokens | -87% | |
| DeepSeek V4 Pro 0813DeepSeek | Text input | $0.5795 per 1M tokens | $0.66 per 1M tokens | +14% |
| Text output | $1.738 per 1M tokens | $1.98 per 1M tokens | +14% | |
| Cache read | $0.0193 per 1M tokens | $0.022 per 1M tokens | +14% | |
| 3 long-context rates (above 0 input tokens) | Not listed | Listed | New charge | |
| 15 time-of-day rates (5 UTC windows) | Not listed | Listed | New charge | |
| DeepSeek V4.1 FlashDeepSeek | Text input | $0.15 per 1M tokens | $0.30 per 1M tokens | +100% |
| Text output | $0.60 per 1M tokens | $1.20 per 1M tokens | +100% | |
| Cache read | $0.003 per 1M tokens | $0.006 per 1M tokens | +100% | |
| 3 long-context rates (above 0 input tokens) | Listed | Not listed | No longer listed | |
| 15 time-of-day rates (5 UTC windows) | Listed | Not listed | No longer listed | |
| Gemma 4 26B A4B Google | Text input | $0.042 per 1M tokens | $0.0675 per 1M tokens | +61% |
| Text output | $0.22 per 1M tokens | $0.225 per 1M tokens | +2% | |
| Cache read | Not listed | $0.0375 per 1M tokens | New charge | |
| GLM 4.6Z.ai | Text input | $0.43 per 1M tokens | $0.50 per 1M tokens | +16% |
| Text output | $1.75 per 1M tokens | $2.00 per 1M tokens | +14% | |
| Cache read | $0.08 per 1M tokens | $0.10 per 1M tokens | +25% | |
| GLM 4.7Z.ai | Text input | $0.40 per 1M tokens | $0.60 per 1M tokens | +50% |
| Text output | $1.75 per 1M tokens | $2.20 per 1M tokens | +26% | |
| Cache read | $0.08 per 1M tokens | $0.11 per 1M tokens | +38% | |
| GLM 5.2Z.ai | Text input | $0.60 per 1M tokens | $0.06 per 1M tokens | -90% |
| Text output | $2.00 per 1M tokens | $7.00 per 1M tokens | +250% | |
| Cache read | $0.15 per 1M tokens | $0.059 per 1M tokens | -61% | |
| GLM 5.3Z.ai | Text input | $1.40 per 1M tokens | $0.07 per 1M tokens | -95% |
| Text output | $4.40 per 1M tokens | $4.80 per 1M tokens | +9% | |
| Cache read | $0.26 per 1M tokens | $0.05 per 1M tokens | -81% | |
| GLM 5.3 (batch)Z.ai | Text input | $0.70 per 1M tokens | $0.45 per 1M tokens | -36% |
| Text output | $2.20 per 1M tokens | $2.00 per 1M tokens | -9% | |
| Cache read | $0.13 per 1M tokens | $0.10 per 1M tokens | -23% | |
| GLM 5.3 Flash (batch)Z.ai | Text input | $0.075 per 1M tokens | $0.06 per 1M tokens | -20% |
| Text output | $0.25 per 1M tokens | $0.20 per 1M tokens | -20% | |
| Cache read | $0.015 per 1M tokens | $0.012 per 1M tokens | -20% | |
| GLM Flash LatestZ.ai | Text input | $0.075 per 1M tokens | $0.04 per 1M tokens | -47% |
| Text output | $0.25 per 1M tokens | $0.50 per 1M tokens | +100% | |
| Cache read | $0.015 per 1M tokens | $0.0125 per 1M tokens | -17% | |
| GLM LatestZ.ai | Text input | $0.8727 per 1M tokens | $0.07 per 1M tokens | -92% |
| Text output | $3.36 per 1M tokens | $4.80 per 1M tokens | +43% | |
| Cache read | $0.1639 per 1M tokens | $0.05 per 1M tokens | -69% | |
| GPT Luna LatestOpenAI | Text input | $0.20 per 1M tokens | $0.10 per 1M tokens | -50% |
| Text output | $1.20 per 1M tokens | $0.50 per 1M tokens | -58% | |
| Cache read | $0.02 per 1M tokens | $0.01 per 1M tokens | -50% | |
| Cache write | $0.25 per 1M tokens | $0.125 per 1M tokens | -50% | |
| Text input, above 272,000 input tokens | $0.40 per 1M tokens | $0.20 per 1M tokens | -50% | |
| Text output, above 272,000 input tokens | $1.80 per 1M tokens | $0.75 per 1M tokens | -58% | |
| Cache read, above 272,000 input tokens | $0.04 per 1M tokens | $0.02 per 1M tokens | -50% | |
