Rankings
The top five of every output type and every benchmark. Each row carries the card price, the cheapest list price and the cheapest effective price with the provider that has it.
text 412 models
| # | model | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Ox Alpha stealth/ox-alpha | 4.168T | 1 | – | – | – | 85% | 20 | 2026-08-20 |
| 2 | DeepSeek: DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | 2.701T | 41 | $0.3 | $0.006 · 0.5 relace/fp4 | $0.0045 deepinfra/fp8/flex | 93% | 597 | 2026-10-17 |
| 3 | Tencent: Hy4 tencent/hy4 | 1.202T | 1 | $0.417 | $0.417 · 1.2505 tencent/fp4 | $0.0816 tencent/fp4 | 95% | 47 | 2026-11-04 |
| 4 | DeepSeek: DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | 831.32B | 32 | $0.15 | $0.006 · 0.5 relace/fp4 | $0.0048 primeintellect | 90% | 224 | 2026-09-10 |
| 5 | Z.ai: GLM 5.3 Flash z-ai/glm-5.3-flash | 806.12B | 40 | $0.15 | $0.0399 · 0.0784 relace/fp4 | $0.0204 primeintellect | 84% | 146 | 2026-08-26 |
image 66 models
| # | model | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|
| 1 | ByteDance Seed: Seedream 5.0 Flash bytedance-seed/seedream-5-0-flash | 336.2M | 1 | – | $0.018 /image Image Output seed | – | 0% | 0 | 2026-10-01 |
| 2 | Google: Nano Banana 2 (Gemini 3.1 Flash Image) google/gemini-3.1-flash-image | 213.6M | 2 | – | $0.5 · 3.0 google-ai-studio | $0.4998 google-ai-studio | 1% | 0 | 2026-06-18 |
| 3 | Google: Nano Banana 2.1 google/gemini-nano-banana-2.1 | 167.0M | 1 | – | $1.5 · 7.5 google-ai-studio | $1.4999 google-ai-studio | 9% | 0 | 2026-10-06 |
| 4 | OpenAI: GPT Image 2.5 Sunburst openai/gpt-image-2.5-sunburst | 138.2M | 1 | $8.0 | $8.0 · 8.0 openai | $7.0032 openai | 0% | 0 | 2026-09-09 |
| 5 | OpenAI: GPT Image 2.5 Flare openai/gpt-image-2.5-flare | 92.1M | 1 | $8.0 | $8.0 · 8.0 openai | $7.2149 openai | 0% | 0 | 2026-09-09 |
video 34 models
| # | model | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Google: Gemini Omni 1.1 Flash google/gemini-omni-1.1-flash | 3.6M | 1 | – | $0.0337925 /second Video (with audio) google-ai-studio | $1.4998 google-ai-studio | 0% | 0 | 2026-11-04 |
| 2 | Google: Gemini Omni 1.2 Flash google/gemini-omni-1.2-flash | 90032 | 1 | – | $0.023172 /second Video (with audio) google-ai-studio | $1.4998 google-ai-studio | 0% | 0 | 2026-11-05 |
| 3 | OpenAI: Sora 2 Pro openai/sora-2-pro | – | 1 | – | $0.30 /second Video Output openai | – | – | 0 | 2026-03-23 |
| 4 | TBC: mischief 1 tbc/mischief-1 | – | 1 | – | $0.005 /second Video Output ambient | – | – | 0 | 2026-10-30 |
| 5 | SpaceXAI: Grok Imagine Video 1.5 Lite x-ai/grok-imagine-video-1.5-lite | – | 1 | – | $0.02 /second Video Output xai | – | – | 0 | 2026-10-06 |
speech 38 models
| # | model | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Google: Gemini 3.8 Flash TTS google/gemini-3.8-flash-tts | 15.0M | 2 | – | $0.5 · 9.0 google-ai-studio | $0.4915 google-ai-studio | 0% | – | 2026-09-23 |
| 2 | Google: Gemini 3.8 Flash Lite TTS google/gemini-3.8-flash-lite-tts | 9.0M | 2 | – | $0.5 · 6.0 google-ai-studio | $0.4936 google-ai-studio | 0% | – | 2026-09-23 |
