LLM·Dex

Claude 3.5 Haiku vs Jamba 1.5 Mini

A complete head-to-head: pricing, context window, benchmarks, modality coverage, and openness, with a programmatic verdict synthesized from the underlying data.

Verdict by category
  • PriceJamba 1.5 Mini

    Jamba 1.5 Mini is roughly 10.0× cheaper on output tokens ($0.40 vs $4.00 per 1M).

  • Context windowJamba 1.5 Mini

    Jamba 1.5 Mini accepts 256K tokens vs 200K, 1.3× the room for long documents and codebases.

  • BenchmarksTie

    No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores.

  • ModalitiesClaude 3.5 Haiku

    Claude 3.5 Haiku supports 2 modalities (text, vision) vs 1 for Jamba 1.5 Mini.

  • OpennessJamba 1.5 Mini

    Jamba 1.5 Mini ships open weights (Jamba Open Model License); Claude 3.5 Haiku is API-only.

On balance Jamba 1.5 Mini edges ahead, winning 3 of 5 categories against Claude 3.5 Haiku's 1. Jamba 1.5 Mini is roughly 10.0× cheaper on output tokens ($0.40 vs $4.00 per 1M). Jamba 1.5 Mini accepts 256K tokens vs 200K, 1.3× the room for long documents and codebases.

No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores. They differ in modality coverage, Claude 3.5 Haiku handles text, vision while Jamba 1.5 Mini handles text, which can be the deciding factor before you even look at benchmarks. Jamba 1.5 Mini ships open weights (Jamba Open Model License); Claude 3.5 Haiku is API-only.

Claude 3.5 Haiku is the newer of the two, released 2 months after Jamba 1.5 Mini, which usually means a more recent knowledge cutoff and updated safety post-training. Claude 3.5 Haiku is usually picked for customer support and code completion workloads, while Jamba 1.5 Mini sees more deployments in long context and summarization. If pricing matters more than every last benchmark point, run the numbers in the calculator below before committing.

Side-by-side specs

SpecClaude 3.5 HaikuJamba 1.5 Mini
ProviderAnthropicAI21
ReleasedNov 2024Aug 2024
Modalitiestext, visiontext
Context window200K tokens256K tokens
Max output,,
Input · 1M$0.80 / 1M tokens$0.20 / 1M tokens
Output · 1M$4.00 / 1M tokens$0.40 / 1M tokens
Knowledge cutoff,,
Open weightsNoYes (Jamba Open Model License)
API availableYesYes

Pricing at scale

What you'd actually pay at typical workloads. Numbers come from each model's published per-million-token rates.

  • Light usage, 100k in / 50k out per day$8.40 vs $1.20
  • Heavy usage, 1M in / 500k out per day$84.00 vs $12.00
  • RAG workload, 5M in / 200k out per day$144 vs $32.40

Light usage, 100k in / 50k out per day: $8.40 vs $1.20 per month, model B comes out ahead. Heavy usage, 1M in / 500k out per day: $84.00 vs $12.00 per month, model B comes out ahead. RAG workload, 5M in / 200k out per day: $144 vs $32.40 per month, model B comes out ahead.

Price calculator

Estimated spend for the listed models at your usage. Numbers are derived from each model's published per-million-token rates.

  • Claude 3.5 Haiku$0.280
  • Jamba 1.5 Mini$0.040

Benchmarks compared

Only sourced numbers. Where a benchmark is missing for one model we show the available value rather than fabricating the other.

Benchmark scores not yet available. We only publish numbers we can source from official model cards or independent leaderboards, see methodology.
Pick Claude 3.5 Haiku if

Claude 3.5 Haiku fits when…

  • Fast
  • Cheap for Anthropic
  • Strong code at small size
  • Multimodal needs covering vision.
Pick Jamba 1.5 Mini if

Jamba 1.5 Mini fits when…

  • 256k context at small-model price
  • Hybrid SSM-Transformer is efficient on long inputs
  • Open weights for self-hosting
  • Cost-sensitive workloads, 10.0× cheaper than Claude 3.5 Haiku on output tokens.
  • Self-hosting and on-prem requirements, open weights (Jamba Open Model License).
Don't want either?

Consider Claude Opus 4.7

Anthropic's mid-2026 flagship, ahead on SWE-bench, agent reliability, and writing quality.

Frequently asked

  • Is Claude 3.5 Haiku or Jamba 1.5 Mini cheaper?
    Jamba 1.5 Mini is cheaper at $0.40 / 1M tokens per million output tokens, vs $4.00 / 1M tokens for Claude 3.5 Haiku.
  • Which has the larger context window?
    Jamba 1.5 Mini accepts 256K tokens vs 200K for Claude 3.5 Haiku.
  • Is Claude 3.5 Haiku or Jamba 1.5 Mini better for coding?
    Both Claude 3.5 Haiku and Jamba 1.5 Mini are competitive on coding benchmarks. See each model's individual spec page for HumanEval and SWE-bench scores where published. For an opinionated pick, consult our Best LLM for Coding ranking.
  • Are either of these models open source?
    Jamba 1.5 Mini ships open weights (Jamba Open Model License). Claude 3.5 Haiku is API-only.
  • When were Claude 3.5 Haiku and Jamba 1.5 Mini released?
    Claude 3.5 Haiku was released by Anthropic on 2024-11-04. Jamba 1.5 Mini was released by AI21 on 2024-08-22.
Friday digest

The week's AI launches, in your inbox.

One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.