| Cache write, above 272,000 input tokens | $0.50 per 1M tokens | $0.25 per 1M tokens | -50% | |
| GPT Sol LatestOpenAI | Cache read | $0.20 per 1M tokens | $0.10 per 1M tokens | -50% |
| Cache read, above 272,000 input tokens | $0.40 per 1M tokens | $0.20 per 1M tokens | -50% | |
| GPT TranscribeOpenAI | Audio input | $0.0045 per minute | $0.000075 per second | Same price |
| gpt-oss-120b (batch)OpenAI | Text input | $0.15 per 1M tokens | $0.0296 per 1M tokens | -80% |
| Text output | $0.60 per 1M tokens | $0.136 per 1M tokens | -77% | |
| gpt-oss-20bOpenAI | Text input | $0.03 per 1M tokens | $0.018 per 1M tokens | -40% |
| Text output | $0.13 per 1M tokens | $0.09 per 1M tokens | -31% | |
| Cache read | $0.03 per 1M tokens | $0.009 per 1M tokens | -70% | |
| gpt-oss-20b (batch)OpenAI | Text input | $0.05 per 1M tokens | $0.024 per 1M tokens | -52% |
| Text output | $0.20 per 1M tokens | $0.112 per 1M tokens | -44% | |
| Grok STT 1.0SpaceXAI | Audio input | $0.10 per hour | $0.00002778 per second | Same price |
| Hy4 previewTencent | Text input | $0.834 per 1M tokens | $0.7506 per 1M tokens | -10% |
| Text output | $2.501 per 1M tokens | $2.251 per 1M tokens | -10% | |
| Cache read | $0.042 per 1M tokens | $0.0378 per 1M tokens | -10% | |
| 6 time-of-day rates (2 UTC windows) | Not listed | Listed | New charge | |
| Kimi K2 ThinkingMoonshotAI | Cache read | Not listed | $0.15 per 1M tokens | New charge |
| Kimi K2.5MoonshotAI | Text input | $0.45 per 1M tokens | $0.50 per 1M tokens | +11% |
| Text output | $2.25 per 1M tokens | $2.50 per 1M tokens | +11% | |
| Cache read | $0.07 per 1M tokens | $0.15 per 1M tokens | +114% | |
| Kimi K2.6MoonshotAI | Text input | $0.95 per 1M tokens | $0.65 per 1M tokens | -32% |
| Text output | $4.00 per 1M tokens | $3.41 per 1M tokens | -15% | |
| Cache read | $0.16 per 1M tokens | $0.15 per 1M tokens | -6% | |
| Kimi K2.7 CodeMoonshotAI | Text input | $0.71 per 1M tokens | $0.6712 per 1M tokens | -5% |
| Text output | $3.50 per 1M tokens | $3.35 per 1M tokens | -4% | |
| Cache read | $0.15 per 1M tokens | $0.18 per 1M tokens | +20% | |
| Kimi K3MoonshotAI | Text input | $2.648 per 1M tokens | $0.80 per 1M tokens | -70% |
| Text output | $13.28 per 1M tokens | $13.50 per 1M tokens | +2% | |
| Cache read | $0.3026 per 1M tokens | $0.55 per 1M tokens | +82% | |
| Kimi K3 (batch)MoonshotAI | Text input | $3.00 per 1M tokens | $2.28 per 1M tokens | -24% |
| Text output | $15.00 per 1M tokens | $11.40 per 1M tokens | -24% | |
| Cache read | $0.30 per 1M tokens | $0.228 per 1M tokens | -24% | |
| Kimi LatestMoonshotAI | Text input | $2.375 per 1M tokens | $0.74 per 1M tokens | -69% |
| Text output | $13.30 per 1M tokens | $15.00 per 1M tokens | +13% | |
| Cache read | $0.2755 per 1M tokens | $0.30 per 1M tokens | +9% | |
| Krea 2 MediumKrea | Image output, style references | Not listed | $0.035 per image | New charge |
| Image output, moodboards | Not listed | $0.04 per image | New charge | |
| Krea 2 Medium TurboKrea | Image output, style references | Not listed | $0.0175 per image | New charge |
| Image output, moodboards | Not listed | $0.02 per image | New charge | |
| Ling 3.0 Flash Fin | Text input | $0.06 per 1M tokens | $0.042 per 1M tokens | -30% |
| Text output | $0.18 per 1M tokens | $0.1232 per 1M tokens | -32% | |
| Cache read | $0.012 per 1M tokens | $0.0084 per 1M tokens | -30% | |