| 3 | Google: Gemini 3.1 Flash TTS Preview google/gemini-3.1-flash-tts-preview | 6.8M | 1 | – | $1.0 · 20.0 google-vertex | $0.9799 google-vertex/us-central1 | 0% | – | 2026-04-24 |
| 4 | Fish Audio: Drama 3 fish-audio/drama-3 | 1.7M | 1 | $10.0 | $0.00001 /M UTF-8 bytes UTF-8 Bytes fish-audio | – | 0% | – | 2026-10-13 |
| 5 | hexgrad: Kokoro 82M hexgrad/kokoro-82m | 981814 | 2 | – | $0.00000062 /M characters Characters deepinfra/us | – | 0% | – | 2026-04-23 |
transcription 32 models
| # | model | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|
| 1 | OpenAI: GPT-4o Mini Transcribe openai/gpt-4o-mini-transcribe | 12.1M | 1 | $1.25 | $1.25 · 5.0 openai | $1.249 openai | 0% | – | 2026-05-01 |
| 2 | Google: Gemini 3.5 Transcribe google/gemini-3.5-transcribe | 4.8M | 1 | – | $2.0 · 12.0 google-ai-studio | $2.0 google-ai-studio | 0% | – | 2026-09-25 |
| 3 | OpenAI: GPT-4o Transcribe openai/gpt-4o-transcribe | 1.5M | 1 | $2.5 | $2.5 · 10.0 openai | $2.4988 openai | 0% | – | 2026-04-27 |
| 4 | Mistral: Voxtral Mini Transcribe mistralai/voxtral-mini-transcribe | 356108 | 1 | $50.0 | $0.00005 /second Audio Seconds mistral | $150.366 mistral | 0% | – | 2026-05-15 |
| 5 | Mistral: Voxtral Mini Transcribe 3 mistralai/voxtral-mini-transcribe-3-0 | 345122 | 1 | $64.1667 | $0.0000583333 /second Audio Seconds mistral/zdr | $4.6954 mistral/zdr | 0% | – | 2026-10-20 |
embeddings 40 models
| # | model | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Perplexity: Embed V1 0.6B perplexity/pplx-embed-v1-0.6b | 12.85B | 1 | $0.004 | $0.004 · 0.0 perplexity/int8 | $0.0039 perplexity/int8 | 0% | – | 2026-03-16 |
| 2 | OpenAI: Text Embedding 3 Small openai/text-embedding-3-small | 6.57B | 2 | $0.02 | $0.02 · 0.0 azure | $0.0192 azure | 0% | – | 2025-10-30 |
| 3 | Qwen: Qwen3 Embedding 8B qwen/qwen3-embedding-8b | 6.01B | 3 | – | $0.01 · 0.0 deepinfra | $0.0098 nebius/bf16 | 0% | – | 2025-10-28 |
| 4 | BAAI: bge-m3 baai/bge-m3 | 3.78B | 2 | – | $0.01 · 0.0 deepinfra/fp32 | $0.0094 deepinfra/fp32 | 0% | – | 2025-11-18 |
| 5 | Qwen: Qwen3 Embedding 4B qwen/qwen3-embedding-4b | 2.26B | 1 | – | $0.02 · 0.0 deepinfra/us | $0.0199 deepinfra/us | 0% | – | 2025-10-28 |
rerank 13 models
| # | model | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|
| 1 | VoyageAI by MongoDB: rerank-2.5-lite mongodb/rerank-2.5-lite | 4.64B | 1 | – | – | – | 0% | – | 2026-07-27 |
| 2 | VoyageAI by MongoDB: rerank-2.5 mongodb/rerank-2.5 | 1.31B | 1 | – | – | – | 0% | – | 2026-07-27 |
| 3 | VoyageAI by MongoDB: rerank-3-lite mongodb/rerank-3-lite | 854.1M | 1 | – | – | – | 0% | – | 2026-09-30 |
| 4 | VoyageAI by MongoDB: rerank-3 mongodb/rerank-3 | 474.8M | 1 | – | – | – | 0% | – | 2026-09-30 |
| 5 | Qwen3 Reranker 8B qwen/qwen3-reranker-8b | 449.4M | 2 | – | – | – | 0% | – | 2026-08-13 |
decisions 30 models
| # | model | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|
| 1 | TypeSafe: Jev 1.13 typesafe/jev-1.13 | 126.35B | 1 | $0.042 | $0.042 · 0.0 typesafe | $0.0418 typesafe | 0% | 0 | 2026-09-18 |
