Claude Fable 5 vs DeepSeek V4 Flash
At a Glance
| Compare | Claude Fable 5Anthropic |  DeepSeek V4 FlashDeepSeek |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v2.5 | #2 of 4695.6 score · 3/3 sources · complete | UnrankedNot in the 46-model eligible cohort |
| CostLower is better · Published-token output estimate | #44 of 44$1.01 per LiveBench case | UnrankedNot in the 44-model eligible cohort |
| EfficiencyHigher is better · MM Efficiency v1.5 | #29 of 3847.8 score · 3/3 sources · complete | UnrankedNot in the 38-model eligible cohort |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $10.00Anthropic ↗ · Sep 3, 2026 | $0.0868Openrouter ↗ · Aug 28, 2026 |
| Output priceFrom · USD / 1M tokens | $50.00Anthropic ↗ · Sep 3, 2026 | $0.1736Openrouter ↗ · Aug 28, 2026 |
| Context windowMaximum documented tokens | 1,000K | 1,049K |
| Model facts checked | Aug 28, 2026View model evidence → | Aug 28, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
| Benchmark | Claude Fable 5 | DeepSeek-V4-Flash |
|---|---|---|
| ARC-AGI-1verified-v1-ba05d69f6453 · verified_score · leader | 98.50100% of row best · percent · Claude Fable 5 (XHigh) | 89.0090% of row best · percent · DeepSeek V4 Flash 0731 (Max) |
| ARC-AGI-2verified-v2-6c676fa3e9af · verified_score · leader | 89.17100% of row best · percent · Claude Fable 5 (Max) | 61.3969% of row best · percent · DeepSeek V4 Flash 0731 (Max) |
| LMArena Agent Arenaagent-2026-09-15-d25aabda0010 · outcome_score · leader | 8.81100% of row best · score · Claude Fable 5 (High); 95% CI [7.56791873, 10.05963763]; sessions 38293; observations 2061291; rank 5 | 1.8094% of row best · score · Deepseek V4 Flash (High) (20260731); 95% CI [1.06225523, 2.53222539]; sessions 64482; observations 6405377; rank 22 |
| LMArena Text Arenatext-2026-09-13-d25aabda0010 · arena_rating · leader | 1,492.63100% of row best · rating · claude-fable-5; 95% CI [1487.86770992, 1497.38399139]; votes 30057; rank 7 | 1,431.7996% of row best · rating · deepseek-v4-flash; 95% CI [1427.66110387, 1435.91557810]; votes 48887; rank 83 |
| LiveBench2026-06-25 · overall · leader | 86.55100% of row best · percent · claude-fable-5-max-effort · 20,255 output tokens / case | 69.6781% of row best · percent · deepseek-v4-flash · 34,434 output tokens / case |
| ToneBench2026-09-11-10-task-4ef099199c9c · overall_score · unverified | 89.06100% of row best · points · Claude Fable 5 (xhigh) · 18,129 output tokens / case | 78.0088% of row best · points · DeepSeek V4 Flash (xhigh) · 12,709 output tokens / case |
| Overall ResultCounted from the protocol-matched rows above | 5 benchmark winsOverall lead | 0 benchmark wins |
Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.