| Ling 3.0 Flash VLinclusionAI | Text input | $0.06 per 1M tokens | $0.021 per 1M tokens | -65% |
| Text output | $0.18 per 1M tokens | $0.0616 per 1M tokens | -66% | |
| Cache read | $0.012 per 1M tokens | $0.0042 per 1M tokens | -65% | |
| Llama 3.1 70B InstructMeta | Text input | $0.72 per 1M tokens | $0.40 per 1M tokens | -44% |
| Text output | $0.72 per 1M tokens | $0.40 per 1M tokens | -44% | |
| Llama 3.3 70B InstructMeta | Text input | $0.10 per 1M tokens | $0.22 per 1M tokens | +120% |
| Text output | $0.32 per 1M tokens | $0.50 per 1M tokens | +56% | |
| Cache read | Not listed | $0.11 per 1M tokens | New charge | |
| Llama 4 MaverickMeta | Text input | $0.20 per 1M tokens | $0.1875 per 1M tokens | -6% |
| Text output | $0.696 per 1M tokens | $0.6525 per 1M tokens | -6% | |
| Cache read | Not listed | $0.05 per 1M tokens | New charge | |
| MiniMax M2 | Text input | $0.255 per 1M tokens | $0.30 per 1M tokens | +18% |
| Text output | $1.02 per 1M tokens | $1.20 per 1M tokens | +18% | |
| MiniMax M2.7MiniMax | Text input | $0.30 per 1M tokens | $0.21 per 1M tokens | -30% |
| Text output | $1.20 per 1M tokens | $0.84 per 1M tokens | -30% | |
| Cache read | $0.06 per 1M tokens | $0.042 per 1M tokens | -30% | |
| Mistral NemoMistral | Text input | $0.019 per 1M tokens | $0.029 per 1M tokens | +53% |
| Mistral Small 3.2 24BMistral | Text input | $0.075 per 1M tokens | $0.0938 per 1M tokens | +25% |
| Text output | $0.20 per 1M tokens | $0.25 per 1M tokens | +25% | |
| Muse Glimmer 30BMeta | Text output | $1.10 per 1M tokens | $1.20 per 1M tokens | +9% |
| Muse Voice Transcribe 1.0Meta | Audio input | $0.18 per hour | $0.00005 per second | Same price |
| MythoMax 13Bgryphe | Text input | $0.06 per 1M tokens | $0.08 per 1M tokens | +33% |
| Text output | $0.06 per 1M tokens | $0.11 per 1M tokens | +83% | |
| Nano Banana (Gemini 2.5 Flash Image)Google | Image input, Google AI Studio Priority | $0.54 per 1M tokens | Not listed | No longer listed |
| Image output, Google AI Studio Priority | $54.00 per 1M tokens | Not listed | No longer listed | |
| Image input, Google AI Studio Flex | $0.15 per 1M tokens | Not listed | No longer listed | |
| Image output, Google AI Studio Flex | $15.00 per 1M tokens | Not listed | No longer listed | |
| Image input, Google AI Studio | $0.30 per 1M tokens | Not listed | No longer listed | |
| Image output, Google AI Studio | $30.00 per 1M tokens | Not listed | No longer listed | |
| Nano Banana Pro (Gemini 3 Pro Image Preview)Google | Image input, Google AI Studio Flex | $1.00 per 1M tokens | Not listed | No longer listed |
| Image output, Google AI Studio Flex | $60.00 per 1M tokens | Not listed | No longer listed | |
| Nemotron 3 Nano 30B A3BNVIDIA | Text input | $0.05 per 1M tokens | $0.06 per 1M tokens | +20% |
| Text output | $0.20 per 1M tokens | $0.24 per 1M tokens | +20% | |
| Cache read | $0.03 per 1M tokens | Not listed | No longer listed | |
| Nemotron 3 SuperNVIDIA | Text input | $0.085 per 1M tokens | $0.08 per 1M tokens | -6% |
| Text output | $0.40 per 1M tokens | $0.45 per 1M tokens | +13% | |
| Nemotron 3 UltraNVIDIA | Text input | $0.625 per 1M tokens | $0.60 per 1M tokens | -4% |
| Text output | $3.125 per 1M tokens | $2.40 per 1M tokens | -23% | |
| Cache read | $0.1875 per 1M tokens | $0.12 per 1M tokens | -36% | |