| 2 | TypeSafe: Jev 1.14 typesafe/jev-1.14 | 84.34B | 1 | $0.042 | $0.042 · 0.0 typesafe | $0.0418 typesafe | 0% | 0 | 2026-10-14 |
| 3 | Perplexity: Decider V1.2 perplexity/pplx-decider-v1.2 | 28.43B | 2 | $0.02 | $0.019 · 0.0 makora/fp16 | $0.0186 makora/fp16 | 0% | 0 | 2026-10-16 |
| 4 | LiquidAI: d1.1 liquid/d1.1 | 6.29B | 1 | $0.02 | $0.02 · 0.0 liquid | $0.0198 liquid | 0% | 0 | 2026-10-27 |
| 5 | LiquidAI: d1-ultra liquid/d1-ultra | 2.18B | 1 | $0.042 | $0.042 · 0.0 liquid | $0.0417 liquid | 0% | 0 | 2026-10-15 |
audio 4 models
| # | model | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|
| 1 | OpenAI: GPT Audio Mini openai/gpt-audio-mini | 17.3M | 1 | $0.6 | $0.6 · 2.4 openai | $0.5995 openai | 0% | 102 | 2026-01-19 |
| 2 | OpenAI: GPT Audio openai/gpt-audio | 4.8M | 1 | $2.5 | $2.5 · 10.0 openai | $9.7539 openai | 0% | 95 | 2026-01-19 |
| 3 | Google: Lyria 3 Pro Preview google/lyria-3-pro-preview | 815427 | 1 | – | $0.08 /song Song Generation google-ai-studio | – | 0% | 4 | 2026-03-30 |
| 4 | Google: Lyria 3 Clip Preview google/lyria-3-clip-preview | 337577 | 1 | – | $0.04 /song Song Generation google-ai-studio | – | 0% | 12 | 2026-03-30 |
gpqa-diamond 158 models
| # | model | gpqa-diamond | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Google: Gemini 4 Argon google/gemini-4-argon | 96.5 | $0.0947 | 33.36B | 2 | – | $1.0 · 5.0 google-ai-studio/flex | $0.4977 google-ai-studio/flex | 65% | 44 | 2026-10-13 |
| 2 | Google: Gemini 3.8 Flash google/gemini-3.8-flash | 95.6 | $0.0682 | 66.11B | 2 | – | $0.375 · 1.875 google-vertex/global/flex | $0.1745 google-ai-studio/flex | 65% | 83 | 2026-09-02 |
| 3 | OpenAI: GPT-6 Astra Pro openai/gpt-6-astra-pro | 95.5 | $0.3326 | 1.27B | 2 | $10.0 | $5.0 · 25.0 openai/flex | $1.4761 openai/flex | 67% | 59 | 2026-09-04 |
| 4 | Google: Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | 94.5 | $0.202 | 4.37B | 2 | – | $1.0 · 6.0 google-ai-studio/flex | $0.6497 google-ai-studio/flex | 25% | 84 | 2026-02-19 |
| 5 | OpenAI: GPT-6.1 Sol openai/gpt-6.1-sol | 94.4 | $0.0214 | 120.16B | 3 | $2.0 | $1.0 · 5.0 openai/flex | $0.111 openai/flex | 90% | 77 | 2026-09-29 |
tau-bench-airline 152 models
| # | model | tau-bench-airline | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | OpenAI: GPT-5.1 openai/gpt-5.1 | 80.0 | $0.3931 | 999.5M | 2 | $1.25 | $0.625 · 5.0 openai/flex | $0.2471 openai/flex | 75% | 154 | 2025-11-13 |
| 2 | Anthropic: Claude Fable 5 anthropic/claude-fable-5 | 79.4 | $0.8491 | 1.8B | 5 | $10.0 | $10.0 · 50.0 azure | $3.27 anthropic | 53% | 62 | 2026-06-09 |
| 3 | inclusionAI: Ling 3.1 Flash inclusionai/ling-3.1-flash | 79.3 | $0.0315 | 2.47B | 2 | – | $0.045 · 0.135 deepinfra/fp4 | $0.0186 novita | 73% | 52 | 2026-10-02 |
| 4 | Anthropic: Claude Fable 5.1 anthropic/claude-fable-5.1 | 79.2 | $0.7162 | 7.57B | 4 | $10.0 | $10.0 · 50.0 amazon-bedrock | $2.1435 anthropic | 79% | 65 | 2026-09-01 |
| 5 | Anthropic: Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | 78.8 | $0.1593 | 90.35B | 5 | $2.0 | $2.0 · 10.0 amazon-bedrock | $0.3958 google-vertex/us | 79% | 116 | 2026-09-28 |
coding 137 models