Side-by-Side Facts
| Field | Claude Fable 5 | DeepSeek-V4-Flash |
|---|---|---|
| Developer | Anthropic | DeepSeek |
| Family | Claude 5 | Deepseek V4 Flash |
| Model | Claude Fable 5 | DeepSeek-V4-Flash |
| Version | Claude Fable 5 | DeepSeek-V4-Flash |
| Lifecycle | active | retired |
| Released | 2026-06-09 | 2026-04-24 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Text |
| Context window | 1,000K | 1,049K |
| Total parameters | Unknown | 290.9B |
| Active parameters | Unknown | 13B |
| License | Unknown | mit |
| Open weights | No | Yes |
| API available | Yes | Yes |
| Self-hostable | No | Yes |
| Provider access | Anthropic (Standard), Deepinfra (Standard), Openrouter (Standard) | DeepSeek (Standard), Deepinfra (Standard), Fireworks Ai (Standard), Hugging Face (Standard), Openrouter (Standard) |
| Capabilities | chat, generation, reasoning, tools | chat, generation, reasoning |
Claude Fable 5 Capabilities
DeepSeek V4 Flash Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
Claude Fable 5Anthropic | vs |  GPT-6 AstraOpenAI | cross-developer peersimage, text |
Claude Fable 5Anthropic | vs | Claude Fable 5.1Anthropic | family variantsimage, text |
Claude Fable 5Anthropic | vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
Claude Fable 5Anthropic | vs | DeepSeek-V4.1-FlashDeepSeek | cross-developer peersimage, text |
Claude Fable 5Anthropic | vs | Grok 4.6xAI | cross-developer peersimage, text |
Claude Fable 5Anthropic | vs |  Qwen3.8-MaxQwen | cross-developer peersimage, text |
Claude Fable 5Anthropic | vs |  Kimi-K3Moonshot AI | cross-developer peersimage, text |
 MiniMax-M3MiniMax | vs | Claude Fable 5Anthropic | cross-developer peersimage, text |
Claude Fable 5Anthropic | vs |  GLM-5.3Z.ai | cross-developer peerstext |
Claude Fable 5Anthropic | vs |  Hy4 previewTencent | cross-developer peerstext |
Claude Fable 5Anthropic | vs | Seed 2.1 ProByteDance Seed | cross-developer peersimage, text |
Claude Fable 5Anthropic | vs |  Mistral Large 3Mistral AI | cross-developer peersimage, text |
Primary Evidence
Sources and Freshness
Questions
Claude Fable 5 vs DeepSeek V4 Flash FAQs
Is Claude Fable 5 or DeepSeek V4 Flash better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Claude Fable 5 and DeepSeek V4 Flash, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Claude Fable 5 or DeepSeek V4 Flash?+
Claude Fable 5 is $10.00 and DeepSeek V4 Flash is $0.0868 per million tokens, so DeepSeek V4 Flash is cheaper on this metric. Claude Fable 5 is $50.00 and DeepSeek V4 Flash is $0.1736 per million tokens, so DeepSeek V4 Flash is cheaper on this metric.
Which has a larger context window, Claude Fable 5 or DeepSeek V4 Flash?+
DeepSeek V4 Flash has the larger sourced context window. Claude Fable 5 supports 1,000K and DeepSeek V4 Flash supports 1,049K.
Which performs better in benchmarks, Claude Fable 5 or DeepSeek V4 Flash?+
Claude Fable 5 leads the current overall benchmark count. The result uses 5 protocol-matched benchmarks from 3 publishers; it is not a universal quality score.
Can Claude Fable 5 or DeepSeek V4 Flash be self-hosted?+
DeepSeek V4 Flash is the only model in this pair currently marked as self-hostable. Claude Fable 5 is not marked open weight; DeepSeek V4 Flash is open weight.
Can Claude Fable 5 and DeepSeek V4 Flash understand images?+
Claude Fable 5 is documented with image input; DeepSeek V4 Flash is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Claude Fable 5 or DeepSeek V4 Flash?+
Neither has a larger sourced maximum output. Claude Fable 5 is 128K and DeepSeek V4 Flash is —.
Do Claude Fable 5 and DeepSeek V4 Flash support reasoning and tool use?+
Claude Fable 5: reasoning, tool calling, and image input. DeepSeek V4 Flash: reasoning. Feature support does not establish relative quality.
Which is available from more inference providers, Claude Fable 5 or DeepSeek V4 Flash?+
Claude Fable 5 has 3 sourced provider routes; DeepSeek V4 Flash has 5, so DeepSeek V4 Flash has broader tracked availability.
Which offers better value, Claude Fable 5 or DeepSeek V4 Flash?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.