| Nemotron 3.5 LightningNVIDIA | Text input | $0.08 per 1M tokens | $0.07 per 1M tokens | -12% |
| Nova-3Deepgram | Audio input | $0.0043 per minute | $0.00007167 per second | Same price |
| Audio input, multilingual | Not listed | $0.00008667 per second | New charge | |
| Parakeet TDT 0.6B v3NVIDIA | Audio input | $0.0015 per minute | $0.000025 per second | Same price |
| Qwen3 14BQwen | Text input | $0.2275 per 1M tokens | $0.12 per 1M tokens | -47% |
| Text output | $0.91 per 1M tokens | $0.24 per 1M tokens | -74% | |
| Qwen3 235B A22B Instruct 2507Qwen | Text input | $0.0875 per 1M tokens | $0.09 per 1M tokens | +3% |
| Text output | $0.35 per 1M tokens | $0.55 per 1M tokens | +57% | |
| Cache read | $0.0175 per 1M tokens | Not listed | No longer listed | |
| Qwen3 235B A22B Thinking 2507Qwen | Text input | $0.23 per 1M tokens | $0.45 per 1M tokens | +96% |
| Text output | $2.30 per 1M tokens | $3.50 per 1M tokens | +52% | |
| Qwen3 30B A3B Instruct 2507Qwen | Text input | $0.09 per 1M tokens | $0.10 per 1M tokens | +11% |
| Qwen3 Next 80B A3B InstructQwen | Text input | $0.09 per 1M tokens | $0.10 per 1M tokens | +11% |
| Cache read | Not listed | $0.07 per 1M tokens | New charge | |
| Qwen3 VL 30B A3B ThinkingQwen | Text input | $0.20 per 1M tokens | $0.29 per 1M tokens | +45% |
| Text output | $2.40 per 1M tokens | $1.00 per 1M tokens | -58% | |
| Qwen3 VL 8B InstructQwen | Text input | $0.117 per 1M tokens | $0.25 per 1M tokens | +114% |
| Text output | $0.455 per 1M tokens | $0.75 per 1M tokens | +65% | |
| Cache read | Not listed | $0.12 per 1M tokens | New charge | |
| Qwen3.5-27BQwen | Text input | $0.195 per 1M tokens | $0.26 per 1M tokens | +33% |
| Text output | $1.56 per 1M tokens | $2.60 per 1M tokens | +67% | |
| Qwen3.5-35B-A3BQwen | Text input | $0.3125 per 1M tokens | $0.08 per 1M tokens | -74% |
| Text output | $1.25 per 1M tokens | $0.75 per 1M tokens | -40% | |
| Cache read | $0.1563 per 1M tokens | $0.04 per 1M tokens | -74% | |
| Qwen3.6 27BQwen | Text input | $0.30 per 1M tokens | $0.32 per 1M tokens | +7% |
| Text output | $2.00 per 1M tokens | $3.20 per 1M tokens | +60% | |
| Cache read | $0.03 per 1M tokens | Not listed | No longer listed | |
| Qwen3.6 35B A3BQwen | Text output | $0.90 per 1M tokens | $0.95 per 1M tokens | +6% |
| Cache read | $0.05 per 1M tokens | $0.10 per 1M tokens | +100% | |
| Qwen3.8 27BQwen | Text input | $0.214 per 1M tokens | $0.04 per 1M tokens | -81% |
| Text output | $2.55 per 1M tokens | $2.30 per 1M tokens | -10% | |
| Cache read | $0.15 per 1M tokens | $0.0198 per 1M tokens | -87% | |
| Qwen3.8 FlashQwen | Cache write | $0.20 per 1M tokens | Not listed | No longer listed |
| Qwen3.8 Max (0902)Qwen | Cache write | $2.50 per 1M tokens | Not listed | No longer listed |
| Schematron V2 SmallInference.net | Cache read | Not listed | $0.05 per 1M tokens | New charge |
| Schematron V2 TurboInference.net | Cache read | Not listed | $0.03 per 1M tokens | New charge |
| Voxtral Mini TranscribeMistral | Audio input | $0.003 per minute | $0.00005 per second | Same price |
| Whisper 1OpenAI | Audio input | $0.006 per minute | $0.0001 per second | Same price |
Where the rates come from
Each snapshot is OpenRouter's public models API on that date, the same data behind our model pricing pages, kept in the site's source history. The log grows with every refresh. To see what the current rates mean for a real job in pounds, try AI task costs.