| # | model | coding | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Anthropic: Claude Fable 5.1 anthropic/claude-fable-5.1 | 81.6 | – | 7.57B | 4 | $10.0 | $10.0 · 50.0 amazon-bedrock | $2.1435 anthropic | 79% | 65 | 2026-09-01 |
| 2 | OpenAI: GPT-5.6 Sol openai/gpt-5.6-sol | 78.3 | – | 10.41B | 3 | $4.0 | $2.0 · 10.0 openai/flex | $1.2602 azure/us | 69% | 165 | 2026-07-09 |
| 3 | Anthropic: Claude Opus 5 anthropic/claude-opus-5 | 78.0 | – | 10.0B | 5 | $5.0 | $5.0 · 25.0 azure/global | $1.1673 anthropic | 66% | 85 | 2026-07-24 |
| 4 | OpenAI: GPT-6 Astra openai/gpt-6-astra | 76.9 | – | 12.76B | 3 | $10.0 | $5.0 · 25.0 openai/flex | $1.0295 openai/flex | 71% | 73 | 2026-09-04 |
| 5 | SpaceXAI: Grok 4.6 x-ai/grok-4.6 | 76.8 | – | 2.75B | 2 | $2.0 | $2.0 · 6.0 xai/zdr | $0.7725 amazon-bedrock/us-west-2 | 80% | 84 | 2026-08-12 |
design-website 133 models
| # | model | design-website | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Meta: Muse Wonder meta/muse-wonder | 1368.0 | – | 3.01B | 2 | $4.0 | $4.0 · 20.0 google-vertex/global | $0.6407 meta | 87% | 123 | 2026-10-12 |
| 2 | Meta: Muse Spark 1.3 meta/muse-spark-1.3 | 1353.0 | – | 3.33B | 2 | $1.25 | $1.25 · 4.25 google-vertex/global | $0.3469 meta | 82% | 167 | 2026-09-02 |
| 3 | MoonshotAI: Kimi K3 moonshotai/kimi-k3 | 1332.0 | – | 59.5B | 22 | $3.0 | $0.153 · 16.0 wafer/fast | $0.1521 wafer/fast | 90% | 105 | 2026-07-16 |
| 4 | Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5 | 1325.0 | – | 265.23B | 5 | $4.0 | $4.0 · 20.0 azure/global | $0.3991 google-vertex/europe | 90% | 199 | 2026-09-22 |
| 5 | MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | 1320.0 | – | 127.05B | 17 | $2.0 | $0.304 · 8.1953 relace/fp4 | $0.2079 relace/fp4 | 89% | 117 | 2026-10-23 |
design-codecategories 127 models
| # | model | design-codecategories | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Meta: Muse Wonder meta/muse-wonder | 1384.0 | – | 3.01B | 2 | $4.0 | $4.0 · 20.0 google-vertex/global | $0.6407 meta | 87% | 123 | 2026-10-12 |
| 2 | Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5 | 1383.0 | – | 265.23B | 5 | $4.0 | $4.0 · 20.0 azure/global | $0.3991 google-vertex/europe | 90% | 199 | 2026-09-22 |
| 3 | OpenAI: GPT-6.1 Sol openai/gpt-6.1-sol | 1355.0 | – | 120.16B | 3 | $2.0 | $1.0 · 5.0 openai/flex | $0.111 openai/flex | 90% | 77 | 2026-09-29 |
| 4 | MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | 1350.0 | – | 127.05B | 17 | $2.0 | $0.304 · 8.1953 relace/fp4 | $0.2079 relace/fp4 | 89% | 117 | 2026-10-23 |
| 5 | MoonshotAI: Kimi K3 moonshotai/kimi-k3 | 1349.0 | – | 59.5B | 22 | $3.0 | $0.153 · 16.0 wafer/fast | $0.1521 wafer/fast | 90% | 105 | 2026-07-16 |
design-gamedev 126 models
| # | model | design-gamedev | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5 | 1432.0 | – | 265.23B | 5 | $4.0 | $4.0 · 20.0 azure/global | $0.3991 google-vertex/europe | 90% | 199 | 2026-09-22 |
| 2 | OpenAI: GPT-6.1 Sol openai/gpt-6.1-sol | 1410.0 | – | 120.16B | 3 | $2.0 | $1.0 · 5.0 openai/flex | $0.111 openai/flex | 90% | 77 | 2026-09-29 |
| 3 | Meta: Muse Wonder meta/muse-wonder | 1409.0 | – | 3.01B | 2 | $4.0 | $4.0 · 20.0 google-vertex/global | $0.6407 meta | 87% | 123 | 2026-10-12 |
| 4 | MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | 1406.0 | – | 127.05B | 17 | $2.0 | $0.304 · 8.1953 relace/fp4 | $0.2079 relace/fp4 | 89% | 117 | 2026-10-23 |
| 5 | Anthropic: Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | 1397.0 | – | 90.35B | 5 | $2.0 | $2.0 · 10.0 amazon-bedrock | $0.3958 google-vertex/us | 79% | 116 | 2026-09-28 |
design-uicomponent 123 models
| # | model | design-uicomponent | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | 1393.0 | – | 127.05B | 17 | $2.0 | $0.304 · 8.1953 relace/fp4 | $0.2079 relace/fp4 | 89% | 117 | 2026-10-23 |
| 2 | Anthropic: Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | 1384.0 | – | 90.35B | 5 | $2.0 | $2.0 · 10.0 amazon-bedrock | $0.3958 google-vertex/us | 79% | 116 | 2026-09-28 |
| 3 | Meta: Muse Wonder meta/muse-wonder | 1379.0 | – | 3.01B | 2 | $4.0 | $4.0 · 20.0 google-vertex/global | $0.6407 meta | 87% | 123 | 2026-10-12 |
| 4 | Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5 | 1372.0 | – | 265.23B | 5 | $4.0 | $4.0 · 20.0 azure/global | $0.3991 google-vertex/europe | 90% | 199 | 2026-09-22 |
| 5 | Meta: Muse Spark 1.3 meta/muse-spark-1.3 | 1346.0 | – | 3.33B | 2 | $1.25 | $1.25 · 4.25 google-vertex/global | $0.3469 meta | 82% | 167 | 2026-09-02 |
design-dataviz 121 models
| # | model | design-dataviz | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5 | 1390.0 | – | 265.23B | 5 | $4.0 | $4.0 · 20.0 azure/global | $0.3991 google-vertex/europe | 90% | 199 | 2026-09-22 |
| 2 | Z.ai: GLM 5.1 z-ai/glm-5.1 | 1366.0 | – | 1.68B | 18 | $1.4 | $0.9 · 2.9 chutes/fp8 | $0.3379 chutes/fp8 | 62% | 137 | 2026-04-07 |
| 3 | Anthropic: Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | 1362.0 | – | 90.35B | 5 | $2.0 | $2.0 · 10.0 amazon-bedrock | $0.3958 google-vertex/us | 79% | 116 | 2026-09-28 |
| 4 | MoonshotAI: Kimi K3 moonshotai/kimi-k3 | 1348.0 | – | 59.5B | 22 | $3.0 | $0.153 · 16.0 wafer/fast | $0.1521 wafer/fast | 90% | 105 | 2026-07-16 |
| 5 | Anthropic: Claude Fable 5.1 anthropic/claude-fable-5.1 | 1342.0 | – | 7.57B | 4 | $10.0 | $10.0 · 50.0 amazon-bedrock | $2.1435 anthropic | 79% | 65 | 2026-09-01 |
design-3d 119 models
| # | model | design-3d | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5 | 1467.0 | – | 265.23B | 5 | $4.0 | $4.0 · 20.0 azure/global | $0.3991 google-vertex/europe | 90% | 199 | 2026-09-22 |
| 2 | MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | 1445.0 | – | 127.05B | 17 | $2.0 | $0.304 · 8.1953 relace/fp4 | $0.2079 relace/fp4 | 89% | 117 | 2026-10-23 |
| 3 | Meta: Muse Wonder meta/muse-wonder | 1438.0 | – | 3.01B | 2 | $4.0 | $4.0 · 20.0 google-vertex/global | $0.6407 meta | 87% | 123 | 2026-10-12 |
| 4 | OpenAI: GPT-6.1 Sol openai/gpt-6.1-sol | 1433.0 | – | 120.16B | 3 | $2.0 | $1.0 · 5.0 openai/flex | $0.111 openai/flex | 90% | 77 | 2026-09-29 |
| 5 | Anthropic: Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | 1403.0 | – | 90.35B | 5 | $2.0 | $2.0 · 10.0 amazon-bedrock | $0.3958 google-vertex/us | 79% | 116 | 2026-09-28 |
agentic 105 models
| # | model | agentic | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Anthropic: Claude Fable 5.1 anthropic/claude-fable-5.1 | 58.0 | – | 7.57B | 4 | $10.0 | $10.0 · 50.0 amazon-bedrock | $2.1435 anthropic | 79% | 65 | 2026-09-01 |
| 2 | Anthropic: Claude Opus 5 anthropic/claude-opus-5 | 56.5 | – | 10.0B | 5 | $5.0 | $5.0 · 25.0 azure/global | $1.1673 anthropic | 66% | 85 | 2026-07-24 |
| 3 | Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | 56.0 | – | 8.76B | 1 | – | $2.0 · 6.0 alibaba | $0.3589 alibaba | 92% | 38 | 2026-09-03 |
| 4 | Meta: Muse Spark 1.3 meta/muse-spark-1.3 | 55.5 | – | 3.33B | 2 | $1.25 | $1.25 · 4.25 google-vertex/global | $0.3469 meta | 82% | 167 | 2026-09-02 |
| 5 | Z.ai: GLM 5.3 z-ai/glm-5.3 | 53.4 | – | 244.46B | 39 | $1.4 | $0.0699 · 1.4 wafer/us | $0.069 wafer/us | 90% | 207 | 2026-08-18 |
design-svg 88 models
| # | model | design-svg | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Google: Gemini 4 Argon google/gemini-4-argon | 1330.0 | – | 33.36B | 2 | – | $1.0 · 5.0 google-ai-studio/flex | $0.4977 google-ai-studio/flex | 65% | 44 | 2026-10-13 |
| 2 | MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | 1326.0 | – | 127.05B | 17 | $2.0 | $0.304 · 8.1953 relace/fp4 | $0.2079 relace/fp4 | 89% | 117 | 2026-10-23 |
| 3 | Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5 | 1322.0 | – | 265.23B | 5 | $4.0 | $4.0 · 20.0 azure/global | $0.3991 google-vertex/europe | 90% | 199 | 2026-09-22 |
| 4 | Meta: Muse Spark 1.3 meta/muse-spark-1.3 | 1321.0 | – | 3.33B | 2 | $1.25 | $1.25 · 4.25 google-vertex/global | $0.3469 meta | 82% | 167 | 2026-09-02 |
| 5 | Anthropic: Claude Opus 5 anthropic/claude-opus-5 | 1308.0 | – | 10.0B | 5 | $5.0 | $5.0 · 25.0 azure/global | $1.1673 anthropic | 66% | 85 | 2026-07-24 |
intelligence 79 models
| # | model | intelligence | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Anthropic: Claude Fable 5.2 anthropic/claude-fable-5.2 | 64.6 | – | 34.94B | 4 | $8.0 | $8.0 · 40.0 amazon-bedrock | $0.6247 amazon-bedrock | 90% | 181 | 2026-11-09 |
| 2 | Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5 | 59.1 | – | 265.23B | 5 | $4.0 | $4.0 · 20.0 azure/global | $0.3991 google-vertex/europe | 90% | 199 | 2026-09-22 |
| 3 | OpenAI: GPT-6 Astra openai/gpt-6-astra | 56.9 | – | 12.76B | 3 | $10.0 | $5.0 · 25.0 openai/flex | $1.0295 openai/flex | 71% | 73 | 2026-09-04 |
| 4 | OpenAI: GPT-6.1 Sol openai/gpt-6.1-sol | 54.6 | – | 120.16B | 3 | $2.0 | $1.0 · 5.0 openai/flex | $0.111 openai/flex | 90% | 77 | 2026-09-29 |
| 5 | Anthropic: Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | 54.5 | – | 90.35B | 5 | $2.0 | $2.0 · 10.0 amazon-bedrock | $0.3958 google-vertex/us | 79% | 116 | 2026-09-28 |
design-asciiart 70 models
| # | model | design-asciiart | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5 | 1362.0 | – | 265.23B | 5 | $4.0 | $4.0 · 20.0 azure/global | $0.3991 google-vertex/europe | 90% | 199 | 2026-09-22 |
| 2 | Anthropic: Claude Opus 5 anthropic/claude-opus-5 | 1358.0 | – | 10.0B | 5 | $5.0 | $5.0 · 25.0 azure/global | $1.1673 anthropic | 66% | 85 | 2026-07-24 |
| 3 | Anthropic: Claude Fable 5 anthropic/claude-fable-5 | 1324.0 | – | 1.8B | 5 | $10.0 | $10.0 · 50.0 azure | $3.27 anthropic | 53% | 62 | 2026-06-09 |
| 4 | Anthropic: Claude Fable 5.1 anthropic/claude-fable-5.1 | 1321.0 | – | 7.57B | 4 | $10.0 | $10.0 · 50.0 amazon-bedrock | $2.1435 anthropic | 79% | 65 | 2026-09-01 |
| 5 | MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | 1295.0 | – | 127.05B | 17 | $2.0 | $0.304 · 8.1953 relace/fp4 | $0.2079 relace/fp4 | 89% | 117 | 2026-10-23 |
design-graphicdesign 12 models
| # | model | design-graphicdesign | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Sourceful: Riverflow V2.5 Pro sourceful/riverflow-v2.5-pro | 1411.0 | – | 1.2M | 1 | – | $0.13 /image Image Output sourceful | – | 0% | 0 | 2026-06-04 |
| 2 | Microsoft AI: MAI-Image-2.6 microsoft/mai-image-2.6 | 1330.0 | – | 1.8M | 1 | – | $5.0 · 0.0 azure | $7.4577 azure | 0% | 0 | 2026-09-04 |
| 3 | Microsoft AI: MAI-Image-2.6 Flash microsoft/mai-image-2.6-flash | 1308.0 | – | 1.2M | 1 | – | $1.75 · 0.0 azure | $2.2259 azure | 0% | 0 | 2026-09-04 |
| 4 | Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) google/gemini-3.1-flash-image-preview | 1261.0 | – | 22.2M | 1 | – | $0.5 · 3.0 google-ai-studio | $0.4998 google-ai-studio | 4% | 0 | 2026-02-26 |
| 5 | Google: Nano Banana Pro (Gemini 3 Pro Image Preview) google/gemini-3-pro-image-preview | 1251.0 | – | 35.8M | 1 | – | $1.0 · 6.0 google-ai-studio/global/flex | $0.9984 google-ai-studio/global/flex | 5% | 0 | 2025-11-20 |
design-image 12 models
| # | model | design-image | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Sourceful: Riverflow V2.5 Pro sourceful/riverflow-v2.5-pro | 1349.0 | – | 1.2M | 1 | – | $0.13 /image Image Output sourceful | – | 0% | 0 | 2026-06-04 |
| 2 | Microsoft AI: MAI-Image-2.6 microsoft/mai-image-2.6 | 1302.0 | – | 1.8M | 1 | – | $5.0 · 0.0 azure | $7.4577 azure | 0% | 0 | 2026-09-04 |
| 3 | Microsoft AI: MAI-Image-2.6 Flash microsoft/mai-image-2.6-flash | 1290.0 | – | 1.2M | 1 | – | $1.75 · 0.0 azure | $2.2259 azure | 0% | 0 | 2026-09-04 |
| 4 | Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) google/gemini-3.1-flash-image-preview | 1259.0 | – | 22.2M | 1 | – | $0.5 · 3.0 google-ai-studio | $0.4998 google-ai-studio | 4% | 0 | 2026-02-26 |
| 5 | Google: Nano Banana Pro (Gemini 3 Pro Image Preview) google/gemini-3-pro-image-preview | 1226.0 | – | 35.8M | 1 | – | $1.0 · 6.0 google-ai-studio/global/flex | $0.9984 google-ai-studio/global/flex | 5% | 0 | 2025-11-20 |
design-logo 12 models
| # | model | design-logo | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Sourceful: Riverflow V2.5 Pro sourceful/riverflow-v2.5-pro | 1297.0 | – | 1.2M | 1 | – | $0.13 /image Image Output sourceful | – | 0% | 0 | 2026-06-04 |
| 2 | Microsoft AI: MAI-Image-2.6 microsoft/mai-image-2.6 | 1292.0 | – | 1.8M | 1 | – | $5.0 · 0.0 azure | $7.4577 azure | 0% | 0 | 2026-09-04 |
| 3 | Microsoft AI: MAI-Image-2.6 Flash microsoft/mai-image-2.6-flash | 1268.0 | – | 1.2M | 1 | – | $1.75 · 0.0 azure | $2.2259 azure | 0% | 0 | 2026-09-04 |
| 4 | Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) google/gemini-3.1-flash-image-preview | 1263.0 | – | 22.2M | 1 | – | $0.5 · 3.0 google-ai-studio | $0.4998 google-ai-studio | 4% | 0 | 2026-02-26 |
| 5 | Microsoft AI: MAI-Image-2.5 microsoft/mai-image-2.5 | 1248.0 | – | 8.7M | 1 | – | $5.0 · 0.0 azure | $6.5444 azure | 0% | 0 | 2026-06-02 |
design-imageediting 8 models
| # | model | design-imageediting | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Sourceful: Riverflow V2.5 Pro sourceful/riverflow-v2.5-pro | 1290.0 | – | 1.2M | 1 | – | $0.13 /image Image Output sourceful | – | 0% | 0 | 2026-06-04 |
| 2 | Microsoft AI: MAI-Image-2.6 Flash microsoft/mai-image-2.6-flash | 1238.0 | – | 1.2M | 1 | – | $1.75 · 0.0 azure | $2.2259 azure | 0% | 0 | 2026-09-04 |
| 3 | Google: Nano Banana Pro (Gemini 3 Pro Image Preview) google/gemini-3-pro-image-preview | 1230.0 | – | 35.8M | 1 | – | $1.0 · 6.0 google-ai-studio/global/flex | $0.9984 google-ai-studio/global/flex | 5% | 0 | 2025-11-20 |
| 4 | Microsoft AI: MAI-Image-2.6 microsoft/mai-image-2.6 | 1225.0 | – | 1.8M | 1 | – | $5.0 · 0.0 azure | $7.4577 azure | 0% | 0 | 2026-09-04 |
| 5 | Microsoft AI: MAI-Image-2.5 microsoft/mai-image-2.5 | 1205.0 | – | 8.7M | 1 | – | $5.0 · 0.0 azure | $6.5444 azure | 0% | 0 | 2026-06-02 |
design-audiorealism 6 models
| # | model | design-audiorealism | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Microsoft AI: MAI-Voice-2 microsoft/mai-voice-2 | 1208.0 | – | 151886 | 1 | – | $0.000022 /M characters Characters azure | – | 0% | – | 2026-06-02 |
| 2 | Microsoft AI: MAI-Voice-2-Flash microsoft/mai-voice-2-flash | 1137.0 | – | 147625 | 1 | – | $0.000015 /M characters Characters azure | – | 0% | – | 2026-07-23 |
| 3 | Google: Gemini 3.8 Flash TTS google/gemini-3.8-flash-tts | 1080.0 | – | 15.0M | 2 | – | $0.5 · 9.0 google-ai-studio | $0.4915 google-ai-studio | 0% | – | 2026-09-23 |
| 4 | Fish Audio: Drama 3 fish-audio/drama-3 | 958.0 | – | 1.7M | 1 | $10.0 | $0.00001 /M UTF-8 bytes UTF-8 Bytes fish-audio | – | 0% | – | 2026-10-13 |
| 5 | Fish Audio: S2.1 Pro fish-audio/s2.1-pro | 953.0 | – | 215178 | 1 | $15.0 | $0.000015 /M UTF-8 bytes UTF-8 Bytes fish-audio | – | 0% | – | 2026-07-29 |
design-text-to-speech 3 models
| # | model | design-text-to-speech | $ / task | tokens / week | providers | card $/M in | cheapest list | cheapest effective | cache hit | t/s | listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Google: Gemini 3.8 Flash TTS google/gemini-3.8-flash-tts | 1468.0 | – | 15.0M | 2 | – | $0.5 · 9.0 google-ai-studio | $0.4915 google-ai-studio | 0% | – | 2026-09-23 |
| 2 | Microsoft AI: MAI-Voice-2 microsoft/mai-voice-2 | 1164.0 | – | 151886 | 1 | – | $0.000022 /M characters Characters azure | – | 0% | – | 2026-06-02 |
| 3 | Microsoft AI: MAI-Voice-2-Flash microsoft/mai-voice-2-flash | 1123.0 | – | 147625 | 1 | – | $0.000015 /M characters Characters azure | – | 0% | – | 2026-07-23 |